WO2016180224A1 - Method and device for processing image of person - Google Patents

Abstract

The present invention relates to the technical field of image processing. Disclosed are a method and device for processing an image of a person. The method comprises: acquiring a face region in a target image according to a preset face recognition algorithm; when the number of the acquired face regions is two or more, differentiating, according to a preset classification algorithm and/or a selection operation of a user, the acquired face regions into a foreground face region and a background face region; and processing, according to a preset first image processing algorithm, the background face region obtained by the differentiation, such that a visual effect of the background face region obtained by the differentiation worsens. The solution of the present invention effectively distinguishes an individual person in an image obtained via photographing.

Description

Character image processing method and device

The present application claims priority to Chinese Patent Application No. 201510235866.5, entitled "A Person Image Processing Method and Apparatus", filed on May 11, 2015, the entire contents of which is incorporated herein by reference. .

Technical field

The present application relates to the field of image processing technologies, and in particular, to a method and device for processing a person image.

Background technique

In daily life, people usually take photos through terminals such as mobile phones, tablets, and cameras. In the prior art, in order to obtain a character image with better visual effect, the user generally sets a shooting mode of the relevant application, for example, “beauty mode”, so that the terminal is set according to the user after the shooting is performed. The shooting mode processes the captured image of the person and presents the processed person image to the user.

Specifically, after the user selects the shooting mode, all the face regions in the captured person image are beautified, but in practical applications, the user may need to beautify only a few of the face regions to highlight These face areas that have been beautified are processed. Therefore, after the captured image of the person is processed in the above manner, the individual characters in the person image cannot be effectively distinguished.

Summary of the invention

The embodiment of the present application discloses an image processing method and apparatus, so as to be able to effectively distinguish individual characters in the captured image.

To achieve the above objective, the embodiment of the present application discloses a method for processing a character image, and the method includes:

Obtaining a face region in the target image according to a preset face recognition algorithm;

In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.

In a specific implementation of the present application, the target image is obtained by:

Determining image data acquired by the image acquisition device in real time as a target image;

or

A target image is obtained from the stored image set in accordance with a user's selection operation for the stored image set.

In a specific implementation manner of the application, the character image processing method further includes:

The image processed as described above for the background face area is stored and presented to the user.

In a specific implementation manner of the present application, the preset first image processing algorithm includes at least one of the following image processing modes:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

In a specific implementation manner of the present application, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm, including:

Calculating the area of each face area obtained separately;

Sorting the obtained face regions in descending order of area;

According to the sorting result and the preset first number N1, the first N1 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

In a specific implementation manner of the present application, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm, including:

Obtaining a face credibility corresponding to each of the obtained face regions, wherein the face credibility is: a probability for indicating that the region is a face region;

Sorting the obtained face regions in descending order of face credibility;

According to the sorting result and the preset second number N2, the first N2 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

In a specific implementation manner of the application, the character image processing method further includes:

According to the preset second image processing algorithm, the differentiated foreground face region is processed, so that the visual effect of the differentiated foreground face region is improved.

In order to achieve the above object, an embodiment of the present application discloses a character image processing apparatus, and the device Set includes:

a face area obtaining module, configured to obtain a face area in the target image according to a preset face recognition algorithm;

a face area distinguishing module, configured to divide the obtained face area into a foreground according to a preset classification algorithm and/or according to a user's selection operation, if the obtained number of face regions is not less than two Face area and background face area;

The first face area processing module is configured to process the differentiated background face area according to the preset first image processing algorithm, so that the visual effect of the differentiated background face area is deteriorated.

In a specific implementation of the present application, the character image processing apparatus further includes:

a target image obtaining module, configured to determine image data acquired by the image capturing device in real time as a target image;

or

A target image is obtained from the stored image set according to a user's selection operation for the stored image set.

In a specific implementation of the present application, the character image processing apparatus further includes:

The image display module is configured to store the image processed by the background face region and display the image to the user.

In a specific implementation manner of the present application, the preset first image processing algorithm includes at least one of the following image processing modes:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

In a specific implementation manner of the present application, the face area distinguishing module includes: a first face area area molecular module and/or a second face area area molecular module;

The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

The second human face region molecular module is used for the number of face regions obtained by not less than two In the case of the user's selection operation, the obtained face area is divided into a foreground face area and a background face area;

Specifically, the first face region region molecular module includes: a region area calculation unit, a first sorting unit, and a first face region determining unit;

The area calculation unit is configured to separately calculate the area of each of the obtained face regions;

The first sorting unit is configured to sort the obtained face regions in descending order of area of the area;

The first face region determining unit is configured to determine a front N1 personal face region in the sorting result as a foreground face region according to the sorting result and the preset first number N1, and determine the remaining face region as a background. Face area.

In a specific implementation manner of the present application, the face area distinguishing module includes: a first face area area molecular module and/or a second face area area molecular module;

The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

The second face region region molecular module is configured to divide the obtained face region into a foreground face region according to a user's selection operation in a case where the obtained number of face regions is not less than two. Background face area;

Specifically, the first face region region molecular module includes: a face credibility obtaining unit, a second sorting unit, and a second face region determining unit;

The face credibility obtaining unit is configured to obtain the obtained credibility of the face corresponding to each face region, where the credibility of the face is: used to indicate that the region is a face region. Probability

The second sorting unit is configured to sort the obtained face regions in descending order of face trustworthiness;

The second face region determining unit is configured to determine a front N2 personal face region in the sorting result as a foreground face region according to the sorting result and a preset second number N2, and determine the remaining face region as a background person Face area.

In a specific implementation manner of the present application, the character image processing apparatus further includes: a second face area processing module;

The second face area processing module is configured to process the differentiated foreground face area according to the preset second image processing algorithm, so that the visual effect of the differentiated foreground face area is improved. .

To achieve the above objective, the embodiment of the present application discloses a terminal, where the terminal includes:

a processor, a memory, a communication interface, and a bus;

The processor, the memory, and the communication interface are connected by the bus and complete communication with each other;

The memory stores executable program code;

The processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for:

Obtaining a face region in the target image according to a preset face recognition algorithm;

In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.

Correspondingly, the embodiment of the present application further provides an application program for executing the character image processing method described in the embodiment of the present application at runtime.

Correspondingly, the embodiment of the present application further provides a storage medium for storing an application, and the application is used to execute the character image processing method described in the embodiment of the present application.

It can be seen from the above that, in the solution provided by the embodiment of the present application, after obtaining the face region in the target image, if the number of the obtained face regions is not less than two, the obtained face region is divided into The foreground face area and the background face area process the differentiated background face area, so that the visual effect of the background face area is deteriorated. Since the visual effect of the background face area after processing is deteriorated, it is possible to provide a better visual effect from the reverse side to the foreground face area. Therefore, the solution provided in the embodiment of the present application can effectively distinguish the characters in the foreground face region in the target image, and can display the characters in the foreground face region with a relatively better visual effect.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application and the technical solutions of the prior art, the following description of the embodiments and the drawings used in the prior art will be briefly introduced. Obviously, the drawings in the following description are only Some embodiments of the application may also be used to obtain other figures from those of ordinary skill in the art without departing from the scope of the invention.

FIG. 1 is a schematic flowchart diagram of a method for processing a character image according to an embodiment of the present application;

Figure 2 is an original person image;

Figure 3a is an image after identifying a face region in the image shown in Figure 2;

Figure 3b is an image after the face region in the image shown in Figure 3a is divided into a foreground face region and a background face region;

Figure 3c is an image of the background face area in the image shown in Figure 3b;

Figure 3d is another image of the background face region in the image shown in Figure 3b;

FIG. 4 is a schematic flowchart diagram of another method for processing a character image according to an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of a character image processing apparatus according to an embodiment of the present disclosure;

FIG. 6 is a schematic structural diagram of another character image processing apparatus according to an embodiment of the present application.

detailed description

In order to make the objects, technical solutions, and advantages of the present application more comprehensible, the present application will be further described in detail below with reference to the accompanying drawings. It is apparent that the described embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope are the scope of the present application.

FIG. 1 is a schematic flowchart of a method for processing a character image according to an embodiment of the present disclosure, where the method includes:

S101: Obtain a face region in the target image according to a preset face recognition algorithm.

In practical applications, the image data collected by the image acquisition device in real time may be determined as a target image, wherein the image acquisition device may be a mobile phone with a camera, a tablet computer with a camera, a digital camera, a digital video camera, and the like.

For example, when an image is taken using a mobile phone with a camera, the image captured by the mobile phone can be directly determined as the target image;

When shooting a video with a camera-equipped mobile phone, you can directly use each video frame captured by the mobile phone as the target image.

In addition, the target image can also be obtained from the stored image set according to the user's selection operation for the stored image set.

S102: In the case that the obtained number of face regions is not less than two, the obtained face region is divided into the foreground face region and the background person according to a preset classification algorithm and/or according to a user's selection operation. Face area.

When photographing a person's image, the position of the main character is generally higher, so that the face area of the main character in the captured image is generally larger than the face area of other characters in the image.

In view of this, in a specific implementation manner of the present application, according to a preset classification algorithm, when the obtained face region is divided into a foreground face region and a background face region, the obtained face region may be The area is divided.

Specifically, the area of each obtained face area is separately calculated, and the obtained face areas are sorted according to the area of the area from large to small, and then according to the sorting result and the preset first quantity N1, The first N1 personal face area in the sort result is determined as the foreground face area, and the remaining face area is determined as the background face area.

In addition, in practical applications, due to factors such as surrounding objects, scene light, shooting angle, and the robustness of the preset face recognition algorithm, when the face region in the target image is obtained, it is not guaranteed to be completely accurate. The face area in the target image is recognized. Generally, after the face recognition algorithm is used for face recognition, in addition to the face region recognized by the face recognition algorithm, the region can be calculated according to the feature information of the recognized face region. For the probability of a face region, this probability can be called face confidence.

In view of this, in another specific implementation manner of the present application, according to a preset classification algorithm, when the obtained face region is divided into a foreground face region and a background face region, the obtained face may also be obtained according to the obtained face. The face credibility of the area is differentiated.

Specifically, firstly, the obtained face credibility corresponding to each face region is obtained, and the obtained face regions are sorted according to the order of the face credibility from large to small, and then according to the sorting result and the preset The second number N2 determines the front N2 personal face region in the ranking result as the foreground face region, and determines the remaining face region as the background face region.

According to the preset classification algorithm, when the obtained face region is divided into the foreground face region and the background face region, in addition to the above-mentioned region area and face credibility, the face region may also be considered. The characteristics of the facial features and other factors.

For example, after obtaining the face region in the target image, the facial features such as the eyes, the nose, and the mouth in the obtained face region can be identified by the image feature extraction algorithm, the image edge extraction algorithm, and the like, and further based on the identified facial features. The facial expression of the person can be determined. Specifically, the facial expression of the person can be determined by the shape of the eye, the shape of the mouth, and the like.

After determining the facial expressions of the characters corresponding to the obtained face regions, the obtained facial regions are sorted according to the order of the facial expressions of the characters from high to low, according to the sorting result and the preset third number N3, The former N3 face area in the sort result is determined as the foreground face area, and the remaining face area is determined as the background face area.

The degree of facial expression of the character is used to indicate the degree of facial deformation of the person. For example, if the character's mouth is in a normally closed state, the facial expression of the character is less active, and if the character's mouth is in a large state, smiling Status, etc., the character's facial expression is more active and so on.

It should be noted that the present application only takes the above as an example to explain how to obtain the obtained face region into the foreground face region and the background face region. In practical applications, the distinguishing manner is not limited to the above cases.

The preset first number, the preset second number, and the preset third number are integers not less than one.

According to the user's selection operation, when the obtained face region is divided into the foreground face region and the background face region, the face region selected by the user may be determined as the foreground face region, and the obtained face region is obtained. The face area that is not selected by the user is determined as the background face area. In addition, the face area selected by the user may be determined as the background face area, and the obtained face area is not selected by the user. Determined as the foreground face area.

The face area selected by the user may include a face area, and may also include multiple face areas, which is not limited in this application.

It can be understood that, according to the preset classification algorithm, when the obtained face region is divided into the foreground face region and the background face region, the distinction of the face region can be completed without a user operation. However, Generally, any classification algorithm may not be consistent with the ideal face region classification algorithm of all users. Therefore, in order to provide a better experience to the user in practical applications, it may be considered when distinguishing the face region. The preset classification algorithm is combined with the user's selection operation, that is, after the foreground face region and the background face region are distinguished according to the preset classification algorithm, the user may perform a selection operation based on the above-mentioned discrimination result to further The foreground face area and the background face area obtained by the above distinction are adjusted to meet the real requirements of the user.

S103: Process the differentiated background face region according to the preset first image processing algorithm, so that the visual effect of the differentiated background face region is deteriorated.

Optionally, the preset first image processing algorithm may include at least one of the following image processing modes:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

Wherein, the above deformation processing may include stretching processing, twist processing, enlargement processing, reduction processing, and the like.

For example, the partial enlargement processing may be to enlarge the eyes, the mouth, the nose, and the like of the person. Similarly, the local reduction processing may be to reduce the eyes, mouth, nose, and the like of the person.

Further, when the divided background face region includes a plurality of face regions, the processing performed on each face region may be the same process or a different process.

Further, one or more image processing modes included in the preset first image processing algorithm may be selected to process the face region in the differentiated background face region.

When the image processing mode is selected for the face region in the background face region, the image processing mode may be randomly selected from the preset first image processing algorithm, or may be selected from the preset according to a preset processing mode. The selected one of the first image processing algorithms may also be manually selected by the user, which is not limited in this application.

In an optional embodiment of the present application, after the processed background face region is processed in S103, the image processed by the background face region may also be stored.

Further, in order to facilitate the user to view the processed image, the image processed by the background face region may be stored, and the image may be displayed to the user.

It can be seen from the above that, in the solution provided by the embodiment, after obtaining the face region in the target image, if the number of the obtained face regions is not less than two, the obtained face region is divided into the foreground. The face area and the background face area process the differentiated background face area, so that the visual effect of the background face area is deteriorated. Since the visual effect of the background face area after processing is deteriorated, it is possible to provide a better visual effect from the reverse side to the foreground face area. Therefore, by applying the solution provided by the embodiment, the person in the foreground face region in the target image can be effectively distinguished, and the person in the foreground face region can be displayed with a relatively better visual effect.

The above-described character image processing method will be described below by way of a specific example.

According to S101: face recognition is performed on the original person image shown in FIG. 2 according to a preset face recognition algorithm, and a face region in the image is obtained.

Referring to FIG. 3a, the face region in the original image shown in FIG. 2 obtained by the face recognition process is identified in the form of a rectangular frame.

As can be seen from Fig. 3a, the number of face regions obtained is seven, not less than two.

According to S102: according to the area of the area of the face area identified in FIG. 3a, the face area identified in the figure is distinguished, and is divided into a foreground face area and a background face area.

Referring to Figure 3b, the differentiated foreground face and background face regions are identified.

The identifier of the foreground face area is “F”, and the identifier of the background face area is “B”.

According to S103: the background face region obtained by the discrimination in FIG. 3b is processed, so that the visual effect of the differentiated background face region is deteriorated.

Specifically, referring to FIG. 3c, the figure is an image obtained by obfuscating the background face region obtained in FIG. 3b;

Referring to FIG. 3d, the figure is an image obtained by deforming the differentiated background face region in FIG. 3b.

It can be seen from the above two images of Fig. 3c and Fig. 3d that after processing the background face region, it is obvious that the foreground face region can be distinguished from the background face region, and the foreground can be displayed with a relatively better visual effect. People in the face area.

In a specific embodiment of the present application, referring to FIG. 4, another character image processing party is provided. The flow chart of the method is compared with the foregoing embodiments. In this embodiment, the method further includes:

S104: Process the differentiated foreground face region according to the preset second image processing algorithm, so that the visual effect of the differentiated foreground face region becomes better.

The preset second image processing algorithm may include: dermabrasion treatment, face skin area brightening processing, lip processing, and the like.

It can be seen from the above that in the solution provided by the embodiment, the foreground human face region is subjected to the process of making the background face region visually deteriorated, and the foreground face region obtained by the discrimination is made to make the foreground person The processing of the visual effect of the face region is improved, so that not only the characters in the foreground face region in the target image can be effectively distinguished, but also the characters in the foreground face region can be displayed with better visual effects.

Corresponding to the character image processing method described above, the embodiment of the present application further provides a character image processing apparatus.

FIG. 5 is a schematic structural diagram of a person image processing apparatus according to an embodiment of the present disclosure. The device includes: a face area obtaining module 501, a face area distinguishing module 502, and a first face area processing module 503.

The face area obtaining module 501 is configured to obtain a face area in the target image according to a preset face recognition algorithm;

The face region distinguishing module 502 is configured to: when the obtained number of face regions is not less than two, according to a preset classification algorithm and/or according to a user's selection operation, the obtained face region is divided into The foreground face area and the background face area;

The first face area processing module 503 is configured to process the differentiated background face area according to the preset first image processing algorithm, so that the visual effect of the differentiated background face area is deteriorated.

Specifically, the character image processing apparatus may further include: a target image obtaining module (not shown).

The target image obtaining module is configured to determine image data collected by the image capturing device in real time as a target image;

Or

A target image is obtained from the stored image set according to a user's selection operation for the stored image set.

Specifically, the character image processing apparatus may further include: an image display module (not shown).

The image display module is configured to store the image processed by the background face region and display the image to the user.

Specifically, the preset first image processing algorithm may include at least one of the following image processing modes:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

Optionally, the face region distinguishing module 502 may include: a first face region region molecular module and/or a second face region region molecular module;

The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

The second face region region molecular module is configured to divide the obtained face region into a foreground face region according to a user's selection operation in a case where the obtained number of face regions is not less than two. Background face area;

Specifically, the first face region region molecular module may include: a region area calculation unit, a first sorting unit, and a first face region determining unit;

The area calculation unit is configured to separately calculate the area of each of the obtained face regions;

The first sorting unit is configured to sort the obtained face regions in descending order of area of the area;

The first face region determining unit is configured to determine a front N1 personal face region in the sorting result as a foreground face region according to the sorting result and the preset first number N1, and determine the remaining face region as a background. Face area.

Optionally, the face region distinguishing module 502 may include: a first face region region molecular model Block and/or second face region zone molecular module;

The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

The second face region region molecular module is configured to divide the obtained face region into a foreground face region according to a user's selection operation in a case where the obtained number of face regions is not less than two. Background face area;

Specifically, the first face region region molecular module may include: a face credibility obtaining unit, a second sorting unit, and a second face region determining unit;

The face credibility obtaining unit is configured to obtain the obtained credibility of the face corresponding to each face region, where the credibility of the face is: obtained according to a preset face recognition algorithm. The probability obtained when the face region is used to indicate that the region is a face region;

The second sorting unit is configured to sort the obtained face regions in descending order of face trustworthiness;

The second face region determining unit is configured to determine a front N2 personal face region in the sorting result as a foreground face region according to the sorting result and a preset second number N2, and determine the remaining face region as a background. Face area.

It can be seen from the above that, in the solution provided by the embodiment, after obtaining the face region in the target image, if the number of the obtained face regions is not less than two, the obtained face region is divided into the foreground. The face area and the background face area process the differentiated background face area, so that the visual effect of the background face area is deteriorated. Since the visual effect of the background face area after processing is deteriorated, it is possible to provide a better visual effect from the reverse side to the foreground face area. Therefore, by applying the solution provided by the embodiment, the person in the foreground face region in the target image can be effectively distinguished, and the person in the foreground face region can be displayed with a relatively better visual effect.

In a specific implementation manner of the present application, referring to FIG. 6, a schematic structural diagram of another character image processing apparatus is provided. Compared with the foregoing embodiments, the embodiment further includes: second face area processing. Module 504.

The second face area processing module 504 is configured to calculate according to a preset second image processing. The method processes the differentiated foreground face region, so that the visual effect of the differentiated foreground face region becomes better.

It can be seen from the above that in the solution provided by the embodiment, the foreground human face region is subjected to the process of making the background face region visually deteriorated, and the foreground face region obtained by the discrimination is made to make the foreground person The processing of the visual effect of the face region is improved, so that not only the characters in the foreground face region in the target image can be effectively distinguished, but also the characters in the foreground face region can be displayed with better visual effects.

In addition, the embodiment of the present application further provides a terminal, where the terminal includes:

a processor, a memory, a communication interface, and a bus;

The processor, the memory, and the communication interface are connected by the bus and complete communication with each other;

The memory stores executable program code;

The processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for:

Obtaining a face region in the target image according to a preset face recognition algorithm;

In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.

Specifically, the terminal obtains a target image by:

Determining image data acquired by the image acquisition device in real time as a target image;

or

A target image is obtained from the stored image set in accordance with a user's selection operation for the stored image set.

Specifically, the terminal is further configured to store the image processed by the background face region and display the image to the user.

Specifically, the preset first image processing algorithm includes the following image processing methods. One less:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Calculating the area of each face area obtained separately;

Sorting the obtained face regions in descending order of area;

According to the sorting result and the preset first number N1, the first N1 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Obtaining a face credibility corresponding to each of the obtained face regions, wherein the face credibility is: a probability for indicating that the region is a face region;

Sorting the obtained face regions in descending order of face credibility;

According to the sorting result and the preset second number N2, the first N2 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, the terminal is further configured to process the differentiated foreground face region according to the preset second image processing algorithm, so that the visual effect of the differentiated foreground face region becomes better.

The embodiment of the present application further provides an application program for executing the character image processing method provided by the embodiment of the present application at runtime. Among them, the character image processing method includes:

Obtaining a face region in the target image according to a preset face recognition algorithm;

In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.

Specifically, the target image is obtained by:

Determining image data acquired by the image acquisition device in real time as a target image;

or

A target image is obtained from the stored image set in accordance with a user's selection operation for the stored image set.

Specifically, the character image processing method further includes:

The image processed as described above for the background face area is stored and presented to the user.

Specifically, the preset first image processing algorithm includes at least one of the following image processing methods:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Calculating the area of each face area obtained separately;

Sorting the obtained face regions in descending order of area;

According to the sorting result and the preset first number N1, the first N1 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Obtaining a face credibility corresponding to each of the obtained face regions, wherein the face credibility is: a probability for indicating that the region is a face region;

Sorting the obtained face regions in descending order of face credibility;

According to the sorting result and the preset second number N2, the first N2 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, the character image processing method further includes:

According to the preset second image processing algorithm, the differentiated foreground face region is processed, so that the visual effect of the differentiated foreground face region is improved.

The embodiment of the present application further provides a storage medium for storing an application, the application It is used to perform the character image processing method provided by the embodiment of the present application. Among them, the character image processing method includes:

Obtaining a face region in the target image according to a preset face recognition algorithm;

In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.

Specifically, the target image is obtained by:

Determining image data acquired by the image acquisition device in real time as a target image;

or

A target image is obtained from the stored image set in accordance with a user's selection operation for the stored image set.

Specifically, the character image processing method further includes:

The image processed as described above for the background face area is stored and presented to the user.

Specifically, the preset first image processing algorithm includes at least one of the following image processing methods:

Blurring the face area;

Deformation of part or all of the face area;

Add noise processing to the face area.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Calculating the area of each face area obtained separately;

Sorting the obtained face regions in descending order of area;

According to the sorting result and the preset first number N1, the first N1 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, according to the preset classification algorithm, the obtained face region is divided into a foreground face region and a background face region, including:

Obtaining a face credibility corresponding to each obtained face region, wherein the face credibility Is: the probability of indicating that the area is a face area;

Sorting the obtained face regions in descending order of face credibility;

According to the sorting result and the preset second number N2, the first N2 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.

Specifically, the character image processing method further includes:

According to the preset second image processing algorithm, the differentiated foreground face region is processed, so that the visual effect of the differentiated foreground face region is improved.

For the device, the terminal, the application, and the storage medium embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

It should be noted that, in this context, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply such entities or operations. There is any such actual relationship or order between them. Furthermore, the term "comprises" or "comprises" or "comprises" or any other variations thereof is intended to encompass a non-exclusive inclusion, such that a process, method, article, or device that comprises a plurality of elements includes not only those elements but also Other elements, or elements that are inherent to such a process, method, item, or device. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, method, item, or device that comprises the element.

One of ordinary skill in the art can understand that all or part of the steps in implementing the above method embodiments can be completed by a program to instruct related hardware, and the program can be stored in a computer readable storage medium, which is referred to herein. Storage media such as ROM/RAM, disk, CD, etc.

The above is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., which are made within the spirit and principles of the present application, should be included in the present application. Within the scope of protection.

Claims (17)

1. A character image processing method, the method comprising:

   Obtaining a face region in the target image according to a preset face recognition algorithm;

   In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

   According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.
2. The method according to claim 1, wherein the target image is obtained by:

   Determining image data acquired by the image acquisition device in real time as a target image;

   or

   A target image is obtained from the stored image set in accordance with a user's selection operation for the stored image set.
3. The method of claim 2, wherein the method further comprises:

   The image processed as described above for the background face area is stored and presented to the user.
4. The method according to any one of claims 1 to 3, wherein the preset first image processing algorithm includes at least one of the following image processing methods:

   Blurring the face area;

   Deformation of part or all of the face area;

   Add noise processing to the face area.
5. The method according to claim 4, wherein the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm, including:

   Calculating the area of each face area obtained separately;

   Sorting the obtained face regions in descending order of area;

   According to the sorting result and the preset first number N1, the first N1 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.
6. The method according to claim 4, wherein the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm, including:

   Obtaining a face credibility corresponding to each of the obtained face regions, wherein the face credibility is: a probability for indicating that the region is a face region;

   Sorting the obtained face regions in descending order of face credibility;

   According to the sorting result and the preset second number N2, the first N2 personal face region in the sorting result is determined as the foreground face region, and the remaining face region is determined as the background face region.
7. The method according to any one of claims 1 to 3, wherein the method further comprises:

   According to the preset second image processing algorithm, the differentiated foreground face region is processed, so that the visual effect of the differentiated foreground face region is improved.
8. A character image processing apparatus, characterized in that the apparatus comprises:

   a face area obtaining module, configured to obtain a face area in the target image according to a preset face recognition algorithm;

   a face area distinguishing module, configured to divide the obtained face area into a foreground according to a preset classification algorithm and/or according to a user's selection operation, if the obtained number of face regions is not less than two Face area and background face area;

   The first face area processing module is configured to process the differentiated background face area according to the preset first image processing algorithm, so that the visual effect of the differentiated background face area is deteriorated.
9. The device according to claim 8, wherein the device further comprises:

   a target image obtaining module, configured to determine image data acquired by the image capturing device in real time as a target image;

   or

   A target image is obtained from the stored image set according to a user's selection operation for the stored image set.
10. The device according to claim 9, wherein the device further comprises:

    The image display module is configured to store the image processed by the background face region and display the image to the user.
11. The apparatus according to any one of claims 8 to 10, wherein the preset first image processing algorithm includes at least one of the following image processing methods:

    Blurring the face area;

    Deformation of part or all of the face area;

    Add noise processing to the face area.
12. The apparatus according to claim 11, wherein the face area distinguishing module comprises: a first face area area molecular module and/or a second face area area molecular module;

    The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

    The second face region region molecular module is configured to divide the obtained face region into a foreground face region according to a user's selection operation in a case where the obtained number of face regions is not less than two. Background face area;

    Specifically, the first face region region molecular module includes: a region area calculation unit, a first sorting unit, and a first face region determining unit;

    The area calculation unit is configured to separately calculate the area of each of the obtained face regions;

    The first sorting unit is configured to sort the obtained face regions in descending order of area of the area;

    The first face region determining unit is configured to determine a front N1 personal face region in the sorting result as a foreground face region according to the sorting result and the preset first number N1, and determine the remaining face region as a background. Face area.
13. The apparatus according to claim 11, wherein the face area distinguishing module comprises: a first face area area molecular module and/or a second face area area molecular module;

    The first face region area molecular module is configured to divide the obtained face region into a foreground person according to a preset classification algorithm if the obtained number of face regions is not less than two. Face area and background face area;

    The second face region region molecular module is configured to divide the obtained face region into a foreground face region according to a user's selection operation in a case where the obtained number of face regions is not less than two. Background face area;

    Specifically, the first face area area molecular module includes: a face credibility obtaining unit, a second sorting unit and a second face area determining unit;

    The face credibility obtaining unit is configured to obtain the obtained credibility of the face corresponding to each face region, where the credibility of the face is: used to indicate that the region is a face region. Probability

    The second sorting unit is configured to sort the obtained face regions in descending order of face trustworthiness;

    The second face region determining unit is configured to determine a front N2 personal face region in the sorting result as a foreground face region according to the sorting result and a preset second number N2, and determine the remaining face region as a background person Face area.
14. The device according to any one of claims 8 to 10, further comprising: a second face area processing module;

    The second face area processing module is configured to process the differentiated foreground face area according to the preset second image processing algorithm, so that the visual effect of the differentiated foreground face area is improved. .
15. A terminal, wherein the terminal comprises:

    a processor, a memory, a communication interface, and a bus;

    The processor, the memory, and the communication interface are connected by the bus and complete communication with each other;

    The memory stores executable program code;

    The processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for:

    Obtaining a face region in the target image according to a preset face recognition algorithm;

    In the case that the obtained number of face regions is not less than two, the obtained face region is divided into a foreground face region and a background face region according to a preset classification algorithm and/or according to a user's selection operation. ;

    According to the preset first image processing algorithm, the differentiated background face region is processed, so that the visual effect of the differentiated background face region is deteriorated.
16. An application program for performing the character image processing method according to any one of claims 1 to 7 at runtime.
17. A storage medium for storing an application for performing the character image processing method according to any one of claims 1 to 7.

Images