CN108712609A - Focusing processing method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a focusing processing method, a device, equipment and a storage medium, wherein the method comprises the steps of carrying out main body identification on a picture currently acquired by a camera module by using a preset neural network, and determining a target main body and position information of the target main body in the currently acquired picture; determining a current corresponding target shooting mode of the camera module according to the type of the target main body; controlling a camera module to focus the target body according to the position information of the target body, and shooting an image containing the target body in a target shooting mode; the preset neural network is obtained by training by taking various types of shooting subjects as samples. The method realizes that the target main body in the collected picture is identified by utilizing the neural network, and the target main body is automatically focused according to the position of the target main body, thereby not only improving the quality of the shot picture, effectively avoiding the phenomenon of fuzzy shot picture, but also reducing manual operation, facilitating the use of users and improving the user experience.

Description

Focus processing method, device, equipment and storage medium

technical field

The present application relates to the field of electronic technology, and in particular to a focus processing method, device, equipment and storage medium.

Background technique

When a user uses a terminal device including a camera module to take pictures, in order to obtain a clear and high-quality image, the user generally performs a focusing operation on the camera module according to the shooting picture. Among them, focusing refers to the process of adjusting the positions of the object distance and the image distance by moving the focusing mechanism in the camera module, so that the imaging of the object to be photographed becomes clear.

At present, when performing a focusing operation on a shooting screen, two methods of manual focusing and automatic focusing can be used. Among them, the manual focus method mainly selects the object to be photographed manually, and manually rotates the focus ring to adjust the camera lens to make the captured image clear, while the automatic focus method uses the camera module to directly receive and analyze the reflection from the scene itself, and perform Autofocus method. This autofocus method is greatly affected by light, and it is difficult to focus in low contrast and weak light, and it is difficult to autofocus on subjects with thin lines.

When using the manual focus method to focus, the user needs to participate frequently. For example, the user manually selects the focus point, and when the user clicks the touch screen, it will cause the terminal device to shake, which affects the focusing process; when using the automatic focus method to focus, it is easy to be affected by light. Due to the restriction of conditions, when the light is dark or the light and shade difference between the object and the background is very small, it makes focusing difficult or even useless, thus affecting the normal use of users.

Contents of the invention

The present application aims to solve one of the above-mentioned technical deficiencies at least to a certain extent.

For this reason, the first purpose of the present application is to propose a focus processing method, which realizes the target subject in the captured picture by using the neural network recognition, and according to the position of the target subject, the target subject is automatically focused, not only The quality of the shooting picture is improved, the blurred phenomenon of the shooting picture is effectively avoided, and manual operations can be reduced, which is convenient for users to use and improves user experience.

The second purpose of the present application is to provide a focus processing device.

The third purpose of the present application is to provide a terminal device.

The fourth object of the present application is to provide a computer-readable storage medium.

In order to achieve the above purpose, the focus processing method of the embodiment of the first aspect of the present application includes: using a preset neural network to perform subject recognition on the picture currently collected by the camera module, and determine the target subject and the subject included in the currently collected picture. The position information of the target subject; according to the type of the target subject, determine the target shooting mode currently corresponding to the camera module; according to the position information of the target subject, control the camera module to capture the target subject Focusing, and shooting an image including the target subject in the target shooting mode; wherein, the preset neural network is obtained by training with various types of shooting subjects as samples.

In order to achieve the above purpose, the focusing processing device in the second embodiment of the present application includes: a first determining module, configured to use a preset neural network to identify the subject of the currently captured picture by the camera module, and determine the currently captured The target subject included in the screen and the position information of the target subject; the second determination module is used to determine the target shooting mode currently corresponding to the camera module according to the type of the target subject; the control module is used to determine the target shooting mode according to the type of the target subject The position information of the target subject controls the camera module to focus on the target subject, and shoots an image containing the target subject in the target shooting mode; wherein, the preset neural network is It is obtained by training with various types of subjects as samples.

In order to achieve the above purpose, the terminal device in the embodiment of the third aspect of the present application includes: a memory, a processor, a camera module, and a touch screen; the camera module is used to capture the shooting picture; the touch screen is used to display the screen and receiving user operations; the memory is used to store executable program code; the processor is used to read the executable program code stored in the memory to run a program corresponding to the executable program code, It is used to implement the focus processing method described in the embodiment of the first aspect.

In order to achieve the above object, the computer-readable storage medium of the embodiment of the fourth aspect of the present application has a computer program stored thereon, and when the computer program is executed by a processor, the focus processing method described in the embodiment of the first aspect is implemented.

The technical solution disclosed in this application has the following beneficial effects:

By using the preset neural network to perform subject recognition on the picture currently collected by the camera module, the target subject and the location information of the target subject included in the currently collected picture are determined, and according to the type of the target subject, the current subject of the camera module is determined. The corresponding target shooting mode, and then according to the position information of the target subject, control the camera module to focus on the target subject, and shoot images containing the target subject in the target shooting mode, and the preset neural network is used for various types of shooting The subject is obtained by sample training. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein,

FIG. 1 is a flowchart of a focus processing method according to an embodiment of the present application;

FIG. 2 is a flowchart of a focus processing method according to another embodiment of the present application;

FIG. 3 is a schematic structural diagram of a focus processing device according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a terminal device according to another embodiment of the present application.

Detailed ways

Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, and are intended to explain the present application, and should not be construed as limiting the present application.

In order to solve the problem in related technologies, when using manual focus to focus, the user needs to participate frequently, and when the user clicks on the touch screen, it will also cause the terminal device to shake, which affects the focusing process; When the light is dark or the light and shade difference between the object and the background is very small, the focus becomes difficult or even loses its function, which affects the normal use of the user. A focus processing method is proposed.

The focus processing method provided by this application uses a preset neural network to identify the subject of the currently captured picture by the camera module, so as to determine the target subject and the location information of the target subject included in the currently collected picture, and according to the type, determine the target shooting mode currently corresponding to the camera module, and then control the camera module to focus on the target subject according to the position information of the target subject, and shoot an image containing the target subject in the target shooting mode, in which the preset neural network , which is obtained by training with various types of subjects as samples. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience.

The focus processing method, device, device, and storage medium in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Firstly, the focus processing method in this application will be specifically described with reference to FIG. 1 .

Fig. 1 is a flowchart of a focus processing method according to an embodiment of the present application.

As shown in Figure 1, the focus processing method of the present application may include the following steps:

Step 101, using a preset neural network to perform subject recognition on the picture currently captured by the camera module, and determine the target subject and the location information of the target subject included in the currently captured picture.

Optionally, the preset neural network can be trained by taking various types of subjects as samples.

Wherein, the preset neural network may be preset in the terminal device by the manufacturer before leaving the factory, so as to realize subject recognition on the pictures collected by the camera module.

Generally, the preset neural networks set in different terminal devices may be the same or different, which is not specifically limited in this embodiment.

In addition, the type of neural network can be selected according to needs, for example, it can be an ordinary convolutional neural network (CNN), or it can be a Fast-R-CNN convolutional neural network, or it can also be a Faster R-CNN convolution Neural Networks.

In practical applications, in order to facilitate subsequent determination of the location information of the target subject, the preset neural network can first define a coordinate system for the captured picture when performing subject recognition on the picture captured by the camera module. For example, the upper left corner of the captured picture is The origin of the coordinate system, from the origin to the right is the positive direction of the X-axis, and downwards is the positive direction of the y-axis, so as to realize the identification of the subject in the captured picture, not only the type of the subject can be identified, but also the corresponding position information of the subject can be identified .

It should be noted that the focus processing method provided in the embodiment of the present application can be executed by the focus processing device provided in the present application, and the above device is configured in a terminal device to control the process of determining the target subject.

Wherein, the terminal device may be any hardware device with a camera module, such as a smart phone, a personal digital assistant (Personal Digital Assistant, PDA for short), a tablet computer, etc., which is not specifically limited in this application.

During specific implementation, the focus processing device can first detect whether the camera module currently captures a picture, and if it detects that the camera module currently captures a picture, it uses a preset neural network to perform main processing on the picture currently captured by the camera module. Identify, so as to identify all subjects included in the currently captured frame and the corresponding position information of all subjects.

It should be noted that if only one subject is included in the currently collected picture, then the subject is the target subject, and if the currently collected picture includes multiple subjects, the pre-set selection rules are used to select from all identified subjects Determine the target subject and the position information of the target subject included in the current acquisition frame.

Wherein, the preset selection rule may be defaulted by the device, or manually set by the user, which is not specifically limited in this application.

For example, the preset selection rule may default to identifying the subject closest to the middle of the captured image as the target subject.

It should be noted that, in this embodiment, when the preset neural network is used to perform subject recognition on the picture currently captured by the camera module, the recognized subject types may be people, animals, plants, buildings and so on. Correspondingly, the determined type of the target subject may also be a person, an animal, a plant, a building, etc., which is not specifically limited in this embodiment.

Step 102, according to the type of the target subject, determine the target shooting mode currently corresponding to the camera module.

In practical applications, in order to meet users’ needs for taking pictures in different scenarios, manufacturers will configure various shooting modes for the camera module, such as landscape mode, portrait mode, night scene mode, dynamic mode (sports mode), macro mode , panorama mode, and more. That is to say, when the user is taking pictures of different scenes, he can adjust the shooting mode of the camera module according to the subject of the shooting, so as to obtain images with good quality.

For example, when taking pictures of people, the shooting mode of the camera module can be set to portrait mode, so that the camera module can adjust the tone, contrast or softening effect according to the portrait mode, so that the captured image highlights the portrait subject.

For another example, when shooting a night scene, the shooting mode of the camera module can be set to night scene mode, so that the camera module uses a slower shutter exposure time, a smaller aperture and closes the flashlight at the same time to take a brighter image.

An optional implementation form, after determining the target subject and the position information of the target subject included in the current captured image, the focus processing device can determine the current target shooting mode corresponding to the camera module according to the type of the target subject, Therefore, subsequent shooting can be performed according to the determined target shooting mode.

For example, if it is determined that the type of the target subject belongs to "animal", and "animal" is usually more active, that is, in a state of motion, then the focus processing device can determine the camera module according to the characteristics of the "animal". The current corresponding target shooting mode is: dynamic mode.

For another example, when it is determined that the type of the target subject is "landscape", the focusing processing device can determine that the current target shooting mode corresponding to the camera module is: landscape mode according to "landscape".

For another example, when it is determined that the type of the target subject belongs to "flower", in order to capture the details of "flower", the focus processing device can determine that the current target shooting mode corresponding to the camera module is: macro mode, etc. .

Step 103, according to the location information of the target subject, control the camera module to focus on the target subject, and capture an image including the target subject in the target shooting mode.

Specifically, after determining the target subject and the position information of the target subject included in the image currently captured by the camera module, and the corresponding target shooting mode, the focus processing device can control the camera module to focus on the target subject according to the position information of the target subject. Perform a focusing operation, and capture an image including the target subject in target shooting mode.

For example, if the determined target subject is "dog", and the position information of the puppy is (3, 5), then the focusing processing device may determine that the type of the target subject is "animal", and correspondingly, according to "animal "Determine that the shooting mode corresponding to the camera module is "dynamic mode", and then control the movement of the camera module to adjust the focus position to the position specified by (3, 5) to achieve focus on the puppy, and then you can Dynamic mode captures images containing "puppy".

It can be understood that the focus processing device in this embodiment uses a preset neural network to identify the subject of the picture captured by the camera module, and determines the target subject and the position information of the target subject, and according to the type of the target subject , determine the shooting mode corresponding to the camera module, and then control the camera module to move to the position of the target subject to achieve automatic focus on the target subject, and use the determined shooting mode to capture images containing the target subject, which not only improves It not only improves the quality of shooting pictures, but also effectively solves the problem of poor auto-focus effect caused by traditional camera modules being restricted by lighting conditions, and effectively improves user satisfaction.

The focus processing method provided by this application uses a preset neural network to identify the subject of the currently captured picture by the camera module, so as to determine the target subject and the location information of the target subject included in the currently collected picture, and according to the type, determine the target shooting mode currently corresponding to the camera module, and then control the camera module to focus on the target subject according to the position information of the target subject, and capture an image containing the target subject in the target shooting mode, in which the preset nerve The network is obtained by training with various types of subjects as samples. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience.

From the above analysis, it can be seen that in the embodiment of the present application, when taking pictures, the camera module can use the preset neural network to perform subject recognition on the currently captured picture, so as to determine the target subject and the position of the target subject included in the current captured picture information, and then control the camera module to focus on the target subject according to the position information of the target subject.

In the actual implementation, due to the use of the preset neural network, all the subjects and the position information of all subjects included in the picture currently collected by the camera module are recognized, and when there are multiple subjects in the picture, it is necessary to Defined rules to determine the target subject and the location of the target subject. The process of determining the target subject and the location information of the target subject from all identified subjects will be specifically described below in conjunction with FIG. 2 .

FIG. 2 is a flow chart of another focus processing method of the present application.

As shown in Figure 2, the focus processing method of the present application may include the following steps:

Step 201, using a preset neural network to perform subject recognition on the picture currently captured by the camera module.

Wherein, for the specific implementation process and principle of the above step 201, reference may be made to the detailed description of the above embodiment, which will not be repeated here.

Step 202, determine the candidate subject set included in the currently captured frame, and the position information of each candidate subject in the candidate subject set.

Wherein, in this embodiment, the set of candidate subjects specifically refers to a set of all subjects included in the currently captured image.

Specifically, after using the preset neural network to perform subject recognition on the picture currently captured by the camera module, the focusing processing device can form all identified subjects into a candidate subject set.

Correspondingly, when using the preset neural network to identify all the subjects included in the picture currently captured by the camera module, the position information corresponding to all the subjects can be determined at the same time.

In this embodiment, after determining the candidate subject set and the location information of each candidate subject in the candidate subject set, in order to facilitate subsequent operations, the corresponding location information of each subject can be stored correspondingly with the subject; or, all subjects can also be The corresponding location information is displayed next to each subject in the preview screen.

Step 203, selecting a target subject from the candidate subject set.

During specific implementation, this embodiment can implement the selection of the target subject from the candidate subject set in the following ways, as illustrated below:

The first implementation method:

According to the user's operation, select the target subject from the candidate subject set;

Wherein, the user's operation may be a manual click, or a voice selection or the like.

In a possible implementation form, after the candidate subject set included in the picture currently captured by the camera module is determined, each subject in the candidate subject set can be specially displayed on the touch screen of the terminal device. For example, you can use selection boxes of different colors to frame each subject in each selection box. At this time, the user can select one or more boxes from multiple selection boxes according to his own needs, and then the camera module can select the user The principals in the selection box of are used as the target principals.

For example, if the set of candidate subjects displayed on the touch screen of the terminal device includes three candidate subjects, namely character A, character B and building C, then the user can select character A from the above three candidate subjects as the target subject; Alternatively, select person B as the target subject.

The second implementation method:

Select the target subject from the candidate subject set according to the matching degree between the position information of each candidate subject and the preset subject position range;

Wherein, the preset subject position range may be a default setting of the device, or may be a user-defined setting, which is not specifically limited here. For example, the preset subject position range is the closest to the middle position and so on.

Optionally, since the focus processing device in this application can determine each candidate subject and the position of each candidate subject included in the currently captured image of the camera module, this embodiment can combine the determined position information of each candidate subject with Match the preset subject position range to determine the target subject corresponding to the current captured image.

For example, if the preset subject position range is to use the candidate subject closest to the middle position of the captured image as the target subject. Then, in actual use, if the candidate subject set determined by the focus processing device includes plant D, plant C, and animal E, and plant D is located at the lower right corner of the captured image, plant C is located at the upper left corner of the captured image, and animal E is located in the middle of the captured image. At this time, it can be determined that the position information of animal E has the highest matching degree with the preset subject position range, so animal E can be selected as the target subject.

Alternatively, the preset subject position range may also be determined according to the shooting habits of the user. For example, the focus processing device can determine the position of the subject in the picture when the user is shooting by analyzing the pictures taken by the user, and then determine the above preset position according to the position of the subject in the picture when the user is shooting. Subject location range.

The third implementation method:

A target subject is selected from each candidate subject according to the type to which each candidate subject belongs and the shooting habit of the user.

Wherein, the types of candidate subjects may include various types, such as: people, plants, animals, buildings and so on.

The shooting habits of the user may refer to the types of subjects that the user often shoots in a period of time, or the way of taking pictures, and the like. Wherein, the period of time may be one month, half a year, one year, etc., which is not specifically limited here.

Specifically, after the set of candidate subjects is determined, the focusing processing device can select a target subject from each candidate subject according to the type of each candidate subject and the shooting habit of the user.

Since the shooting habits of each user may be different in different time periods, before selecting the target subject from the candidate subjects according to the type of each candidate subject and the user’s shooting habits, it is necessary to first analyze the user’s shooting habits. Habits are determined.

During specific implementation, the focusing processing device can analyze the historical picture collections taken by the user to determine the subject information corresponding to the historical picture collections, wherein the subject information can include: the proportions of various types of subjects in the historical picture collections; and then according to each The proportion of type subjects in the historical picture set determines the user's shooting habits. Wherein, the proportions of various types of subjects in the historical picture set may refer to the frequency of shooting of various types of subjects, and the like.

That is to say, by analyzing the pictures taken by the user in the past period of time, to determine the proportion of various types of subjects photographed by the user in the past period of time in the historical picture collection, so that the focus processing device can be based on the historical pictures of various types of subjects photographed by the user. The proportion of the historical screen concentration, combined with the type of the candidate subject, selects the target subject, thereby meeting the user's target subject selection needs in different time periods, avoiding the user's manual operation to select the target subject, and saving operation time.

For example, if the user’s pictures taken in the last month are analyzed, and it is determined that the user has often taken pictures of animal types in the last month, and the candidate subject types in the currently collected pictures include: animals and people, then the focus processing device can be based on the above The user's shooting habit is "the shooting type is animal", and the subject whose type is animal is selected from the candidate subject set as the target subject.

Further, since the user's shooting habit may also include a shooting method, the shooting method may refer to a user's relatively common shooting angle within a period of time, and the like.

Therefore, in this embodiment, when selecting a target subject from each candidate subject according to the type to which each candidate subject belongs and the user's shooting habit, the user's shooting method may also be determined first. Then, the target subject is selected from the candidate subject set according to the determined shooting method and in combination with the type to which each candidate subject belongs.

For example, if the shooting method of the user's shooting pictures in the last month is to use the candidate subject at the lower corner of the captured picture as the target subject, and the type of the shooting subject in the last month is a person, then the focus processing device can according to the user's shooting habits , selecting a candidate subject whose type is a person from the capture screen, and whose character is at a lower corner of the capture screen, as the target subject.

It can be understood that the above methods of selecting a target subject from the candidate subject set can be implemented individually, or in combination of two or two, and of course, can also be implemented in combination of the three, which is not specifically limited in this embodiment.

It should be noted that the above implementation manner is only an exemplary description of this embodiment, and is not intended as a specific limitation of this application.

Step 204, according to the type of the target subject, determine the target shooting mode currently corresponding to the camera module.

Step 205, according to the location information of the target subject, control the camera module to focus on the target subject, and capture an image including the target subject in the target shooting mode.

In one embodiment of the present application, in order to reduce the processing burden of the device processor and improve user satisfaction, the present application can also analyze the pictures taken by the user during a period of time to determine the pictures taken by the user within a period of time Preferences, for example, in the past month, I prefer to shoot architectural subjects. Then, according to the user's photo preferences during a period of time, the preset neural network is simplified to identify and remove other types of subjects that are not related to the types of subjects that the user often shoots during a period of time, and according to the user's shooting preferences over a period of time screen, correct the remaining subject types.

During specific implementation, the focus processing device can first obtain a reference sample set, and analyze each sample in the reference sample set to obtain the subject in each sample, and then use the subject in each sample to perform a neural network pre-set Corrected to generate a neural network corresponding to the user to which the camera module belongs.

In this embodiment, obtaining a reference sample set can be achieved in the following ways, for example:

method one:

Scan the terminal where the camera module is located to obtain a reference sample set;

That is to say, by acquiring a large number of pictures from the local picture collection of the terminal device, the above large number of pictures are used as a reference sample set.

Method 2:

A reference sample set input by the user is received.

During specific implementation, users can obtain reference sample sets from the server in real time through the Internet according to their needs.

Of course, in addition to the above-mentioned several methods of obtaining the reference sample set, other methods may also be used to obtain the reference sample set, which is not specifically limited in this embodiment.

It should be noted that when using each sample in the sample set to correct the preset neural network, the preset neural network can analyze the samples in each sample set to obtain the subject in each sample, and then according to each shot The main body prunes the model, that is, the pruning of the model is completed during the retraining process of the model; or, after the focus processing device obtains the sample set, it can first filter the sample set, and only connect with the user within a period of time Samples of the same subject type that are often taken are input into the preset neural network model to correct the neural network model.

For example, if the subject type that the user has frequently photographed in the last two weeks is a building, then the focus processing device may select a sample whose subject type is a building from the obtained reference sample set, and input it to the preset neural network model. Alternatively, all reference sample sets can also be input into the neural network model, and then the neural network model corrects the model according to the identified subject type and quantity.

The focus processing method of the embodiment of the present application uses the preset neural network to perform subject recognition on the picture currently captured by the camera module, and determines the set of candidate subjects included in the currently captured picture, and the position of each candidate subject in the set of candidate subjects information, and then according to the preset rules, select the target subject from the candidate subject set, and determine the current target shooting mode corresponding to the camera module according to the type of the target subject, and finally control the camera module according to the position information of the target subject. The subject is focused, and in the target shooting mode, an image including the target subject is captured. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience. In addition, according to the user's shooting habits over a period of time, the preset neural network can be corrected to make the corrected neural network more in line with the user's needs, so that the user can more quickly and accurately identify images based on the corrected neural network. out the favorite target subjects.

In order to realize the above embodiments, the present application also proposes a focusing processing device.

Fig. 3 is a schematic structural diagram of a focusing processing device according to an embodiment of the present application.

As shown in FIG. 3 , the focus processing device of the present application includes: a first determination module 11 , a second determination module 12 and a control module 13 .

Wherein, the first determining module 11 is configured to use a preset neural network to perform subject identification on the picture currently collected by the camera module, and determine the target subject included in the currently collected picture and the position information of the target subject;

The preset neural network is obtained through training with various types of shooting subjects as samples.

The second determination module 12 is used to determine the target shooting mode currently corresponding to the camera module according to the type of the target subject;

The control module 13 is configured to control the camera module to focus on the target subject according to the position information of the target subject, and capture an image including the target subject in the target shooting mode.

In an embodiment of the present application, the first determination module 11 includes: a determination subunit 111 and a selection subunit 112 .

Wherein, the determining subunit 111 is configured to determine the set of candidate subjects included in the currently collected picture, and the position information of each candidate subject in the set of candidate subjects;

The selection subunit 112 is used for selecting a target subject from the candidate subject set.

It should be noted that the foregoing explanations of the embodiment of the focus processing method are also applicable to the focus processing device of this embodiment, and its implementation principles are similar, so details are not repeated here.

The focus processing device provided in this embodiment uses a preset neural network to perform subject recognition on the picture currently captured by the camera module, so as to determine the target subject and the position information of the target subject included in the currently captured picture, and according to the target subject The type to which the camera module belongs determines the target shooting mode currently corresponding to the camera module, and then controls the camera module to focus on the target subject according to the position information of the target subject, and shoots an image containing the target subject in the target shooting mode, wherein the preset The neural network is trained by taking various types of shooting subjects as samples. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience.

In order to implement the foregoing embodiments, the present application further proposes a terminal device.

Fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Referring to FIG. 4 , the embodiment of the present application takes a mobile phone as an example for illustration and display. The terminal device 100 of the present application includes: a memory 21 , a processor 22 , a camera module 23 and a touch screen 24 ;

The camera module 23 is used to collect the shooting picture;

The touch screen 24 is used to display the current acquisition picture and receive user operations;

The memory 21 is used to store executable program codes;

The processor 22 is configured to read the executable program code stored in the memory 21 to run a program corresponding to the executable program code, so as to realize the focus processing method described in the embodiment of the first aspect.

In an optional implementation form, as shown in FIG. 5 , the computer device 200 may further include: a memory 210 and a processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), and the memory 210 stores There is a computer program, and when the processor 220 executes the program, the focus processing method described in the embodiment of the present invention is realized.

Bus 230 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. These architectures include, by way of example, but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect ( PCI) bus.

Computer device 200 typically includes a variety of computer device readable media. These media can be any available media that can be accessed by computer device 200 and include both volatile and nonvolatile media, removable and non-removable media.

Memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and/or cache memory 250 . The computer device 200 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 260 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a disk drive for reading and writing to removable nonvolatile disks (e.g., "floppy disks") may be provided, as well as for removable nonvolatile optical disks (e.g., CD-ROM, DVD-ROM or other optical media) CD-ROM drive. In these cases, each drive may be connected to bus 230 through one or more data media interfaces. Memory 210 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present invention.

Program/utility 280 having a set (at least one) of program modules 270, such as may be stored in memory 210, such program modules 270 including - but not limited to - an operating system, one or more application programs, other program Modules and program data, each or some combination of these examples may include the implementation of the network environment. The program modules 270 generally perform the functions and/or methods of the described embodiments of the invention.

The computer device 200 may also communicate with one or more external devices 290 (e.g., a keyboard, pointing device, display 291, etc.), and may also communicate with one or more devices that enable a user to interact with the computer device 200, and/or communicate with Any device (eg, network card, modem, etc.) that enables the computing device 200 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 292 . Also, the computer device 200 can also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN) and/or a public network, such as the Internet) through the network adapter 293 . As shown, network adapter 293 communicates with other modules of computer device 200 via bus 230 . It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with computer device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

The processor 220 executes various functional applications and data processing by executing programs stored in the memory 210 .

It should be noted that the foregoing explanations of the embodiment of the focus processing method are also applicable to the terminal device of this embodiment, and the implementation principles thereof are similar, and details are not repeated here.

The terminal device provided in this embodiment uses a preset neural network to perform subject recognition on the picture currently collected by the camera module, so as to determine the target subject and the location information of the target subject included in the currently collected picture, and according to the type, determine the target shooting mode currently corresponding to the camera module, and then control the camera module to focus on the target subject according to the position information of the target subject, and capture an image containing the target subject in the target shooting mode, in which the preset nerve The network is obtained by training with various types of subjects as samples. As a result, the neural network is used to identify the target subject in the captured picture, and according to the position of the target subject, the target subject is automatically focused, which not only improves the quality of the shooting picture, but also effectively avoids the blurred phenomenon of the shooting picture , and can also reduce manual operations, which is convenient for users and improves user experience.

In order to implement the above embodiments, the present application also proposes a computer-readable storage medium.

The computer-readable storage medium stores a computer program thereon, and when the program is executed by a processor, the focus processing method of the embodiment of the first aspect is implemented.

In an optional implementation form, this embodiment may use any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more leads, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including - but not limited to - electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including - but not limited to - wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out the operations of the present invention may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural programming language—such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

In this application, unless otherwise clearly specified and limited, the terms "arrangement", "connection" and other terms should be understood in a broad sense, for example, it can be mechanical connection or electrical connection; it can be direct connection or through An indirect connection through an intermediary may be an internal communication between two elements or an interaction relationship between two elements, unless otherwise clearly defined. Those of ordinary skill in the art can understand the specific meanings of the above terms in this application according to specific situations.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present application.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent modules, segments or portions of code comprising one or more executable instructions for implementing specific logical functions or steps of the process , and the scope of preferred embodiments of the present application includes additional implementations in which functions may be performed out of the order shown or discussed, including in substantially simultaneous fashion or in reverse order depending on the functions involved, which shall It should be understood by those skilled in the art to which the embodiments of the present application belong.

It should be understood that each part of the present application may be realized by hardware, software, firmware or a combination thereof. In the embodiments described above, various steps or methods may be implemented by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques known in the art: Discrete logic circuits, ASICs with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. During execution, one or a combination of the steps of the method embodiments is included.

The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present application, and those skilled in the art can make the above-mentioned The embodiments are subject to changes, modifications, substitutions and variations.

Claims (10)

1. A focus processing method, characterized in that, comprising: Using the preset neural network to perform subject recognition on the picture currently collected by the camera module, and determine the target subject included in the currently collected picture and the position information of the target subject; Determine the target shooting mode currently corresponding to the camera module according to the type of the target subject; controlling the camera module to focus on the target subject according to the position information of the target subject, and capturing an image including the target subject in the target shooting mode; Wherein, the preset neural network is obtained through training with various types of shooting subjects as samples. 2. The method according to claim 1, wherein the determining the target subject included in the currently captured picture comprises: determining a set of candidate subjects included in the currently collected picture, and position information of each candidate subject in the set of candidate subjects; A target subject is selected from the candidate subject set. 3. The method according to claim 1, wherein said selecting a target subject from said candidate subject set comprises: selecting a target subject from the candidate subject set according to the user's operation; and / or, selecting a target subject from the set of candidate subjects according to the matching degree between the position information of each candidate subject and the preset subject position range; and / or, A target subject is selected from the candidate subjects according to the type to which the candidate subjects belong and the shooting habit of the user. 4. The method according to claim 3, wherein, before selecting the target subject from the candidate subjects according to the type of the candidate subjects and the shooting habits of the user, further comprising: Analyzing the set of historical pictures taken by the user, and determining subject information corresponding to the set of historical pictures, the subject information includes the proportion of various types of subjects in the set of historical pictures; According to the proportions of the subjects of various types in the set of historical pictures, the photographing habit of the user is determined. 5. The method of claim 1, wherein the method further comprises: Obtain a reference sample set; Analyzing each sample in the reference sample set to obtain the subject in each sample; Using the shooting subjects in the samples, the preset neural network is corrected to generate a neural network corresponding to the user to which the camera module belongs. 6. The method according to claim 5, wherein said obtaining a reference sample set comprises: Scanning the terminal where the camera module is located to obtain a reference sample set; or, A reference sample set input by the user is received. 7. A focus processing device, comprising: The first determination module is configured to use a preset neural network to perform subject identification on the picture currently collected by the camera module, and determine the target subject included in the currently collected picture and the position information of the target subject; The second determination module is used to determine the target shooting mode currently corresponding to the camera module according to the type of the target subject; A control module, configured to control the camera module to focus on the target subject according to the position information of the target subject, and capture an image containing the target subject in the target shooting mode; Wherein, the preset neural network is obtained through training with various types of shooting subjects as samples. 8. The device according to claim 7, wherein the first determining module comprises: A determining subunit, configured to determine a set of candidate subjects included in the currently captured picture, and position information of each candidate subject in the set of candidate subjects; The selection subunit is used to select a target subject from the candidate subject set. 9. A terminal device, characterized in that it comprises: a memory, a processor, a camera module and a touch screen; The camera module is used to collect and shoot pictures; The touch screen is used to display the current acquisition screen and receive user operations; The memory is used to store executable program codes; The processor is configured to read the executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the focus processing method according to any one of claims 1-6 . 10. A computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the focus processing method according to any one of claims 1-6 is implemented.