CN117409027B

CN117409027B - Image searching method, device, product, equipment and medium

Info

Publication number: CN117409027B
Application number: CN202311295252.7A
Authority: CN
Inventors: 李嘉昕
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2023-09-28
Filing date: 2023-09-28
Publication date: 2024-12-17
Anticipated expiration: 2043-09-28
Also published as: WO2025066865A1; CN117409027A

Abstract

The application discloses an image searching method, device, product, equipment and medium, which comprises the steps of carrying out contour searching on a target image along N searching directions, obtaining conversion data of contours searched along each of the N searching directions, wherein the first searching direction is any searching method, the conversion data of the contours searched along the first searching direction comprise indication data respectively associated with each searching direction except the first searching direction, the indication data are used for indicating the contours searched along the first searching direction in contour searching in the associated searching directions, the contour searching of the indication contours corresponding to each searching direction is skipped in each of the N searching directions to obtain the contours searched along each searching direction, the indication contours are contours indicated by the indication data, and the contours in the target image comprise the contours searched along the N searching directions. By adopting the method and the device, the searching efficiency of the outline in the target image can be improved.

Description

Image searching method, device, product, equipment and medium

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image searching method, apparatus, product, device, and medium.

Background

In many scenarios, a search for contours contained in an image is typically involved, so that a corresponding object (i.e., a target) to which the contours in the image belong can be quickly located by the searched contours.

In the prior art, the contour searching is usually performed on the image according to a specified direction, and when the image is relatively large or the contours contained in the image are relatively large, the contour searching efficiency on the image is very low.

Disclosure of Invention

The application provides an image searching method, an image searching device, a product, equipment and a medium, which can improve the searching efficiency of contours in target images.

In one aspect, the present application provides an image searching method, including:

Performing contour search on the target image along N search directions, wherein N is an integer greater than 1;

The method comprises the steps of acquiring conversion data of contours searched along each of N search directions, wherein any one of the N search directions is a first search direction, and the conversion data of the contours searched along the first search direction comprises indication data respectively associated with each search direction except the first search direction, wherein the indication data are used for indicating the contours searched along the first search direction in contour searching in the associated search directions;

In the process of searching the outline of the target image, skipping the outline searching of the indicated outline corresponding to each searching direction in N searching directions to obtain the outline searched along each searching direction in the N searching directions;

Wherein the contours in the target image include contours searched along the N search directions.

In one aspect, the present application provides an image search apparatus, comprising:

the searching module is used for carrying out contour searching on the target image along N searching directions, wherein N is an integer greater than 1;

the acquisition module is used for acquiring conversion data of the profile searched along each of the N search directions; the conversion data of the profile searched along the first search direction comprises indication data respectively associated with each search direction except the first search direction, wherein the indication data is used for indicating the profile searched along the first search direction in the profile search in the associated search direction;

The searching module is also used for skipping the contour searching of the indication contour corresponding to each searching direction in the N searching directions in the contour searching process of the target image to obtain the contour searched along each searching direction in the N searching directions;

Optionally, the searching module performs contour searching on the target image along N searching directions, including:

performing binarization processing on the target image to obtain a binary image of the target image;

and carrying out contour searching on the binary image along N searching directions.

Optionally, the searching module performs a contour searching process on the binary image along a first searching direction, including:

sequentially searching pixel points in the binary image along a first searching direction;

When the first pixel point is searched, performing contour searching based on the first pixel point to search and obtain a target contour where the first pixel point is located;

the first pixel points are pixel points meeting the contour initial search condition in the first search direction.

Optionally, one contour searched along the first search direction has one conversion data, the target contour is any contour searched along the first search direction, and any indication data associated with one search direction except the first search direction is indication data of the target contour in the one search direction;

The obtaining module generates a flow of conversion data of the target contour searched along the first searching direction, including:

Acquiring contour starting points of the target contour in all search directions except the first search direction in the binary image;

Generating indication data of the target contour in each search direction based on contour starting points of the target contour in the search directions except the first search direction;

determining the indication data of the target contour in each search direction except the first search direction as conversion data of the target contour;

The first pixel point which accords with the contour starting search condition in the searching direction on the searched target contour in the contour searching in the searching direction is the first pixel point which accords with the contour starting search condition in the searching direction.

Optionally, the obtaining module generates the manner of indicating data in each search direction based on the outline starting point of the target outline in each search direction except the first search direction, including:

Acquiring pixel coordinates of a target contour in each searching direction except the first searching direction, wherein the pixel coordinates of a contour starting point of the target contour in the binary image are respectively acquired;

Pixel coordinates of a start point of a contour of the target in each of the search directions other than the first search direction are determined as indicating data of the contour of the target in the each search direction.

Optionally, any one of the N search directions except the first search direction is the second search direction;

The searching module skips the contour searching of the indication contour corresponding to each searching direction in the N searching directions in the contour searching process of the target image to obtain the contour searched along each searching direction in the N searching directions, and the method comprises the following steps:

skipping the process of searching for the contour based on the second pixel point in the second searching direction when the second pixel point meeting the contour starting searching condition in the second searching direction is searched for along the second searching direction and the second pixel point is detected to belong to the pixel point indicated by the indication data of the target contour in the second searching direction, and

And acquiring each pixel point on the target contour based on the indication data of the target contour in the second searching direction, and skipping the contour searching process based on each pixel point on the target contour except the second pixel point in the second searching direction.

Optionally, when the target contour is searched along the first search direction or after the target contour is searched, the apparatus is further configured to:

Acquiring pixel coordinates of each pixel point on the searched target contour in the binary image respectively;

Adopting the indication data of the target contour in the second search direction to correlate and record the pixel coordinates of each pixel point on the target contour;

Based on the indication data of the target contour in the second search direction, acquiring each pixel point on the target contour comprises the following steps:

and acquiring pixel coordinates of each pixel point on the target contour of the associated record based on the indication data of the target contour in the second search direction.

Optionally, the pixel value of the pixel point in the binary image is a first pixel value or a second pixel value, and the first pixel value is greater than the second pixel value;

the target contour is of a hole boundary type or an outer boundary type, and if the target contour is of a hole boundary type, the pixel values of the pixel points in the target contour are all second pixel values;

If the target contour is of the outer boundary type, the pixel values of the pixel points in the target contour are all first pixel values, and the pixel values of the pixel points outside the target contour and adjacent to the target contour are second pixel values.

Alternatively, the first search direction is a reverse search direction or a forward search direction, wherein the reverse search direction is a direction of searching pixels meeting the contour initial search condition in the first search direction in the binary image from left to right and from top to bottom, and the forward search direction is a direction of searching pixels meeting the contour initial search condition in the first search direction in the binary image from right to left and from bottom to top;

the first pixel point is expressed as (i, j), the pixel value of the first pixel point is expressed as f (i, j), i is the longitudinal coordinate of the first pixel point in the binary image, j is the transverse coordinate of the first pixel point in the binary image, and both i and j are non-negative integers;

If the target contour is of a hole boundary type and the first search direction is a reverse search direction, the contour start search condition in the first search direction is that f (i, j) is equal to a first pixel value and f (i, j+1) is equal to a second pixel value;

If the target contour is of a hole boundary type and the first search direction is a forward search direction, the contour start search condition in the first search direction is that f (i, j) is equal to a first pixel value and f (i, j-1) is equal to a second pixel value;

if the target contour is of the outer boundary type and the first search direction is the reverse search direction, the contour start search condition in the first search direction is that f (i, j) is equal to the first pixel value and f (i, j-1) is equal to the second pixel value;

If the target contour is of the outer boundary type and the first search direction is the forward search direction, the contour start search condition in the first search direction is that f (i, j) is equal to the first pixel value and f (i, j+1) is equal to the second pixel value.

Optionally, the searching module performs contour searching based on the first pixel point to search and obtain a target contour where the first pixel point is located, including:

in the binary image, a plurality of pixel points which are mutually connected in series and have the pixel values of the first pixel value are searched from the first pixel point;

and determining the searched target contour based on the first pixel point and the searched plurality of pixel points.

Optionally, the device is further configured to:

identifying a contour searched for the target image in the target image;

in the target image, the image within the identified contour is segmented, which belongs to the local image in the target image.

In one aspect the application provides a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the method of one aspect of the application.

An aspect of the application provides a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the method of the above aspect.

According to one aspect of the present application, there is provided a computer program product comprising a computer program stored in a computer readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program to cause the computer device to execute the method provided in various optional manners of the above aspect and the like.

The method and the device can perform contour searching on the target image along N searching directions, N is an integer larger than 1, conversion data of contours searched along each of the N searching directions can be obtained, any one of the N searching directions is a first searching direction, the conversion data of the contours searched along the first searching direction comprise indication data respectively associated with each searching direction except the first searching direction, the indication data are used for indicating the contours searched along the first searching direction in contour searching in the associated searching directions, and contour searching of the indication contours corresponding to each searching direction in each of the N searching directions can be skipped in the contour searching process of the target image, so that the contours searched along each searching direction in the N searching directions are obtained, the indication contours corresponding to the first searching direction comprise the contours indicated by the indication data associated with the first searching direction, and the contours in the target image comprise the contours searched along the N searching directions. Therefore, the method provided by the application can simultaneously perform contour searching on the target image along a plurality of searching directions (namely N searching directions), and in the process of performing contour searching along the plurality of searching directions, the contour searching of the contours searched in other searching directions can be skipped through the associated indication information in each searching direction, so that the same contour in the target image can not be repeatedly searched in each searching direction, and the efficiency of searching the contours in the target image can be greatly improved.

Drawings

In order to more clearly illustrate the application or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained from them without inventive effort for a person skilled in the art.

Fig. 1 is a schematic structural diagram of a network architecture according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a profile search scenario provided by an embodiment of the present application;

Fig. 3 is a schematic flow chart of an image searching method according to an embodiment of the present application;

Fig. 4a to fig. 4c are schematic structural diagrams of a pixel neighborhood according to an embodiment of the present application;

FIGS. 5 a-5 b are schematic diagrams of a reverse contour search scenario provided by an embodiment of the present application;

FIGS. 6 a-6 b are schematic diagrams of a scenario for determining a starting point of a contour according to an embodiment of the present application;

FIG. 7 is a schematic view of a scene of image segmentation according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an image searching apparatus according to an embodiment of the present application;

fig. 9 is a schematic structural view of another image searching apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a computer device according to the present application.

Detailed Description

The following description of the embodiments of the present application will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the application are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The application relates to an artificial intelligence related technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include, for example, sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, pre-training model technologies, operation/interaction systems, mechatronics, and the like. The pre-training model is also called a large model and a basic model, and can be widely applied to all large-direction downstream tasks of artificial intelligence after fine adjustment. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The application mainly relates to Computer Vision technology (CV) in artificial intelligence. The computer vision is a science for researching how to make a machine "see", and more specifically, a camera and a computer are used to replace human eyes to identify and measure targets and perform graphic processing, so that the computer is processed into images more suitable for human eyes to observe or transmit to an instrument to detect. As a scientific discipline, computer vision research-related theory and technology has attempted to build artificial intelligence systems that can acquire information from images or multidimensional data. The large model technology brings important changes for the development of computer vision technology, and pre-training models in the vision fields of swin-transducer (a self-focusing neural network), viT (vision transformer, a vision model), V-MOE (a sparse hybrid model), MAE (a self-coding model) and the like can be quickly and widely applied to specific downstream tasks through fine tuning.

The computer vision technology generally comprises technologies such as image processing, image recognition, image semantic understanding, image retrieval, optical Character Recognition (OCR), video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D (3D) technology, virtual reality, augmented reality, synchronous positioning, map construction and the like, and common biological feature recognition technologies such as face recognition, fingerprint recognition and the like.

In the application, the contours in the images can be searched rapidly and accurately mainly through computer vision technology, and particularly, the related description in the following embodiments can be seen.

Firstly, it should be noted that all data collected by the present application (such as related data of a target image for performing a contour search) are collected under the condition that an object (such as a user, an organization or an enterprise) to which the data belongs agrees and authorizes, and the collection, the use and the processing of the related data need to comply with related laws and regulations and standards of related countries and regions.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a network architecture according to an embodiment of the present application. As shown in fig. 1, the network architecture may include a server 200 and a cluster of terminal devices, which may include one or more terminal devices, the number of which will not be limited here. As shown in fig. 1, the plurality of terminal devices may specifically include a terminal device 1, a terminal device 2, a terminal device 3, a terminal device n, and as shown in fig. 1, the terminal device 2, the terminal device 3, the terminal device n may be connected to the server 200 through a network, so that each terminal device may interact with the server 200 through the network connection.

The server 200 shown in fig. 1 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligence platforms, and the like. The terminal equipment can be intelligent terminals such as intelligent mobile phones, tablet computers, notebook computers, desktop computers, intelligent televisions and the like. A specific description of an embodiment of the present application will be made below taking communication between the terminal device 1 and the server 200 as an example.

Referring to fig. 2, fig. 2 is a schematic diagram of a scene of contour searching according to an embodiment of the application. The user may upload a target image to be subjected to contour search in the terminal device 1, and further, the terminal device 1 may transmit the target image to the server 200 to request the server 200 to perform contour search on the target image. The process of performing the contour search on the target image by the server 200 may include:

The server 200 may perform contour searching on the target image in a plurality of search directions at the same time, such as the plurality of search directions may include a top-to-bottom and left-to-right direction (may be referred to as a reverse search direction), and a bottom-to-top and right-to-left direction (may be referred to as a forward search direction) herein.

Wherein in the course of performing contour searching on the target image in the reverse search direction, conversion data (which may be denoted as conversion data 1) of the contour searched in the reverse search direction may be acquired, the conversion data 1 may be used to indicate the contour searched in the reverse search direction in the contour searching in the forward search direction, and in the same way, in the course of performing contour searching on the target image in the forward search direction, conversion data (which may be denoted as conversion data 2) of the contour searched in the forward search direction may be acquired, the conversion data 2 may be used to indicate the contour searched in the forward search direction in the contour searching in the reverse search direction.

Further, in the contour search in the reverse search direction, the search process for the contour indicated by the conversion data 2 (i.e., the search process for the contour that has been searched in the forward search direction) may be skipped, and in the contour search in the forward search direction, the search process for the contour indicated by the conversion data 1 (i.e., the search process for the contour that has been searched in the reverse search direction) may be skipped.

By the above process, the contour 1 and the contour 2 in the target image can be searched in the reverse search direction, and the contour 3 and the contour 4 in the target image can be searched in the forward search direction. All contours in the target image may include contours 1 and 2 searched in the reverse search direction, and contours 3 and 4 searched in the forward search direction.

It will be appreciated that, based on the difference in complexity of the contours in the target image and the difference in positions of the contours, the time consumed for searching the corresponding contours along each search direction may be different, so the number of contours searched along different search directions may also be different, and the specific number of contours searched in each search direction may be determined according to the actual application scenario, which is not limited.

After searching the contours in the target image, the server 200 may identify each searched contour in the target image, and may return the target image with the contour identified to the terminal device 1, where the terminal device 1 may perform further service processing according to the actual application requirement by identifying the target image with the contour, for example, may divide the image in the contour identified in the target image to obtain a local image of the target image in the contour, where the local image may belong to the foreground image divided in the target image, and so on.

By adopting the method provided by the application, the contour searching can be carried out on the image along a plurality of searching directions simultaneously (in parallel), in the process of carrying out the contour searching on the image along each searching direction simultaneously, the conversion data of the contour searched along each searching direction can be obtained, and the searching process of the contour searched in other searching directions can be skipped in each searching direction based on the conversion data, so that the searching efficiency of the contour in the image can be greatly improved, and each contour in the image can be quickly searched and obtained.

Referring to fig. 3, fig. 3 is a flowchart of an image searching method according to an embodiment of the present application. The execution body in the embodiment of the present application may be an image searching device, where the image searching device may be one computer device or a cluster of computer devices formed by a plurality of computer devices, and the computer device may be a server, a terminal device, or other devices, which is not limited to this. As shown in fig. 3, the method may include:

and step S101, performing contour search on the target image along N search directions, wherein N is an integer greater than 1.

Optionally, N search directions may be set according to an actual application scenario, where N is an integer greater than 1, i.e., N search directions are multiple search directions, and N is at least equal to 2. The N search directions are directions in which contour search is performed on the target image, that is, the N search directions are directions in which contour search is performed on the target image.

The image searching device can acquire a target image, the target image can be any image needing contour searching, and the specific image of the target image can be determined according to the actual application scene. For example, the target image may be an image requiring foreground segmentation, a foreground image in the target image (e.g., a local image of an object in the target image) may be segmented by a contour searched for the target image, the target image may be an image requiring detection of a target object (e.g., an object) may be segmented by a contour searched for the target image, or the target image may be an image requiring detection of a target region (e.g., a region of an organ in a medical field) may be extracted by a contour searched for the target image.

From the above, it can be appreciated that the present application can be applied to any scene where contour searching (co-detection) of an image is required. The specific application to what scene can be determined according to the actual application scene, and the method is not limited.

The image searching apparatus may perform contour searching on the target image simultaneously (i.e., synchronously, which may be understood as parallel) along the above-mentioned N search directions to search out contours in the target image. In order to perform contour search on the target image more accurately, binarization processing may be performed on the target image to obtain a binarized image (may be referred to as a binary image) of the target image, where the dimension of the binary image is the same as that of the target image, and the pixels in the target image and the binary image may be in one-to-one correspondence (the pixel coordinates of the pixels in the target image and the binary image that are in one-to-one correspondence may be the same), that is, the pixel after binarization processing is performed on one pixel in the target image is one pixel in the binary image.

As the name implies, the range of pixel values of the pixel points in the binary image includes two pixel values, where the two pixel values may be 0 and 1,0 represents black and 1 represents white, that is, the binary image may be a black-and-white image, and the pixel value of one pixel point in the binary image may be a pixel value of 0 or a pixel value of 1. The pixel value 1 may be referred to as a first pixel value and the pixel value 0 may be referred to as a second pixel value, the first pixel value being greater than the second pixel value. Accordingly, the pixel value of each pixel point in the binary image may be the first pixel value or the second pixel value.

Accordingly, the image searching apparatus performs contour searching on the target image in N search directions, which may mean performing contour searching on the binary image of the target image in the N search directions. Wherein the contour searches of the respective search directions may be performed separately.

Alternatively, the N search directions may include a forward search direction and a reverse search direction, the reverse search direction may refer to a search direction in which the binary image is searched for contours from left to right and from top to bottom, and the forward search direction may refer to a search direction in which the binary image is searched for contours from right to left and from bottom to top.

In some possible implementations, the N search directions may further include other search directions, such as a left-to-right and a bottom-to-top search direction, or/and a right-to-left and a top-to-bottom search direction, etc., which may be specifically determined according to an actual application scenario, and which search directions are specifically included in the N search directions may be determined according to an actual application scenario, and the principle of processing between the N search directions is the same, so the following procedure of the present application may be described by taking the N search directions including a forward search direction and a reverse search direction as an example, which may be specifically described as follows.

And step S102, acquiring conversion data of the contours searched along each of N search directions, wherein any one of the N search directions is a first search direction, and the conversion data of the contours searched along the first search direction comprises indication data respectively associated with each search direction except the first search direction, wherein the indication data is used for indicating the contours searched along the first search direction in the associated contour search directions.

Alternatively, the image search apparatus may acquire conversion data of the contours searched in each of the N search directions, wherein each time a contour is searched in each of the N search directions, the conversion data of the contour may be generated in real time. It will be appreciated that a profile searched in one search direction may have a transformation data for use in profile searches in other search directions to indicate the profile searched in that search direction, as described in more detail below.

Any one of the N search directions may be referred to as a first search direction, i.e., the first search direction may be any one of the N search directions. The following description will be made mainly by taking the first search direction as an example for describing the relevant characteristics of the contour search along the search direction, and it is to be understood that, since the first search direction may be any search direction, the contour search in each search direction may have the relevant characteristics described in the contour search in the first search direction.

The conversion data of the contour searched along the first search direction may include indication data respectively associated with each of the N search directions other than the first search direction, the indication data being usable in the contour search in the associated search direction to indicate the contour searched along the first search direction.

Wherein the contours searched along the first search direction may include contours that have not been searched in other search directions when searched in the first search direction.

In the application, the pixel points in the binary image, which respectively meet the contour starting search conditions of each search direction, can be searched along each search direction, and then the contour where the pixel points are located (namely the contour belongs to) is searched by taking the pixel points as starting points. Here, taking the process of searching to obtain the corresponding contour as an example for performing contour searching on the binary image along the first searching direction, the process may include:

The image searching device can search the pixel points in the binary image along the first searching direction in sequence, and when the first pixel point is searched, contour searching can be performed based on the first pixel point so as to search and obtain the contour of the first pixel point. The contour where the first pixel point is located may be referred to as a target contour, and the target contour may be any contour searched along the first search direction.

The first pixel point may be a pixel point that meets the contour start search condition in the first search direction, and the first pixel point may be a first pixel point that meets the contour start search condition in the first search direction on the target contour searched along the first search direction, so the first pixel point may be referred to as a contour start point of the target contour in the first search direction.

First, all the points on the contour are pixels having the first pixel value, that is, the contour may be composed of pixels having all the pixel values of 1. The target contour may be a contour of a hole boundary type, which may refer to a contour having an internal pixel value of 0, or a contour of an outer boundary type, which may refer to a contour having an internal pixel value of 1 and an externally adjacent pixel value of 0.

Therefore, if the target contour is a contour of a hole boundary type (may be referred to as a hole boundary contour), the pixel values of the pixel points within the target contour may all be the second pixel value (i.e., pixel value 0). If the target contour is an outer boundary contour (may be referred to as an outer boundary contour), the pixel values of the pixel points within the target contour may be all the first pixel value (i.e., pixel value 1), and the pixel values of the pixel points outside the target contour (next to) adjacent to the target contour may be the second pixel value (i.e., pixel value 0).

Alternatively, the first search direction may be the above-described reverse search direction or the above-described forward search direction, which may refer to a direction in which each row of pixels in the binary image is sequentially searched from left to right and from top to bottom to search for pixels conforming to the contour start search condition in the first search direction, and the forward search direction may refer to a direction in which each row of pixels in the binary image is sequentially searched from right to left and from bottom to top to search for pixels conforming to the contour start search condition in the first search direction.

The first pixel point may be expressed as (i, j), and the pixel value of the first pixel point may be expressed as f (i, j), where i and i are non-negative integers, i may be a longitudinal coordinate (e.g., a number of rows, which may be counted from 0 or 1) of the first pixel point in the binary image, and j may be a transverse coordinate (e.g., a number of columns, which may also be counted from 0 or 1) of the first pixel point in the binary image.

Thus, based on the above description of the outline of the hole boundary type and the outline of the outer boundary type, it can be appreciated that if the target outline is of the hole boundary type and the first search direction is the reverse search direction, the outline start search condition in the first search direction to which the first pixel point conforms may be f (i, j) equal to the first pixel value and f (i, j+1) equal to the second pixel value. In other words, if the contour of the hole boundary type needs to be searched in the reverse search direction in the target image, a pixel point with a pixel value of 1 and a pixel value of 0 of one pixel point adjacent to the right may be searched in the binary image, and the contour where the pixel point is located may be searched starting with the pixel point.

If the target contour is of the hole boundary type and the first search direction is the forward search direction, the contour start search condition in the first search direction, which the first pixel point conforms to, may be that f (i, j) is equal to the first pixel value and f (i, j-1) is equal to the second pixel value. In other words, if the contour of the hole boundary type needs to be searched in the forward search direction in the target image, a pixel point with a pixel value of 1 and a pixel value of 0 of one pixel point adjacent to the left can be searched in the binary image, and the contour where the pixel point is located can be searched starting with the pixel point.

More, if the target contour is of the outer boundary type and the first search direction is the reverse search direction, the contour start search condition in the first search direction, which is met by the first pixel point, may be that f (i, j) is equal to the first pixel value and f (i, j-1) is equal to the second pixel value. In other words, if the contour of the outer boundary type needs to be searched in the reverse search direction in the target image, a pixel point with a pixel value of 1 and a pixel value of 0 of one pixel point adjacent to the left may be searched in the binary image, and the contour where the pixel point is located may be searched starting with the pixel point.

If the target contour is of the outer boundary type and the first search direction is the forward search direction, the contour start search condition in the first search direction, which the first pixel conforms to, may be that f (i, j) is equal to the first pixel value and f (i, j+1) is equal to the second pixel value. In other words, if the contour of the outer boundary type needs to be searched in the forward search direction in the target image, a pixel point with a pixel value of 1 and a pixel value of 0 of one pixel point adjacent to the right may be searched in the binary image, and the contour where the pixel point is located may be searched starting with the pixel point.

Where f (i, j-1) may refer to a pixel value of a pixel point in the same row as and one column to the left of the first pixel point, and f (i, j+1) may refer to a pixel value of a pixel point in the same row as and one column to the right of the first pixel point.

Further, when the image searching device searches the first pixel point according to the contour start searching condition in the first searching direction, the image searching device may start performing contour searching based on the first pixel point to search and obtain a target contour where the first pixel point is located, and the process may include:

The image searching device may search for a plurality of pixels in the binary image, where the pixels are connected in series from the first pixel and each have a first pixel value (i.e. pixel value 1), and further determine, based on the first pixel and the plurality of pixels obtained by searching from the first pixel, a searched target contour, where the target contour is formed by the first pixel and the plurality of pixels obtained by searching from the first pixel, and the specific process is described below.

To facilitate understanding of the specific procedure of contour searching, the following explains the meaning of the relevant coordinates involved in contour searching through table 1:

Pixel coordinates (i, j)	Contour starting point
		Pixel coordinates (i 1, j 1)	Initial search base point
Pixel coordinates (i 2, j 2)	Starting boundary point for contour search
		Pixel coordinates (i 3, j 3)	Center point of each neighborhood search
Pixel coordinates (i 4, j 4)	Results of each neighborhood search
		Pixel coordinates (i 5, j 5)	Conversion coordinates

TABLE 1

If the first search direction is the reverse search direction, the process of searching in the reverse search direction to obtain the target contour may include that after the contour starting point (i.e., the first pixel point) of the target contour in the first search direction is searched, the first pixel point is firstly subjected to initial search and then to cyclic search, each time of cyclic search may search to obtain a pixel point on the target contour, and finally, the searched whole target contour may be formed through the first pixel point and the search result obtained by each time of cyclic search, as described below.

Search phase 1 for target contours in reverse search direction initializing search phase for target contours in reverse search direction.

The initialization search phase may be a phase of searching for a starting search base point (i 1, j 1). The contour starting point (i.e., the first pixel point) on the target contour searched along the first search direction in the binary image may be represented as the contour starting point (i, j), then, based on the contour starting point (i, j), a starting boundary point (i 2, j 2) for the target contour in the reverse search direction may be determined, specifically, if the outer boundary contour is currently required to be searched, the pixel point (i, j-1) in the binary image may be used as the starting boundary point (i 2, j 2), that is, a pixel point on the left side adjacent to the contour starting point (i, j) in the same line may be used as the starting boundary point (i 2, j 2), the pixel value of the pixel point (i, j-1) may be 0, and if the hole boundary contour is currently required to be searched, the pixel point (i, j+1) in the binary image may be used as the starting boundary point (i 2, j+2), that is, the pixel point (i, j+1) on the right adjacent to the same line as the contour starting point (i, j) may be used as the starting boundary point (i+2). Further, a starting search base point (i 1, j 1) can be searched out from the binary image by the contour starting point (i, j) and the starting boundary point (i 2, j 2), and the starting search base point (i 1, j 1) can be used for finding a reference point of the starting boundary point of the contour search when the backward contour search (i.e., the contour search in the backward search direction) is performed subsequently.

The specific process of determining the initial search base point (i 1, j 1) may include searching the initial search base point (i 1, j 1) in the neighborhood of the contour starting point (i, j) clockwise from the initial boundary point (i 2, j 2), specifically, using the contour starting point (i, j) as a center, starting from the initial boundary point (i 2, j 2) and rotating clockwise, finding a first non-zero point in the neighborhood of the contour starting point (i, j), and using the first non-zero point as the initial search base point (i 1, j 1).

The above-mentioned neighborhood is an infrastructure in the topological space, and specifically, a special section centered on a certain pixel point. The field of pixel points can be used for representing the adjacency property between the pixel points and surrounding pixel points, and is generally divided into a 4 neighborhood, an 8 neighborhood and a D neighborhood according to different adjacency properties, and the like.

Referring to fig. 4 a-4 c, fig. 4 a-4 c are schematic structural diagrams of a pixel neighborhood according to an embodiment of the present application. First, as shown in fig. 4a, a pixel point P may be taken as a center point, and four pixel points of up (e.g., reference numeral 1), down (e.g., reference numeral 3), left (e.g., reference numeral 2), and right (e.g., reference numeral 0) having an adjacent relationship with the center point may be taken as 4 fields of the pixel point P.

As shown in fig. 4b, the pixel point P may be further used as a center point, and eight pixel points, which have an adjacent relationship with the center point, including an upper (e.g., 2), a lower (e.g., 6), a left (e.g., 4), a right (e.g., 0), an upper left (e.g., 3), an upper right (e.g., 1), a lower left (e.g., 5), and a lower right (e.g., 7), are used as the 8 neighbors of the pixel point P.

Further, as shown in fig. 4c, the pixel point P may be taken as a center point, and the pixel points on the four diagonals having an adjacent relationship with the pixel point P, that is, the upper left (e.g., reference numeral 3), the upper right (e.g., reference numeral 1), the lower left (e.g., reference numeral 5), and the lower right (e.g., reference numeral 7) are taken as the D neighborhood of the pixel point P.

It should be noted that the image searching method provided by the embodiment of the application has wider universality, can be applied to contour searching of any neighborhood including but not limited to a 4 neighborhood, an 8 neighborhood, a D neighborhood and the like, is not limited to the specific application neighborhood, and can be determined according to actual application scenes.

Search phase 2 for target contours in reverse search direction-a cyclic search phase for target contours in reverse search direction.

The cyclic search phase for the target contour may be implemented based on the starting search base point (i 1, j 1) of the initialization search phase described above. Specifically, a loop search may be performed based on the initial search base point (i 1, j 1) and the contour start point (i, j) to search for a corresponding search result (i.e., a result of a neighborhood search), where the obtained search result belongs to a pixel point on the target contour, and the loop search may have one or more searches, and may stop the current contour search until the searched search result meets the contour search end condition, and obtain the searched corresponding contour (i.e., the target contour). As described below.

Specifically, the initial search base point (i 1, j 1) obtained by the initial stage search may be used as the initial boundary point (i 2, j 2) of the first search in the cyclic search stage, and the contour start point (i, j) may be used as the center point (i 3, j 3) of the neighborhood search in the first search in the cyclic search stage. Then, the first search of the cyclic search stage may be performed on the binary image based on the start boundary point (i 2, j 2) and the center point (i 3, j 3) of the first search of the cyclic search stage, a search result (i 4, j 4) of the first search may be obtained, and it may be determined whether the search result (i 4, j 4) meets the contour search end condition. If so, ending the contour search, wherein the target contour only comprises a contour starting point (i, j).

Otherwise, if the search result (i 4, j 4) does not meet the profile search ending condition, it indicates that the search result (i 4, j 4) of the first search may be used as a boundary point for forming the target profile, that is, the search result (i 4, j 4) of the first search is a pixel point connected to the profile starting point and belonging to the target profile, and the next search in the cyclic search stage may be continued based on the search result (i 4, j 4) of the first search. Specifically, the center point (i 3, j 3) of the first search may be taken as the starting boundary point (i 2, j 2) of the second search, and the search result (i 4, j 4) of the first search may be taken as the center point (i 3, j 3) of the second search.

Therefore, the second search of the cyclic search stage can be performed on the binary image based on the initial boundary point (i 2, j 2) of the second search and the central point (i 3, j 3) of the second search to obtain the search result (i 4, j 4) of the second search, whether the search result (i 4, j 4) of the second search meets the contour search ending condition can be continuously judged, if yes, the contour search can be ended to obtain the searched target contour, if not, the next search of the cyclic search stage can be continuously performed based on the search result (i 4, j 4) of the second search, and the steps are repeated until the search result (i 4, j 4) of the k-th search of the cyclic search meets the contour search ending condition, the searched target contour can be obtained, and the target contour can be formed by the contour starting point (i, j) (i.e. the first pixel point) and the search result searched in the cyclic search stage each time, and the search result in the first pixel stage can be sequentially connected in series. Where k may be an integer greater than 1.

Here, the principle of implementation of each search in the cyclic search phase of the reverse search direction is the same. Here, the implementation process of the second search in the cyclic search stage is described as an example, the first non-zero point in the neighborhood of the center point (i 3, j 3) of the second search may be searched in a counterclockwise direction from the start boundary point (i 2, j 2) of the second search, specifically, the center point (i 3, j 3) of the second search may be used as the center point of the 8 neighborhood, the next pixel point in the counterclockwise direction of the start boundary point (i 2, j 2) of the second search may be recorded as a starting point, the coordinates (i2_ jext, j2_ jext) may be recorded, and the 8 neighborhood of the center point (i 3, j 3) of the second search may be searched counterclockwise from the pixel point (i2_ jext, j2_ jext) until the first non-zero value is found, and the first non-zero point may be used as the search result (i 4, j 4) of the second search.

Optionally, the profile search ending condition met by the search result (i 4, j 4) of any one of the above-mentioned cyclic search stages of the reverse search direction may include that the search result (i 4, j 4) obtained by the any one search is identical to the profile starting point (i, j) and the center point (i 3, j 3) of the any one search is identical to the starting search base point (i 1, j 1), that is, if the search result (i 4, j 4) of the any one search meets the profile search ending condition, it is indicated that the any one search returns to the profile starting point (i, j) of the present profile search, that is, the starting point and the boundary point of the present profile search form a closed profile. Alternatively, the target contour searched in the present application may be a closed loop contour, or may also be an unclosed curve, and it may be understood that if the contour is an unclosed curve, when the contour searching is performed, after all points on the contour are searched for the first time, all points on the contour may be searched for continuously in the reverse order, so that the contour starting point (i, j) of the current contour searching may be returned finally.

By the above process, the target contour is searched along the reverse searching direction.

Referring to fig. 5 a-5 b, fig. 5 a-5 b are schematic views of a scene of reverse contour search according to an embodiment of the present application. An exemplary process of determining the search base point (i 1, j 1) in the initialization search stage of the binary image shown in fig. 5a may include that the image search apparatus may search for a pixel point having pixel coordinates (1, 2) from the binary image as a contour start point in the reverse search direction, which is a contour where the pixel point (1, 2) is located, according to a judgment condition of a contour start point in the reverse search direction (such as the contour start search condition described above).

Further, the left adjacent pixel point (1, 1) belonging to the same line as the contour start point (1, 2) may be set as a start boundary point (i 2, j 2), that is, a start boundary point (i 2, j 2) = (1, 1), and the pixel value of the start boundary point (i 2, j 2) may be 0.

Then, a first non-zero point (1, 3) in the neighborhood of the contour start point (1, 2) may be found in the clockwise direction with the contour start point (1, 2) as the center point of the neighborhood and starting from the start boundary point (i 2, j 2), and the first non-zero point (1, 3) may be taken as the start search base point (i 1, j 1), i.e., the start search base point (i 1, j 1) = (1, 3).

As shown in fig. 5b, the contour starting point (1, 2) may be set as a center point (i 3, j 3) of the neighborhood search in the first search in the loop search stage in the reverse search direction, the starting search base point (i 1, j 1) = (1, 3) may be set as a starting boundary point (i 2, j 2) = (1, 3) in the first search in the loop search stage in the reverse search direction, and further, the search result (i 4, j 4) = (2, 2) of the first search may be obtained by searching the center point (i 3, j 3) and the starting boundary point (i 2, j 2).

Further, since the search result (i 4, j 4) = (2, 2) does not satisfy the contour search end condition in the reverse search direction, the second search of the loop search stage in the reverse search direction can be continued, in which the center point (i 3, j 3) = (1, 2) that can be searched for in the first time can be used as the start boundary point (i 2, j 2) of the second search, and the search result (i 4, j 4) = (2, 2) of the first time can be used as the center point (i 3, j 3) of the second search, and further, the search result (i 4, j 4) = (3, 2) of the second search can be searched for based on the center point (i 3, j 3) and the start boundary point (i 2, j 2).

And so on, since the search result (i 4, j 4) = (3, 2) does not meet the contour search ending condition in the reverse search direction, the search can be continued for more times in the cyclic search stage in the reverse search direction until the searched search result meets the contour search ending condition in the reverse search direction, and the corresponding contour can be obtained by searching.

More, if the first search direction is the forward search direction, the process of searching along the forward search direction to obtain the target contour may include, as also described in conjunction with table 1 above, performing a cyclic search after the initial search based on the first pixel after searching for the contour starting point (i.e., the first pixel) of the target contour in the first search direction, where each search of the cyclic search may be performed to obtain a pixel on the target contour, and finally forming the searched whole target contour by the first pixel and the search result obtained by each search in the cyclic search, as described below.

Search phase 1 for target contours in the forward search direction initializing search phase for target contours in the forward search direction.

Similarly, the initial search phase may be a phase of searching for the starting search base point (i 1, j 1). The contour starting point (i.e., the first pixel point) on the target contour searched along the first search direction in the binary image may be represented as the contour starting point (i, j), then, based on the contour starting point (i, j), a starting boundary point (i 2, j 2) for the target contour in the forward search direction may be determined, specifically, if the outer boundary contour is currently required to be searched, the pixel point (i, j+1) in the binary image may be used as the starting boundary point (i 2, j 2), that is, a pixel point on the right side adjacent to the contour starting point (i, j) in the same line may be used as the starting boundary point (i 2, j 2), the pixel value of the pixel point (i, j+1) may be 0, and if the hole boundary contour is currently required to be searched, the pixel point (i, j-1) in the binary image may be used as the starting boundary point (i 2, j-1) and the pixel point (i, j-1) on the left side adjacent to the same line as the starting boundary point (i, j-2). Further, a start search base point (i 1, j 1) can be searched out from the binary image by the contour start point (i, j) and the start boundary point (i 2, j 2), and the start search base point (i 1, j 1) can be used to find a reference point of the start boundary point of the contour search when the forward contour search (i.e., the contour search in the forward search direction) is performed subsequently.

The specific process of determining the initial search base point (i 1, j 1) may include searching the initial search base point (i 1, j 1) in the neighborhood of the contour start point (i, j) according to the anticlockwise direction from the initial boundary point (i 2, j 2), specifically may be searching the first non-zero point in the neighborhood of the contour start point (i, j) according to the anticlockwise direction from the initial boundary point (i 2, j 2) by taking the contour start point (i, j) as the center, and taking the first non-zero point as the initial search base point (i 1, j 1).

The search phase 2 for the target contour in the forward search direction is a cyclic search phase for the target contour in the forward search direction.

Similarly, a circular search phase for the target contour may be implemented based on the initial search base point (i 1, j 1) of the initialization search phase described above. Specifically, a loop search may be performed based on the initial search base point (i 1, j 1) and the contour start point (i, j) to search for a corresponding search result (i.e., a result of a neighborhood search), where the obtained search result belongs to a pixel point on the target contour, and the loop search may have one or more searches, and may stop the current contour search until the searched search result meets the contour search end condition, and obtain the searched corresponding contour (i.e., the target contour). As described below.

Here, the principle of implementation of each search in the cyclic search phase of the forward search direction is the same. Here, the implementation process of the second search in the cyclic search stage is described as an example, the first non-zero point in the neighborhood of the center point (i 3, j 3) of the second search may be searched in a clockwise direction from the start boundary point (i 2, j 2) of the second search, specifically, the center point (i 3, j 3) of the second search may be used as the center point of the 8 neighborhood, the next pixel point in the clockwise direction of the start boundary point (i 2, j 2) of the second search may be marked as a starting point, the coordinates (i2_ jext, j2_ jext) may be marked, and the 8 neighborhood of the center point (i 3, j 3) of the second search may be searched in a clockwise direction from the pixel point (i2_ jext, j2_ jext) until the first non-zero value is found, and the first non-zero point may be used as the search result (i 4, j 4) of the second search.

Optionally, the profile search ending condition met by the search result (i 4, j 4) of any one search in the cycle search stage of the forward search direction may include that the search result (i 4, j 4) obtained by the any one search is identical to the profile starting point (i, j), and the center point (i 3, j 3) of the any one search is identical to the starting search base point (i 1, j 1), that is, if the search result (i 4, j 4) of the any one search meets the profile search ending condition, it is indicated that the any one search returns to the profile starting point (i, j) of the present profile search, that is, the starting point and the boundary point of the present profile search form a closed profile.

By the above process, the target contour is searched along the forward searching direction.

After searching for the target contour, the image searching apparatus may generate conversion data of the target contour, which may include indication data respectively associated with each of the search directions other than the first search direction, which may be used to indicate the target contour in the contour search of the associated search direction. Since the target contour may be any contour searched in the first search direction, any indication data associated with one search direction other than the first search direction may be indication data of the target contour in the one search direction, the indication data being used to indicate the target contour searched in the first search direction in the contour search in the one search direction. That is, the target contour has an indication data in one search direction other than the first search direction, which is used to indicate the target contour in the contour search in that search direction.

Accordingly, the process of generating conversion data of the target profile searched in the first search direction may include:

First, the image processing apparatus may acquire, in the binary image, a contour start point of the target contour in each search direction other than the first search direction. It should be noted that the target contour has a contour start point in each of the N search directions. The contour starting point of the target contour in one search direction may refer to the first (i.e., 1 st) pixel point on the searched target contour that meets the contour starting search condition in the one search direction in the contour search in the one search direction. In other words, the contour start point of the target contour in one search direction may refer to the 1 st pixel point belonging to the target contour searched along the one search direction.

Alternatively, any one of the N search directions other than the first search direction may be referred to as a second search direction. If the first search direction is a reverse search direction and the second search direction is a forward search direction, the contour starting point of the target contour in the second search direction may be obtained according to the following logic:

if(i4>i3)

(i 5, j 5) = (i 4, j 4)// if i4 in the search result (i 4, j 4) of a search in the circular search phase of the reverse search direction is greater than i3 in the center point (i 3, j 3), the coordinates (i 5, j 5) are transformed with the search result (i 4, j 4) update (which may be an overlay update)

else if((i4==i3)&&(j4>j3))

(I 5, j 5) = (i 4, j 4)// if i4 in the search results (i 4, j 4) of a search in the cyclic search phase of the reverse search direction is equal to i3 in the center point (i 3, j 3) and j4 in the search results (i 4, j 4) is greater than j3 in the center point (i 3, j 3), then the transformed coordinates (i 5, j 5) are updated (may be an overlay update) with the search results (i 4, j 4)

In the searching process of the target contour, the conversion coordinates (i 5, j 5) can be updated based on each pixel point searched on the target contour, and the finally updated conversion coordinates (i 5, j 5) are one pixel point which is the lowest and the rightmost (firstly satisfies the lowest and then satisfies the rightmost) pixel point on the target contour, and the pixel point is the contour starting point of the target contour in the forward searching direction.

The above process is a process of converting the searched contour starting point of the target contour in the forward searching direction in the process of searching the target contour in the reverse searching direction.

More, if the first search direction is a forward search direction and the second search direction is a reverse search direction, the contour starting point of the target contour in the second search direction may be obtained according to the following logic:

if(i4<i3)

(i 5, j 5) = (i 4, j 4)// if i4 in the search result (i 4, j 4) of a search in the cyclic search phase of the forward search direction is less than i3 in the center point (i 3, j 3), the coordinates (i 5, j 5) are transformed with the search result (i 4, j 4) update (which may be an overlay update)

else if((i4==i3)&&(j4<j3))

(I 5, j 5) = (i 4, j 4)// if i4 in the search results (i 4, j 4) of a search in the cyclic search phase of the forward search direction is equal to i3 in the center point (i 3, j 3) and j4 in the search results (i 4, j 4) is less than j3 in the center point (i 3, j 3), then the transformed coordinates (i 5, j 5) are updated (may be an overlay update) with the search results (i 4, j 4)

In the searching process of the target contour, the conversion coordinates (i 5, j 5) can be updated based on each pixel point searched on the target contour, and the finally updated conversion coordinates (i 5, j 5) are one pixel point which is the uppermost and leftmost (firstly satisfies the uppermost and then satisfies the leftmost) pixel point on the target contour, and the pixel point is the contour starting point of the target contour in the reverse searching direction.

The above process is a process of converting the searched contour starting point of the target contour in the reverse searching direction in the process of searching the target contour in the forward searching direction.

After acquiring the contour start points of the target contour in each of the N search directions except the first search direction, the image search apparatus may generate the indication data of the target contour in each of the search directions by the contour start points of the target contour in each of the search directions except the first search direction, the image search apparatus may acquire the pixel coordinates (including the lateral coordinates and the longitudinal coordinates) of the contour start points of the target contour in each of the search directions except the first search direction in the binary image, respectively, and the image search apparatus may further use the pixel coordinates of the contour start points of the target contour in each of the search directions except the first search direction as the indication data of the target contour in each of the search directions.

In other words, the indication data of the target contour in one search direction may be the pixel coordinates of the contour start point of the target contour in the search direction.

Further, the image search apparatus may use, as the conversion data that is the target contour, the instruction data of the target contour in the respective search directions other than the first search direction.

Referring to fig. 6 a-6 b, fig. 6 a-6 b are schematic views of a scene for determining a starting point of a contour according to an embodiment of the present application. As shown in fig. 6a, the contour starting point of the target contour in the reverse search direction in the binary image may be the uppermost and leftmost pixel point on the target contour, which is the 1 st pixel point searched on the target contour when the contour search is performed on the binary image in the reverse search direction.

Similarly, the contour starting point of the target contour in the binary image in the forward search direction may be the lowest and rightmost pixel point on the target contour, and when the contour search is performed on the binary image in the forward search direction, the lowest and rightmost pixel point is the 1 st pixel point searched on the target contour.

As shown in fig. 6b, the contour search of the target image is performed in the reverse search direction, that is, each row of pixels in the binary image is scanned in a traversing manner (for example, scan 1 st row of pixels from left to right, scan 2 nd row of pixels from left to right, scan 3 rd row of pixels from left to right) in the top-bottom and left-right direction, so as to search for a pixel that meets the contour start search condition in the reverse search direction, and search for the contour where the pixel is located from the pixel, where the pixel (1, 2) may be a pixel that meets the contour start search condition in the reverse search direction.

Similarly, the contour of the target image is searched in the forward search direction, that is, each row of pixels in the binary image is scanned in a traversing manner (such as scanning from right to left for the 1 st row of pixels, scanning from right to left for the 2 nd row of pixels, and scanning from right to left for the 3 rd row of pixels) in the bottom-to-top and right-to-left direction, so as to search for pixels meeting the contour initial search condition in the forward search direction, and the contour where the pixels are located is searched for from the pixels, so that the pixels (4, 9) can be pixels meeting the contour initial search condition in the forward search direction.

Step S103, skipping contour searching of the indication contours related to the N searching directions in the process of searching the contours of the target image, so as to obtain the contours searched along the N searching directions, wherein the indication contours related to the first searching direction comprise the contours indicated by the indication data related to the first searching direction.

Alternatively, in the process of performing contour searching on the target image along the N search directions, the image searching apparatus may skip contour searching on the indication contour associated with each of the N search directions, so as to obtain the contour searched along each of the N search directions.

Wherein the indication profile associated with the first search direction may include a profile indicated by all indication data associated with the first search direction, in other words, the indication profile associated with the first search direction may include profiles searched in various search directions other than the first search direction.

The target profile has an indication data in the second search direction, and thus, here, a search process of skipping the target profile searched in the first search direction in the second search direction will be specifically described, and the process may include:

When a second pixel point meeting the contour start search condition in the second search direction is searched along the second search direction, and the second pixel point is detected to belong to the pixel point (such as the first pixel point) indicated by the indication data (such as the indication data belonging to the target contour in the second search direction) associated with the second search direction (such as when the second pixel point is the first pixel point), the image search device may skip the contour search process based on the second pixel point in the second search direction, that is, not start searching the contour where the second pixel point is located from the second pixel point. And, the image searching apparatus may further acquire each pixel point on the target contour through the indication data of the target contour in the second searching direction, and may skip the process of performing contour searching based on each pixel point on the target contour except the second pixel point in the second searching direction, so that searching of the target contour where each pixel point is located from each pixel point on the target contour may be achieved, that is, skip the process of performing contour searching based on each pixel point on the target contour which has been searched in the first searching direction in the second searching direction.

The process of the image searching device obtaining each pixel point on the target contour (i.e. obtaining the set of the pixel points on the target contour) through the indication data of the target contour in the second searching direction may include that the image searching device may obtain the pixel coordinates of each pixel point on the target contour in the binary image when the image searching device searches the target contour along the first searching direction or after searching the target contour.

Further, the image search apparatus may use the indication data of the target contour in the second search direction to correlate the pixel coordinates of the respective pixel points on the recording target contour. That is, it can be understood that the pixel coordinates of the outline starting point of the target outline in the second search direction may be regarded as the outline identification of the target outline in the second search direction, that is, the target outline may be identified by the indication data of the target outline in the second search direction, and the pixel coordinates of the respective pixel points on the identified target outline may be recorded.

In other words, when the target contour is searched in the first search direction, the pixel coordinates of the respective pixels on the recording target contour, that is, the set of the respective pixels on the recording target contour can be associated by the instruction data generated for the second search direction based on the target contour.

Therefore, when the second pixel point on the target contour is searched in the second search direction, the pixel coordinates of each pixel point on the target contour recorded by the association of the indicating data (such as the pixel coordinates of the second pixel point) in the second search direction can be obtained through the indicating data of the target contour (such that each pixel point on the target contour except for the second pixel point can be obtained through the process). It can be understood that the pixel coordinates of each pixel point on the acquired target contour are the pixel points on the acquired target contour.

From the above-described related features, it can be understood that the first pixel is not a pixel indicated by the indication data associated with the first search direction, and is not a pixel on the outline where the pixel indicated by the indication data associated with the first search direction is located. And it can be understood that when the first pixel point is searched along the first search direction, no pixel points meeting the contour start search condition of the corresponding search direction on the target contour are searched in other search directions, i.e. no contour where the first pixel point is located is searched in other search directions.

Therefore, by skipping the searching process of the indication contour associated with each of the N searching directions, the same contour is not repeatedly searched in different searching directions in the contour searching in each searching direction, so that the efficiency of searching the contour of the target image by adopting a plurality of searching directions can be improved, and the searching completeness and searching consistency of the contour in the target image are ensured.

Each time a contour is searched in one search direction, each line of pixel points in the binary image can be scanned from the initial position (for example, for the reverse search direction, the initial position is the position at the 1 st line and the 1 st column, for the forward search direction, the initial position is the position at the 1 st line and the 1 st column) along the search direction, so as to find out the pixel points which meet the contour starting search condition in the search direction and do not belong to the searched contour in each search direction (including all search directions), and the next contour is searched in the search direction as a contour starting point. On the basis of this, it is understood that when the contour starting point at which the contour search can be started is not searched in one search direction (e.g., the contour starting point which is not searched for except for the pixel points on the contour which has been searched for in the respective search directions (including the search direction itself and which meets the contour starting search condition in the one search direction), it is indicated that the contour search in the one search direction has been completed, i.e., that the contour search in the one search direction has been completed entirely.

The contours searched in the binary image of the target image can be understood as contours searched in the target image, and the contours in the target image can comprise all contours searched along the N searching directions.

After searching the outline in the target image, the outline searched for in the target image can be identified (in any identification mode, such as highlighting identification or highlighting identification, etc.), the image in the identified outline can be segmented (such as clipping) in the target image, the image is a local image in the target image, the local image can also be different according to different practical application scenes, such as a foreground image in the target image, an image of a target object or an image of a target area (such as an area of a specific biological organ in the medical field), etc., and the local image can be specifically determined according to the practical application scene.

The identifying the contour searched for in the target image may include identifying the contour according to the pixel coordinates of each pixel point on the contour in the binary image after the image searching device searches for the corresponding contour in the binary image along N searching directions, in which the pixel coordinates of each pixel point on the contour in the target image are identical to the pixel coordinates of each pixel point on the contour in the binary image, that is, the pixel coordinates of each pixel point on the contour in the binary image are identical to the pixel coordinates of each pixel point on the contour in the binary image, that is, the pixel coordinates of each pixel point on the target image are identical to the pixel points on the contour in the binary image, that is, the pixel points (pixel points with identical pixel coordinates) corresponding to the pixel points in the target image can be identified by the pixel points on the contour in the binary image.

Referring to fig. 7, fig. 7 is a schematic view of a scene of image segmentation according to an embodiment of the present application. As shown in fig. 7, the contour search can be performed on the target image according to the method provided by the application, the contour of the puppy in the target image can be obtained by searching, the contour of the puppy can be identified in the target image, and further, the local image in the identified contour can be segmented in the target image, and the local image is the local image of the puppy in the target image.

Based on the above detailed description of the image search method, respective units for realizing the image search method are described below. Referring to fig. 8, fig. 8 is a schematic structural diagram of an image searching apparatus according to an embodiment of the present application. As shown in fig. 8, the structure may include a forward contour search unit, a forward contour boundary conversion unit corresponding to the forward contour search unit, a reverse contour boundary conversion unit corresponding to the reverse contour search unit, and a scan state query unit, the image processing method provided by the application can be deployed in the image processing device, and the image processing device is operated by the computer equipment to realize the image processing method, so that each unit in the structure can be deployed in the image processing device.

The forward contour searching unit is used for searching the contours of the target images along the forward searching direction so as to obtain corresponding contours in the target images from the forward searching direction, and the reverse contour searching unit is used for searching the contours of the target images along the reverse searching direction so as to obtain corresponding contours in the target images from the reverse searching direction.

The forward contour boundary conversion unit corresponding to the forward contour search unit may be configured to perform boundary conversion processing on the contour searched by the forward contour search unit (i.e., the contour searched along the forward search direction) to obtain conversion data of the contour searched by the forward contour search unit, where the conversion data may include indication data associated with the reverse search direction, the indication data may be configured to indicate the contour searched by the forward contour search unit in the contour search in the reverse search direction, the conversion data may be stored in the scan state query unit, and pixel coordinates of each pixel point on the contour searched by the forward contour search unit may also be stored in the scan state query unit.

Similarly, the reverse contour boundary conversion unit corresponding to the reverse contour search unit may be configured to perform boundary conversion processing on the contour searched by the reverse contour search unit (i.e., the contour searched along the forward search direction) to obtain conversion data of the contour searched by the reverse contour search unit, where the conversion data may include indication data associated with the forward search direction, the indication data may be configured to indicate the contour searched by the reverse contour search unit in the contour search in the forward search direction, the conversion data may be stored in the scan state query unit, and pixel coordinates of each pixel point on the contour searched by the reverse contour search unit may also be stored in the scan state query unit.

Further, it can be understood that, in the process of scanning the pixel points in the binary image by the forward contour searching unit to perform contour searching, the scanning state searching unit may search based on the scanned (i.e., searched) pixel points meeting the contour starting searching condition in the forward searching direction, so as to determine whether the scanned pixel points are included in the scanning state searching unit, if so, the contour searching is not started with the currently scanned pixel point as the contour starting point, and if not, the contour searching is started with the currently scanned pixel point as the contour starting point.

Similarly, in the process that the inverse contour searching unit scans the pixel points in the binary image to perform contour searching, the scanning state searching unit may search based on the scanned (i.e. searched) pixel points meeting the contour starting searching condition in the inverse searching direction, so as to determine whether the scanned pixel points are included in the scanning state searching unit, if so, the contour searching is not started by taking the currently scanned pixel point as the contour starting point, and if not, the contour searching is started by taking the currently scanned pixel point as the contour starting point.

When the forward contour searching unit cannot search the binary image for the pixel points which meet the contour start searching condition in the forward searching direction and are not contained in the scanning state inquiring unit, the contour searching of the binary image by the forward contour searching unit is completed completely, and the contour searching can be finished. Similarly, when the reverse contour searching unit cannot search the binary image for the pixel points which meet the contour start searching condition in the reverse searching direction and are not included in the scanning state inquiring unit, the contour searching of the binary image by the reverse contour searching unit is completed completely, and the contour searching can be finished.

Through the units, each contour in the target image can be obtained through searching along the reverse searching direction and the forward searching direction at the same time. As can be seen from the above, the forward/reverse contour boundary conversion unit and the scan state query unit provided by the present application are a novel technique, so that contour searching is not performed based on pixel points on the searched contour in each searching direction, repeated searching of the contour is avoided, and the integrity of contour searching in the image is ensured. Based on the support of the forward/reverse contour boundary conversion unit and the scanning state query unit, different contours in the target image can be searched in parallel along a plurality of searching directions on the basis of ensuring the correctness of contour searching, so that the speed and the efficiency of contour searching for the target image are greatly improved, and the contour searching performance is improved.

Referring to fig. 9, fig. 9 is a schematic structural diagram of another image searching apparatus according to an embodiment of the present application. As shown in fig. 9, the image search apparatus 1 may include a search module 11 and an acquisition module 12.

A search module 11, configured to perform contour search on the target image along N search directions, where N is an integer greater than 1;

An acquisition module 12 for acquiring conversion data of the contours searched along each of the N search directions, wherein any one of the N search directions is a first search direction, and the conversion data of the contours searched along the first search direction includes indication data respectively associated with each search direction other than the first search direction, the indication data being used for indicating the contours searched along the first search direction in the associated search direction;

The searching module 11 is further configured to skip, in a process of performing contour searching on the target image, contour searching on the indication contours corresponding to the N search directions in each of the N search directions, to obtain contours searched along each of the N search directions;

Optionally, the searching module 11 performs contour searching on the target image along N searching directions, including:

Optionally, the searching module 11 performs a contour search on the binary image along the first searching direction, including:

the acquiring module 12 generates a flow of conversion data of the target profile searched along the first search direction, including:

Optionally, the obtaining module 12 generates, based on the contour starting points of the target contour in each search direction except the first search direction, the manner of indicating data in each search direction, including:

the searching module 11 skips, in the process of performing contour searching on the target image, contour searching on the indicated contour corresponding to each of the N search directions in each of the N search directions, to obtain a contour searched along each of the N search directions, including:

Optionally, when or after searching for the target contour along the first search direction, the apparatus 1 is further configured to:

Optionally, the searching module 11 performs contour searching based on the first pixel point to search for a target contour where the first pixel point is located, including:

Optionally, the above device 1 is further configured to:

identifying a contour searched for the target image in the target image;

According to one embodiment of the present application, the steps involved in the image search method shown in fig. 3 may be performed by respective modules in the image search apparatus 1 shown in fig. 9. For example, step S101 shown in fig. 3 may be performed by the search module 11 in fig. 9, step S102 shown in fig. 3 may be performed by the acquisition module 12 in fig. 9, and step S103 shown in fig. 3 may be performed by the search module 11 in fig. 9.

The method and the device can perform contour searching on the target image along N searching directions, N is an integer larger than 1, conversion data of contours searched along each of the N searching directions can be obtained, any one of the N searching directions is a first searching direction, the conversion data of the contours searched along the first searching direction comprise indication data respectively associated with each searching direction except the first searching direction, the indication data are used for indicating the contours searched along the first searching direction in contour searching in the associated searching directions, and contour searching of the indication contours corresponding to each searching direction in each of the N searching directions can be skipped in the contour searching process of the target image, so that the contours searched along each searching direction in the N searching directions are obtained, the indication contours corresponding to the first searching direction comprise the contours indicated by the indication data associated with the first searching direction, and the contours in the target image comprise the contours searched along the N searching directions. Therefore, the device provided by the application can perform contour searching on the target image along a plurality of searching directions (namely N searching directions), and in the process of performing contour searching along the plurality of searching directions, the contour searching of the contours searched in other searching directions can be skipped through the associated indication information in each searching direction, so that the same contour in the target image can not be repeatedly searched in each searching direction, and the efficiency of searching the contours in the target image can be greatly improved.

According to an embodiment of the present application, each module in the image searching apparatus 1 shown in fig. 9 may be separately or completely combined into one or several units to form a structure, or some (some) of the units may be further split into a plurality of sub-units with smaller functions, so that the same operation may be implemented without affecting the implementation of the technical effects of the embodiment of the present application. The above modules are divided based on logic functions, and in practical applications, the functions of one module may be implemented by a plurality of units, or the functions of a plurality of modules may be implemented by one unit. In other embodiments of the present application, the image search apparatus 1 may also include other units, and in practical applications, these functions may also be realized with assistance of other units, and may be realized by cooperation of a plurality of units.

According to one embodiment of the present application, a computer program capable of executing the steps involved in the respective methods shown in the embodiments of the present application can be run on a general-purpose computer device, which may contain a processing element and a storage element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read only storage medium (ROM), etc., to construct the image search apparatus 1 as shown in fig. 9. The above-described computer program may be recorded on, for example, a computer-readable recording medium, and may be loaded into and executed in the above-described computer apparatus through the computer-readable recording medium.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a computer device according to the present application. As shown in fig. 10, the computer device 1000 may include a processor 1001, a network interface 1004, and a memory 1005, and in some embodiments, the computer device 1000 may also include a user interface 1003, and at least one communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface, among others. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1005 may also optionally be at least one storage device located remotely from the processor 1001. As shown in fig. 10, an operating system, a network communication module, a user interface module, and a device control application program may be included in the memory 1005, which is one type of computer storage medium.

In the computer device 1000 shown in fig. 10, the network interface 1004 may provide network communication functions, while the user interface 1003 is mainly used as an interface for providing input to a user, and the processor 1001 may be used to invoke a device control application program stored in the memory 1005 to realize:

In the process of searching the outline of the target image, skipping the outline searching of the indication outline associated with each searching direction in N searching directions to obtain the outline searched along each searching direction in the N searching directions;

It should be understood that the computer device 1000 described in the embodiments of the present application may perform the description of the image searching method described above in the embodiments of the present application, and may also perform the description of the image searching apparatus 1 described above in the embodiment corresponding to fig. 9, which is not repeated here. In addition, the description of the beneficial effects of the same method is omitted.

In addition, it should be noted that the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, which when executed by a processor, can perform the description of the image searching method in each embodiment of the present application, and therefore, a detailed description thereof will not be provided herein. In addition, the description of the beneficial effects of the same method is omitted. For technical details not disclosed in the embodiments of the computer storage medium according to the present application, please refer to the description of the method embodiments of the present application.

As an example, the above-described computer program may be deployed to be executed on one computer device or on multiple computer devices that are located at one site, or on multiple computer devices that are distributed across multiple sites and interconnected by a communication network, where the multiple computer devices that are distributed across multiple sites and interconnected by a communication network may constitute a blockchain network.

The computer readable storage medium may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), etc. that are provided on the computer device. Further, the computer-readable storage medium may also include both internal storage units and external storage devices of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

The present application provides a computer program product comprising a computer program stored in a computer readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the description of the image search method in the embodiments of the present application, and thus, a detailed description thereof will not be provided herein. In addition, the description of the beneficial effects of the same method is omitted. For technical details not disclosed in the embodiments of the computer-readable storage medium according to the present application, please refer to the description of the method embodiments of the present application.

The terms first, second and the like in the description and in the claims and drawings of embodiments of the application are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the term "include" and any variations thereof is intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or modules but may, in the alternative, include other steps or modules not listed or inherent to such process, method, apparatus, article, or device.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The foregoing disclosure is illustrative of the present application and is not to be construed as limiting the scope of the application, which is defined by the appended claims.

Claims

1. An image search method, characterized in that the method comprises:

Perform contour search on the target image along N search directions; N is an integer greater than 1;

Acquire conversion data of contours searched along each of the N search directions; any one of the N search directions is a first search direction, and the conversion data of contours searched along the first search direction includes indication data respectively associated with each search direction except the first search direction, and the indication data is used to indicate the contours searched along the first search direction in the contour search in the associated search direction;

In the process of performing contour search on the target image, in each of the N search directions, a contour search of the indicated contour associated with each of the search directions is skipped to obtain the contour searched along each of the N search directions; the indicated contour associated with the first search direction includes the contour indicated by the indication data associated with the first search direction;

The contours in the target image include contours searched along the N search directions.

2. The method according to claim 1, characterized in that the contour search of the target image along N search directions comprises:

A contour search is performed on the binary image along the N search directions.

3. The method according to claim 2, characterized in that the process of performing contour search on the binary image along the first search direction comprises:

Searching pixel points in the binary image in sequence along the first search direction;

When the first pixel point is searched, a contour search is performed based on the first pixel point to search for a target contour where the first pixel point is located;

The first pixel point refers to a pixel point that meets the contour start search condition in the first search direction.

4. The method according to claim 3, characterized in that a contour searched along the first search direction has a conversion data, the target contour is any contour searched along the first search direction, and any indication data associated with a search direction other than the first search direction is the indication data of the target contour in the search direction;

The process of generating conversion data of the target contour searched along the first search direction includes:

In the binary image, obtaining a contour starting point of the target contour in each search direction except the first search direction;

Based on the contour starting point of the target contour in each search direction except the first search direction, generating indication data of the target contour in each search direction;

Determine the indication data of the target contour in each search direction except the first search direction as the conversion data of the target contour;

Among them, the target contour has a contour starting point in each of the N search directions, and the contour starting point of the target contour in a search direction refers to the first pixel point on the target contour searched in the contour search in the search direction that meets the contour starting search conditions in the search direction.

5. The method according to claim 4, characterized in that the step of generating indication data in each search direction based on the contour starting point of the target contour in each search direction except the first search direction comprises:

Obtaining pixel coordinates of the starting points of the contour of the target in each search direction except the first search direction in the binary image;

The pixel coordinates of the starting point of the target contour in each search direction except the first search direction are determined as the indication data of the target contour in each search direction.

6. The method according to claim 4, characterized in that any search direction among the N search directions except the first search direction is a second search direction;

In the process of performing contour search on the target image, in each of the N search directions, the contour search of the indicated contour corresponding to the respective search direction is skipped to obtain the contour searched along each of the N search directions, including:

When a second pixel point that meets the contour start search condition in the second search direction is searched along the second search direction, and it is detected that the second pixel point belongs to the pixel point indicated by the indication data of the target contour in the second search direction, skipping the contour search based on the second pixel point in the second search direction; and,

Based on the indication data of the target contour in the second search direction, each pixel point on the target contour is obtained, and in the second search direction, the process of performing contour search based on each pixel point on the target contour except the second pixel point is skipped.

7. The method according to claim 6, characterized in that when or after searching for the target contour along the first search direction, the method further comprises:

Obtaining the pixel coordinates of each pixel point on the searched target contour in the binary image;

Using the indication data of the target contour in the second search direction, the pixel coordinates of each pixel point on the target contour are recorded in association;

The acquiring each pixel point on the target contour based on the indication data of the target contour in the second search direction comprises:

Based on the indication data of the target contour in the second search direction, the pixel coordinates of each pixel point on the target contour of the associated record are obtained.

8. The method according to claim 3, characterized in that the pixel value of the pixel point in the binary image is a first pixel value or a second pixel value, and the first pixel value is greater than the second pixel value;

The target contour is a hole boundary type or an outer boundary type. If the target contour is the hole boundary type, the pixel values of the pixel points within the target contour are all the second pixel values;

If the target contour is of the outer boundary type, the pixel values of the pixel points within the target contour are all the first pixel values, and the pixel values of the pixel points outside the target contour and adjacent to the target contour are the second pixel values.

9. The method according to claim 8, characterized in that the first search direction is a reverse search direction or a forward search direction; the reverse search direction refers to a direction of searching for pixel points that meet the contour start search condition in the first search direction in the binary image from left to right and from top to bottom, and the forward search direction refers to a direction of searching for pixel points that meet the contour start search condition in the first search direction in the binary image from right to left and from bottom to top;

The first pixel is represented by (i, j), the pixel value of the first pixel is represented by f(i, j), i is the longitudinal coordinate of the first pixel in the binary image, j is the transverse coordinate of the first pixel in the binary image, and both i and j are non-negative integers;

If the target contour is the hole boundary type, and the first search direction is the reverse search direction, the contour start search condition in the first search direction is: f(i, j) is equal to the first pixel value, and f(i, j+1) is equal to the second pixel value;

If the target contour is the hole boundary type, and the first search direction is the forward search direction, the contour start search condition in the first search direction is: f(i, j) is equal to the first pixel value, and f(i, j-1) is equal to the second pixel value;

If the target contour is the outer boundary type, and the first search direction is the reverse search direction, the contour start search condition in the first search direction is: f(i, j) is equal to the first pixel value, and f(i, j-1) is equal to the second pixel value;

If the target contour is the outer boundary type and the first search direction is the forward search direction, the contour starting search condition in the first search direction is: f(i, j) is equal to the first pixel value, and f(i, j+1) is equal to the second pixel value.

10. The method according to claim 8, characterized in that the performing contour search based on the first pixel point to search for the target contour where the first pixel point is located comprises:

In the binary image, starting from the first pixel point, searching for a plurality of pixel points which are connected in series and whose pixel values are all the first pixel value;

The searched target contour is determined based on the first pixel point and the searched multiple pixel points.

11. The method according to claim 1, characterized in that the method further comprises:

In the target image, identifying the contour searched for the target image;

In the target image, an image within the identified contour is segmented; the image belongs to a local image in the target image.

12. An image search device, characterized in that the device comprises:

A search module, used for performing contour search on a target image along N search directions; N is an integer greater than 1;

an acquisition module, configured to acquire conversion data of contours searched along each of the N search directions; any one of the N search directions being a first search direction, and the conversion data of contours searched along the first search direction comprising indication data respectively associated with each of the search directions except the first search direction, the indication data being used to indicate the contours searched along the first search direction in the contour search in the associated search direction;

The search module is further configured to, during the process of performing contour search on the target image, skip the contour search of the indicated contour corresponding to each of the N search directions, and obtain the contour searched along each of the N search directions; the indicated contour corresponding to the first search direction includes the contour indicated by the indication data associated with the first search direction;

13. A computer program product, comprising a computer program, which implements the steps of the method according to any one of claims 1 to 11 when executed by a processor.

14. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, wherein the computer program is suitable for being loaded by a processor and executing the method according to any one of claims 1 to 11.