CN107944501A - Image-recognizing method and device - Google Patents

Abstract

The disclosure provides an image recognition method and device. The disclosed image recognition method includes: acquiring image features and size information of an object to be recognized; and identifying the object to be recognized according to the image feature and size information. The present disclosure can improve the accuracy of image recognition and improve user experience.

Description

Image recognition method and device

technical field

The present disclosure relates to image recognition technology, in particular to an image recognition method and device.

Background technique

With the development of artificial intelligence, image recognition technology is becoming more and more perfect. Specifically, the development of image recognition has gone through three stages: character recognition, digital image processing and recognition, and object recognition.

At present, the recognition of objects is basically based on the image features of the items. In this way, current image recognition cannot distinguish two objects when their appearances are similar.

Contents of the invention

In order to overcome the problems existing in related technologies, the present disclosure provides an image recognition method and device. Described technical scheme is as follows:

According to the first aspect of the embodiments of the present disclosure, an image recognition method is provided. The method includes:

Obtain the image features and size information of the object to be recognized;

According to the image features and size information, identify the object to be identified.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: the object to be recognized can be identified through image features and size information, compared to identifying objects to be recognized based only on image features, objects with similar appearances but different sizes can be further distinguished, improving The accuracy of image recognition improves user experience.

Optionally, the acquisition of image features and size information of the object to be identified may include:

Obtain the image features and depth information of the object to be recognized through the camera;

According to the depth information, the size information is obtained.

Optionally, the aforementioned cameras are monocular cameras or binocular cameras.

Optionally, the above-mentioned identifying the object to be identified based on the image features and the size information may specifically include:

Determining a first object set according to the image features, the first object set includes at least the object to be identified;

In the first object set, identify the object to be identified according to the size information.

Optionally, the above-mentioned image recognition method may also include:

Obtain the label information of the object to be identified;

Correspondingly, the above-mentioned identification of the object to be identified based on the image features and the size information may include:

Determining a second object set according to the image feature and size information, the second object set includes at least the object to be identified;

In the second object set, identify the object to be identified according to the tag information.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: preliminarily identify the object to be identified through image features and size information, determine the set where the object to be identified is located, that is, the second object set, and in the second object set further according to The tag information identifies the object to be recognized, so as to realize the recognition of objects with similar appearance and size, and further improve the accuracy of image recognition and user experience.

According to a second aspect of the embodiments of the present disclosure, an image recognition device is provided. The image recognition device includes: a first acquisition module and a recognition module; wherein,

The first acquisition module is configured to acquire image features and size information of the object to be identified;

The identification module is configured to identify the object to be identified according to image features and size information.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: the object to be recognized can be identified through image features and size information, compared to identifying objects to be recognized based only on image features, objects with similar appearances but different sizes can be further distinguished, improving The accuracy of image recognition improves user experience.

Optionally, the above-mentioned first acquisition module is configured to: acquire image features and depth information of the object to be identified through a camera; and acquire size information according to the depth information.

Optionally, the aforementioned cameras may be monocular cameras or binocular cameras.

Optionally, the above identification module includes:

The determining submodule is configured to determine a first object set according to image features, and the first object set includes at least the object to be identified;

The identification submodule is configured to identify the object to be identified according to the size information in the first object set.

Optionally, the above-mentioned image recognition device also includes:

The second acquisition module is configured to acquire label information of the object to be identified;

Accordingly, the recognition module is configured to:

Determining a second object set according to the image feature and size information, the second object set includes at least the object to be identified;

In the second object set, identify the object to be identified according to the tag information.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: preliminarily identify the object to be identified through image features and size information, determine the set where the object to be identified is located, that is, the second object set, and in the second object set further according to The tag information identifies the object to be recognized, so as to realize the recognition of objects with similar appearance and size, and further improve the accuracy of image recognition and user experience.

According to a third aspect of the embodiments of the present disclosure, an image recognition device is provided. The image recognition device includes: a processor and a memory for storing executable instructions; wherein the processor is configured to execute the executable instructions to perform the image recognition method according to any one of the first aspect.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the image recognition method according to any one of the first aspect is implemented.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present disclosure. Those skilled in the art can also obtain other drawings based on these drawings without any creative effort.

Fig. 1 is a flowchart of an image recognition method shown according to an exemplary embodiment;

Fig. 2 is a flowchart of an image recognition method according to another exemplary embodiment;

Fig. 3 is a flowchart of an image recognition method according to yet another exemplary embodiment;

Fig. 4 is a schematic structural diagram of an image recognition device according to an exemplary embodiment;

Fig. 5 is a schematic structural diagram of an image recognition device according to another exemplary embodiment;

Fig. 6 is a schematic structural diagram of an image recognition device according to yet another exemplary embodiment;

Fig. 7 is a block diagram of an image recognition device according to an exemplary embodiment.

By means of the above-mentioned drawings, certain embodiments of the present disclosure have been shown and will be described in more detail hereinafter. These drawings and written description are not intended to limit the scope of the disclosed concept in any way, but to illustrate the disclosed concept for those skilled in the art by referring to specific embodiments.

Detailed ways

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

The terms "first", "second" and the like in the specification and claims of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are, for example, capable of practice in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Multiple, including two or more.

And/or, it should be understood that the term "and/or" used in the present disclosure is only an association relationship describing associated objects, indicating that there may be three relationships. For example, A and/or B may mean that A exists alone, A and B exist simultaneously, and B exists alone.

Since there are many similar-looking objects in practical applications (for example, some smartphones have similar appearances), the image features of these similar-looking objects are basically the same. Therefore, these objects cannot be distinguished only by image features, resulting in a low image recognition rate. Considering that there may be differences in the sizes of these objects with similar appearances, the present disclosure introduces size information during image recognition, combines image features and size information to identify objects, improves the accuracy of image recognition, and improves user experience.

Fig. 1 is a flow chart of an image recognition method according to an exemplary embodiment. This embodiment provides an image recognition method, which can be executed by an image recognition device, and the device can be realized by means of hardware and/or software.

The image recognition device may be a device with image recognition function such as a handheld device, a wearable device, a vehicle-mounted device, a computer, and a server. Handheld devices can be smartphones, tablet computers, personal digital assistants, and the like. Wearable devices include simulation devices such as augmented reality (Augmented Reality, AR) devices and virtual reality (Virtual Reality, VR) devices.

As shown in Figure 1, the image recognition method includes the following steps:

In step 101, image features and size information of an object to be recognized are acquired.

Image features may include image color features, texture features, shape features and spatial relationship features. Among them, the color feature and the texture feature are global features, which describe the surface properties of the scene corresponding to the image or image area; there are two types of representation methods for the shape feature, one is the contour feature, and the other is the regional feature, the contour feature of the image It is mainly aimed at the outer boundary of the object, while the regional features of the image are related to the entire shape area; the spatial relationship feature refers to the mutual spatial position or relative direction relationship between multiple targets segmented in the image, and these relationships can also be divided into For connection or adjacency relationship, overlap or overlap relationship and containment or containment relationship, etc.

Dimension information, used to describe the information of the external dimensions of the object to be recognized, such as one or more of the length, width, and height. The size information can be obtained by the subject performing this step through other devices, or the subject performing this step obtains it through its built-in components, for example, a smart phone obtains the size information through its built-in camera; or, the subject performing this step has The size information is stored, and the process of obtaining is the process of reading.

In step 102, the object to be recognized is recognized according to the image feature and size information.

This step shows that in the present disclosure, image recognition is not based solely on image features, but also combined with size information. In this way, when multiple objects with different sizes cannot be distinguished by image features, the image recognition method provided in the present disclosure can be used to distinguish them by combining image features with size information to improve the image recognition rate.

To sum up, the image recognition method provided in this embodiment identifies objects to be recognized through image features and size information. Compared with identifying objects to be recognized based only on image features, it can further distinguish objects with similar appearances but different sizes, and improve image quality. The accuracy of recognition improves user experience.

Fig. 2 is a flowchart of an image recognition method according to another exemplary embodiment. Referring to FIG. 2, on the basis of the process shown in FIG. 1, step 101, acquiring image features and size information of the object to be identified may specifically include:

In step 201, image features and depth information of an object to be recognized are acquired through a camera.

This step includes: acquiring image features of the object to be identified through the camera, and acquiring depth information of the object to be identified through the camera.

Wherein, for the specific description of acquiring the image features of the object to be recognized through the camera, reference may be made to related technologies. Next, how to obtain the depth information of the object to be recognized through the camera.

For the depth information, it can be understood that in the camera coordinate system, the straight line perpendicular to the imaging plane and passing through the center of the mirror is the Z axis. If the coordinates of the object in the camera coordinate system are (X, Y, Z), then the Z value That is, the depth information of the object in the imaging plane of the camera.

When implemented, the depth information can be obtained through the camera.

The acquisition methods of depth information may include at least the following two methods:

Obtaining method 1, monocular depth estimation method

The monocular depth estimation method is based on an image to estimate its depth information. For example, monocular depth estimation methods may include depth estimation methods based on image content understanding, depth estimation methods based on focusing, and the like.

Obtaining method 2, binocular depth estimation method

Imaging through two cameras, because there is a certain distance between the two cameras, there is parallax in the image of the same scene through the two lenses, and the depth information is estimated through the parallax.

Based on the above analysis, it can be seen that the camera involved in the present disclosure may be a monocular camera or a binocular camera, and the specific implementation may be set according to timing requirements, which is not limited in the present disclosure.

In step 202, size information is obtained according to the depth information.

According to the depth information, the size information of the object to be recognized is calculated. Specifically, the size information can be obtained by calculating multiple edge point coordinates (including depth information) of the object to be recognized. Wherein, the size information includes three-dimensional size information of the object to be recognized.

Optionally, step 102, identifying the object to be identified according to the image features and the size information may specifically include:

In step 203, a first object set is determined according to image features.

The first set of objects includes at least objects to be identified.

Since the image features of objects with similar appearance are basically the same, in this step, the set in which the object to be recognized is located is preliminarily determined based on the image features, that is, the first object set.

In step 204, in the first object set, identify the object to be identified according to the size information.

Through this step, an object corresponding to the size information of the object to be recognized is matched in the first object set, and the image recognition is completed.

Fig. 3 is a flow chart of an image recognition method according to yet another exemplary embodiment. Referring to FIG. 3, on the basis of the process shown in FIG. 1, the image recognition method may also include:

In step 301, tag information of an object to be recognized is acquired.

The tag information includes the name of the object to be identified. Further, the label information may also include material, manufacturer and place of origin, etc.

The way to acquire the label information is similar to the way to acquire the above-mentioned size information. For example, the tag information may have been stored in the main body executing the image recognition method and obtained by reading; or, the tag information may be obtained in real time, for example, the terminal device obtains the tag information of the object to be recognized through a camera, and so on.

It should be noted that the present disclosure does not limit the order of execution of step 301 and step 101, the two may be executed simultaneously or successively, for example, step 101 is executed first and then step 301 is executed, or step 301 is executed first and then step 301 is executed 101.

At this time, step 102, identifying the object to be identified according to the image features and size information may include:

In step 302, a second object set is determined according to image features and size information.

The second set of objects includes at least objects to be identified.

It can be understood that when there are multiple objects with similar appearance, some or all of them have similar size information, at this time, the object to be recognized cannot be identified according to the image features and size information, and only the set of the object to be recognized can be determined. , that is, the second set of objects.

In step 303, in the second object set, identify the object to be identified according to the tag information.

Since the tag information includes basic information of each object, such as a name, the object to be recognized can be accurately identified in the second object set according to the tag information.

To sum up, the method provided in this embodiment initially identifies the object to be identified through image features and size information, determines the set where the object to be identified is located, that is, the second object set, and further identifies objects in the second object set according to the label information. The object to be recognized can be identified, so as to realize the recognition of objects with similar appearance and size, and further improve the accuracy of image recognition and user experience.

The following are device embodiments of the present disclosure, which can be used to implement the method embodiments of the present disclosure. For details not disclosed in the disclosed device embodiments, please refer to the disclosed method embodiments.

Fig. 4 is a schematic structural diagram of an image recognition device according to an exemplary embodiment. The present disclosure provides an image recognition device, which can be realized by means of hardware and/or software.

Referring to FIG. 4 , the image recognition device 40 includes a first acquisition module 41 and a recognition module 42 .

The first acquiring module 41 is configured to acquire image features and size information of the object to be identified.

The identification module 42 is configured to identify the object to be identified according to image features and size information.

To sum up, the image recognition device provided in this embodiment can identify objects to be recognized through image features and size information. Compared with identifying objects to be recognized based only on image features, it can further distinguish objects with similar appearances but different sizes, and improve image quality. The accuracy of recognition improves user experience.

Optionally, the first acquiring module 41 is configured to: acquire image features and depth information of the object to be identified through a camera; and acquire size information according to the depth information.

Optionally, the aforementioned camera may be a monocular camera or a binocular camera.

Fig. 5 is a schematic structural diagram of an image recognition device according to another exemplary embodiment. Referring to FIG. 5 , on the basis of the structure shown in FIG. 4 , in the image recognition device 50 , the recognition module 42 may include: a determination submodule 421 and a recognition submodule 422 . in,

The determining sub-module 421 is configured to determine a first object set according to image features, and the first object set includes at least the object to be identified.

The identification submodule 422 is configured to identify the object to be identified according to the size information in the first object set.

Fig. 6 is a schematic structural diagram of an image recognition device according to yet another exemplary embodiment. Referring to FIG. 6 , on the basis of the structure shown in FIG. 4 , the image recognition device 60 further includes: a second acquisition module 61 .

The second acquiring module 61 is configured to acquire tag information of the object to be identified.

Correspondingly, in this embodiment, the identification module 42 is configured to: determine the second object set according to the image features and size information, the second object set includes at least the object to be identified; in the second object set, identify object to be identified.

In this embodiment, the object to be identified is preliminarily identified through image features and size information, and the set where the object to be identified is determined, that is, the second object set. In the second object set, the object to be identified is further identified according to the label information, so as to achieve a similar appearance. Moreover, the recognition of objects of comparable size further improves the accuracy of image recognition and user experience.

Fig. 7 is a block diagram of an image recognition device according to an exemplary embodiment. 7, the image recognition device 800 includes one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (input/output, referred to as: I/ O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls the overall operations of the image recognition device 800, such as operations associated with display, data communication, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802 .

The memory 804 is configured to store various types of data to support operations in the image recognition device 800 . Examples of such data include instructions for any application programs or methods operating on the image recognition device 800 , and the like. The memory 804 can be implemented by any type of volatile or non-volatile storage device or their combination, such as Static Random Access Memory (Static Random Access Memory, referred to as: SRAM), Electrically Erasable Programmable Read-Only Memory (EPROM) Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-Only Memory (Read-Only Memory, ROM for short), magnetic memory, flash memory, magnetic disk or optical disk.

The power supply component 806 provides power to various components of the image recognition device 800 . Power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for image recognition device 800 .

The multimedia component 808 includes a screen providing an output interface between the image recognition device 800 and the user. In some embodiments, the screen may include an OLED display and a touch panel (Touch Panel, TP for short). If the OLED display includes a touch panel, the OLED display may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense a boundary of a touch or swipe action, but also detect duration and pressure associated with the touch or swipe action.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a microphone (Microphone, MIC for short), and when the image recognition device 800 is in the massage mode, the microphone is configured to receive an external audio signal. Received audio signals may be further stored in memory 804 or sent via communication component 816 . In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, and the peripheral interface module may be a button or the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.

Sensor assembly 814 includes one or more sensors for providing image recognition device 800 with various aspects of status assessment.

The communication component 816 is configured to facilitate wired or wireless communication between the image recognition apparatus 800 and other devices. The image recognition apparatus 800 may access a wireless network based on a communication standard, such as Wireless-Fidelity (Wireless-Fidelity, Wi-Fi for short), 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 further includes a near field communication (Near Field Communication, NFC for short) module to facilitate short-range communication. For example, the NFC module can be based on radio frequency identification (Radio Frequency Identification, referred to as: RFID) technology, infrared data association (Infrared Data Association, referred to as: IrDA) technology, ultra wideband (Ultra Wideband, referred to as: UWB) technology, Bluetooth (Bluetooth, Abbreviation: BT) technology and other technologies to achieve.

In an exemplary embodiment, the image recognition apparatus 800 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), digital signal processors (Digital Signal Processor, DSP for short), digital signal processing devices ( Digital Signal Processing Device, referred to as: DSPD), programmable logic device (Programmable Logic Device, referred to as: PLD), field programmable gate array (Field Programmable Gate Array, referred to as: FPGA), controller, microcontroller, microprocessor or other electronic components to implement the above method.

In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium including instructions, such as the memory 804 including instructions, which can be executed by the processor 820 of the image recognition device 800 to complete the above method. For example, the non-transitory computer-readable storage medium may be ROM, random access memory (Random Access Memory, referred to as: RAM), read-only disc (Compact Disc Read-Only Memory, referred to as: CD-ROM), magnetic tape, floppy disk and optical data storage devices, etc.

A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the terminal device, the terminal device can execute the method: acquire the image feature and size information of the object to be identified; according to the image feature and size information to identify the object to be identified.

Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and examples are to be considered exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (10)

1. An image recognition method, characterized in that, comprising: Obtain the image features and size information of the object to be recognized; The object to be recognized is recognized according to the image feature and the size information. 2. The method according to claim 1, wherein said acquiring image features and size information of the object to be identified comprises: Obtaining image features and depth information of the object to be identified through a camera; According to the depth information, the size information is obtained. 3. The method according to claim 1, wherein the identifying the object to be identified according to the image features and the size information comprises: Determine a first object set according to the image features, the first object set includes at least the object to be identified; In the first object set, the object to be identified is identified according to the size information. 4. The method according to any one of claims 1 to 3, characterized in that the method further comprises: Acquiring tag information of the object to be identified; Correspondingly, the identifying the object to be identified according to the image feature and the size information includes: determining a second object set according to the image features and the size information, the second object set including at least the object to be identified; In the second object set, the object to be identified is identified according to the tag information. 5. An image recognition device, characterized in that it comprises: The first acquisition module is configured to acquire image features and size information of the object to be identified; The identification module is configured to identify the object to be identified according to the image features and the size information. 6. The device according to claim 5, wherein the first acquisition module is configured to: Obtaining image features and depth information of the object to be identified through a camera; According to the depth information, the size information is obtained. 7. The device according to claim 5, wherein the identification module comprises: The determining submodule is configured to determine a first object set according to the image features, and the first object set includes at least the object to be identified; The identification submodule is configured to identify the object to be identified in the first object set according to the size information. 8. The device according to any one of claims 5 to 7, further comprising: The second acquiring module is configured to acquire the label information of the object to be identified; Correspondingly, the identification module is configured to: determining a second object set according to the image features and the size information, the second object set including at least the object to be identified; In the second object set, the object to be identified is identified according to the tag information. 9. An image recognition device, characterized in that it comprises: processor and memory for storing executable instructions; Wherein, the processor is configured to execute the executable instructions to perform the image recognition method according to any one of claims 1-4. 10. A computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the image recognition method according to any one of claims 1 to 4 is implemented.