WO2018177364A1

WO2018177364A1 - Filter implementation method and device

Info

Publication number: WO2018177364A1
Application number: PCT/CN2018/081068
Authority: WO
Inventors: 李亮; 张文明; 陈少杰
Original assignee: 武汉斗鱼网络科技有限公司
Priority date: 2017-03-29
Filing date: 2018-03-29
Publication date: 2018-10-04
Also published as: CN106971165A; CN106971165B

Abstract

Disclosed are a filter implementation method and device. The method comprises: obtaining a face region in a target image, the face region being a region comprising a face image; determining whether sub-region images on the target image belong to the face region or not, wherein the target image is divided into N sub-region images, N is an integer greater than 1; and when the sub-region images do not belong to the face region, blurring the sub-region images using a fuzzy algorithm, replacing the sub-region images with the obtained blurred images, and displaying a final image. By means of the method and the device provided by the present application, the technical problem in the prior art that the video filter has a single function and cannot meet more requirements of users can be solved. The filter function is enriched, and the demands of users for highlighting the human face and increasing the environment secrecy are satisfied.

Description

Method and device for implementing filter

Technical field

The present invention relates to the field of image processing technologies, and in particular, to a method and an apparatus for implementing a filter.

Background technique

At present, various types of Internet business models are emerging one after another, and live video is also one of the dark horses. In order to provide a better visual experience and rich entertainment experience for the live broadcast anchor or viewer, the existing live video will often provide a filter function for the user to use.

The existing filter function is mainly used to realize various special scene effects of the image, generally by directly changing the color style of the image, that is, performing color adjustment. For example, nostalgia, black and white, sketch, beautiful and so on. However, current filter functions are no longer able to meet the increasing demands of users.

It can be seen that the video filter in the prior art has a single function and cannot meet the technical problems of more users' needs.

Summary of the invention

The invention provides a method and a device for implementing a filter, which are used to solve the technical problem that the video filter in the prior art has a single function and cannot meet more demands of users.

In one aspect, the present invention provides a method of implementing a filter, comprising:

Acquiring a face area in the target image, the face area being an area including a face image;

Determining whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, and N is an integer greater than 1;

When the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed.

Optionally, when the target image is an image in a video, the acquiring a face region in the target image includes: alternately using a face detection algorithm and a face tracking algorithm to acquire a target image in the video. Face area.

Optionally, after the determining whether the partition image on the target image belongs to the face region, the method further includes: when the partition image belongs to the face region, adopting a dermabrasion algorithm and/or tone After the color algorithm processes the partition image, the obtained foreground image replaces the partition image and performs display.

Optionally, the acquiring a face region in the target image includes: detecting and acquiring a face image in the target image; and using the circular region including the face image as the face region; Whether the partition image on the target image belongs to the face region includes: determining a distance between the partition image and a center of the face region; and determining, when the distance is less than or equal to a radius of the face region, determining The partition image belongs to the face area; when the distance is greater than a radius of the face area, it is determined that the partition image does not belong to the face area.

Optionally, when the distance is greater than a radius of the face region, determining that the partition image does not belong to the face region comprises: when the distance is greater than a radius of the face region, and is smaller than And determining that the partition image belongs to a transition region, wherein the preset radius is greater than or equal to a radius of the face region; and when the distance is greater than the preset radius, determining that the partition image belongs to a background area; when the partition image does not belong to the face area, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, including: when the partition image belongs to the In the transition region, the partition image is replaced by a mixed image of (1 - v) times the foreground image and v times the blurred image, wherein v = (dis - r) / (Rr), wherein Dis is the distance, r is the radius of the face region, and R is the predetermined radius, wherein the foreground image is an image obtained by processing the partition image by using a microdermabrasion algorithm and/or a toning algorithm. When the partition image At the time of the background region, the blurred image to replace the image partitioning.

Optionally, the blurring algorithm is used to blur the partition image, including: performing a downsampling process on the partition image; and using a blur algorithm to blur the downsampled processed partition image; The partition image is subjected to upsampling processing.

In another aspect, an apparatus for implementing a filter is provided, comprising:

An acquiring module, configured to acquire a face area in the target image, where the face area is an area including a face image;

a determining module, configured to determine whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, where N is an integer greater than one;

And a fuzzy module, configured to: when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, and is displayed.

Optionally, the acquiring module is further configured to: alternately use a face detection algorithm and a face tracking algorithm to acquire a face region of the target image in the video.

Optionally, the device further includes: a beautification module, configured to obtain a foreground image after the partition image is processed by using a microdermabrasion algorithm and/or a toning algorithm when the partition image belongs to the face region Replace the partition image and display it.

Optionally, the obtaining module is further configured to: detect a face image in the target image; use a circular area that includes the face image as the face area; and the determining module is further configured to: Determining a distance between the partition image and a center of the face region; when the distance is less than or equal to a radius of the face region, determining that the partition image belongs to the face region; when the distance is greater than the Determining that the partition image does not belong to the face region when the radius of the face region is determined; the determining module is further configured to: when the distance is greater than a radius of the face region and less than or equal to a preset radius, determine The partition image belongs to a transition area, wherein the preset radius is greater than a radius of the face area; when the distance is greater than the preset radius, determining that the partition image belongs to a background area; For replacing the partition image with a mixed image of (1-v) times the foreground image and v times the blurred image when the partition image belongs to the transition region, where v=(dis -r)/(R- r), wherein dis is the distance, r is a radius of the face region, and R is the predetermined radius, wherein the foreground image is processed by using a microdermabrasion algorithm and/or a toning algorithm An image obtained after the image; when the partition image belongs to the background region, the partition image is replaced with the blurred image.

One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

The method and device provided by the embodiment of the present application first acquire a face region in a target image, and then determine whether each partition image segmented on the target image belongs to the face region, and when the partition image does not belong to the In the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed, thereby realizing a filter with background blurring function, which not only enriches the filter The function also makes the face in the target image more prominent, and increases the confidentiality of the environment by blurring the background, thereby satisfying more needs of the user.

The above description is only an overview of the technical solutions of the present invention, and the above-described and other objects, features and advantages of the present invention can be more clearly understood. Specific embodiments of the invention are set forth below.

DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description of the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description It is a certain embodiment of the present invention, and other drawings can be obtained from those skilled in the art without any creative work.

1 is a flowchart of a method for implementing a filter according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of an apparatus for implementing a filter according to an embodiment of the present invention.

detailed description

The embodiment of the present application provides a method and an apparatus for implementing a filter, which is used to solve the technical problem that the video filter in the prior art has a single function and cannot meet more demands of users. A rich filter function has been implemented to meet the technical effects of users' needs for highlighting faces and increasing environmental confidentiality.

The general technical idea of the technical solution in the embodiment of the present application is as follows:

Obtaining a face region in the target image, the face region being an area including a face image; determining whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partitions The image, N is an integer greater than 1; when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed.

In the above method, the face region in the target image is first acquired, and then it is determined whether each of the segment images segmented on the target image belongs to the face region, and when the segment image does not belong to the face region, After the fuzzy algorithm blurs the partition image, the obtained blurred image replaces the partition image and performs display, thereby realizing a filter with background blur function, which not only enriches the filter function, but also makes the target The faces in the image are more prominent, and the privacy of the environment is increased by blurring the background, thereby satisfying more needs of users.

The technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. It is a partial embodiment of the invention, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Embodiment 1

This embodiment provides a method for implementing a filter. As shown in FIG. 1, the method includes:

Step S101, acquiring a face area in the target image, where the face area is an area including a face image;

Step S102, determining whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, where N is an integer greater than one;

Step S103: When the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed.

It should be noted that the target image may be a single picture, or may be a live video or a picture stored in the video, which is not limited herein.

When the target image is a single picture, the method can implement background blurring on the picture; when the target image is a picture in the video, the implementation is implemented by using each frame picture or part of the picture in the video. The method provided by the example can achieve background blurring of the video.

In a specific implementation process, the method can be applied to a terminal such as a smart phone, a tablet computer, or a desktop computer, and can also be applied to a server, and is not limited herein.

The specific implementation steps of the method provided in this embodiment are described in detail below with reference to FIG.

First, step S101 is performed to acquire a face region in the target image, the face region being an area including a face image.

In the specific implementation process, the location of the face in the target image and the size of the region in the target image are obtained, which can be implemented by various existing face detection algorithms.

In the embodiment of the present application, when the target image is an image in a video, the acquiring a face region in the target image includes:

The face detection algorithm and the face tracking algorithm are alternately used to acquire a face region of the target image in the video.

Specifically, the alternate use of the face detection algorithm and the face tracking algorithm are particularly suitable for the target image in the live video to improve the efficiency of acquiring the face region of the plurality of images in the video in real time.

In a specific implementation process, in order to facilitate the subsequent determination of whether the partition image belongs to the face region, the capturing the face region in the target image may include: detecting and acquiring a face image in the target image; A circular area of the face image is described as the face area.

Of course, in a specific implementation process, a square area or an elliptical area including the face image may be used as the face area, which is not limited herein.

Then, step S102 is executed to determine whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, and N is an integer greater than 1.

In the embodiment of the present application, the partition image may be N partition images that are divided in advance by a small triangle, a small square, or a small diamond. The larger the number of N, the better it is to determine whether the partition image belongs to the The face area may also be a pixel point, where N is the number of pixel points, which is not limited herein.

In the embodiment of the present application, there are many methods for determining whether the partition image belongs to the face region, and two examples are as follows:

The first type is judged according to the coordinates of the partition image.

That is, the coordinates of the partition image and the coordinate range of the face region are first acquired; and it is determined whether the coordinates of the partition image belong to the coordinate range of the face region; when the coordinates of the partition image belong to the face When the coordinate range of the region is determined, the partition image is determined to belong to the face region; when the coordinates of the partition image do not belong to the coordinate range of the face region, it is determined that the partition image does not belong to the face region.

Secondly, the face area is set as a regular figure, and is determined according to the distance between the partition image and the center of the face area.

Specifically, in order to facilitate determining whether the partition image belongs to the face region, the face region may be set as a circular region. Correspondingly, determining whether the partition image on the target image belongs to the face region comprises: determining a distance between the partition image and a center of the face region; and when the distance is less than or equal to the face When the radius of the region is determined, the partition image is determined to belong to the face region; when the distance is greater than a radius of the face region, it is determined that the partition image does not belong to the face region.

For example, the location information of the face in the video image is obtained. Assuming that the face region is set to a circle, the coordinates of the center point A of the face region are obtained as A(x, y), and the radius is r. The calculation formula of the distance di s of the center point D(i,j) of the partition image and the point A(x,y) is as follows:

When dis is less than or equal to r, it is determined that the partition image belongs to the face region; when dis is greater than r, it is determined that the partition image does not belong to the face region.

Then, in step S103, when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed.

In the embodiment of the present application, a blur algorithm may be used to blur the target image as a whole, and then a blurred image corresponding to the partition image may be obtained according to the position of the partition image. Of course, each of the partition images may be blurred by using a blurring algorithm to obtain a blurred image corresponding to each of the partition images, which is not limited herein.

In the embodiment of the present application, the blurring algorithm is used to blur the partition image, including:

Performing downsampling processing on the partition image;

The partition image after the downsampling process is blurred by using a fuzzy algorithm;

Performing upsampling processing on the blurred partition image.

Specifically, in order to achieve the background blur effect, it is first necessary to obtain a blurred video image. Many fuzzy algorithms can implement blurring functions. For example, the fuzzy algorithm can be Gaussian blur, mean filtering, median filtering, and the like. Taking the median filtering as the background blur algorithm as an example, the larger the blur radius of the median filter, the more blurred the image, but the larger the blur radius, the larger the computation amount. Therefore, in order to improve the running efficiency of the program, you can first The target image is subjected to downsampling processing, and then the target image is blurred by median filtering, and then the target image is upsampled, and since the blurred image is obtained by acquiring the blurred image, the image is downsampled and uploaded. Sampling does not affect the final result of the image.

In the embodiment of the present application, after the determining whether the partition image on the target image belongs to the face region, the method further includes:

When the partition image belongs to the face region, after the partition image is processed by using a dermabrasion algorithm and/or a toning algorithm, the obtained foreground image replaces the partition image and is displayed.

In the embodiment of the present application, the target image may be processed in advance by using a microdermabrasion algorithm and/or a toning algorithm, and then the foreground image corresponding to the partition image may be obtained according to the position of the partition image. Of course, each of the partition images may be processed by using a dermabrasion algorithm and/or a grading algorithm to obtain a foreground image corresponding to each of the partition images, which is not limited herein.

Specifically, the present application not only considers the blurring of the background, but also considers the beautification of the face area.

Among them, the main function of the microdermabrasion algorithm is to denoise, that is, to remove or blur the noise in the image, so that the user can obtain a better visual experience. There are many kinds of dermabrasion algorithms, such as Gaussian filtering, bilateral filtering, local mean square error, surface ambiguity, mean blur, Gaussian blur and median filtering. For better, the dermabrasion algorithm can be used as a combination of bilateral filtering and Gaussian filtering. .

Further, before performing the dermabrasion algorithm, the skin color can be detected first, and only the noise in the skin color is processed, and the hair, eyes and the like are not treated, so that the skin dermabrasion effect is more natural.

Among them, there are many kinds of color grading algorithms, and the effects of different color grading algorithms are different. The adjustment objects of simple color grading algorithm are: contrast, saturation, brightness, exposure, sharpness, etc.; adjustment of complex color grading algorithm Objects such as: soft light, elegant, retro, beautiful, sketch, rape, etc.

In the embodiment of the present application, in a case where the partition area does not belong to the face area, a transitional area that is attached to the attachment of the face area and a background area that is far from the face area may be further set, where The size of the transition area can be adjusted according to the actual situation.

Taking the face area as a circular area as an example, when the distance is greater than a radius of the face area, determining that the partition image does not belong to the face area includes: when the distance is greater than When the radius of the face region is less than or equal to the preset radius, it is determined that the partition image belongs to the transition region, wherein the preset radius is greater than or equal to the radius of the face region; when the distance is greater than the preset At the radius, it is determined that the partition image belongs to the background area.

Correspondingly, when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, including: when the partition image belongs to the In the transition region, the partition image is replaced by a mixed image of (1 - v) times the foreground image and v times the blurred image, wherein v = (dis - r) / (Rr), wherein Dis is the distance, r is the radius of the face region, and R is the predetermined radius, wherein the foreground image is an image obtained by processing the partition image by using a microdermabrasion algorithm and/or a toning algorithm. When the partition image belongs to the background area, the partition image is replaced with the blurred image.

Specifically, the partitioned area in the face area is displayed as a clear dermabrasion and/or the toned foreground image; the partitioned area in the background area is displayed as blurred by a fuzzy algorithm. The blurred image; a transition region of the transition between the face region and the background region is displayed as a mixture of the foreground image and the blurred image.

For example, if the face area is a circle with a point A as a center and r is a radius, and R is the predetermined radius, the background area is centered on point A, and R is a radius. A portion other than the circle, the transition region being a ring region centered on the point A, the ring having a thickness of Rr. Assuming that the coordinates of the center point D of a certain partition image on the image are (i, j), then the specific algorithm of the partition image E is as follows:

Where dis is the distance between point D and point A, F is the foreground image of the partition image, B is the blurred image of the partition image, and v is the proportion of the foreground image F mixed with the blurred image B, v The range is [0, 1]. When the distance between the current pixel point D and the center of the face region is less than or equal to r, the foreground image F is displayed; when the distance between the current pixel point D and the center of the face region is greater than r and less than or equal to R, the foreground image F is displayed. Mixed with the blurred image B, the mixing coefficient is v; when the distance between the current pixel point D and the center of the face region is greater than R, the blurred image B is displayed.

In a specific implementation process, if there are multiple faces in the target image, the same processing as described above may be performed for each face region.

If a human face is not detected in the target image, a function that does not require background blurring may be set to directly display a foreground image of the target image, that is, after the target image is subjected to microdermabrasion and/or color adjustment. The display effect.

Specifically, the method provided by the embodiment implements the microdermabrasion and the background blur on the basis of the color adjustment, thereby realizing a filter with a background blur function, which not only enriches the filter function, but also makes the The face in the target image is more prominent and beautified, and the privacy of the environment is increased by blurring the background, thereby satisfying more needs of the user.

Based on the same inventive concept, the present application also provides an apparatus corresponding to the implementation method of the filter in the first embodiment. For details, see Embodiment 2.

Embodiment 2

The embodiment provides a filter implementation device. As shown in FIG. 2, the device includes:

The obtaining module 201 is configured to acquire a face area in the target image, where the face area is an area including a face image;

The determining module 202 is configured to determine whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, where N is an integer greater than one;

The blurring module 203 is configured to: when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, and is displayed.

In a specific implementation process, the device may be a terminal such as a smart phone, a tablet computer, or a desktop computer, or may be a server, and is not limited herein.

In the embodiment of the present application, the obtaining module 201 is further configured to:

In the embodiment of the present application, the device further includes:

And a beautification module, configured to replace the partition image with the foreground image after the partition image is processed by the dermabrasion algorithm and/or the color grading algorithm, and display the partition image after the partition image belongs to the face region.

In the embodiment of the present application, the acquiring module 201 is further configured to: detect and acquire a face image in the target image; and use a circular area including the face image as the face region;

The determining module 202 is further configured to: determine a distance between the partition image and a center of the face region; and when the distance is less than or equal to a radius of the face region, determine that the partition image belongs to the face a region; when the distance is greater than a radius of the face region, determining that the partition image does not belong to the face region;

The determining module 202 is further configured to: when the distance is greater than a radius of the face region and less than or equal to a preset radius, determine that the partition image belongs to a transition region, where the preset radius is greater than the person a radius of the face region; when the distance is greater than the preset radius, determining that the partition image belongs to a background region;

The blurring module 203 is further configured to replace the partition image with a mixed image of (1-v) times the foreground image and v times the blurred image mixed when the partition image belongs to the transition region, Where v=(dis-r)/(Rr), where dis is the distance, r is the radius of the face region, and R is the predetermined radius, wherein the foreground image is a microdermabrasion An image obtained after processing the partition image by an algorithm and/or a toning algorithm; when the partition image belongs to the background region, replacing the partition image with the blurred image.

The device described in the second embodiment of the present invention is a device for implementing the method for implementing the filter according to the first embodiment of the present invention. Therefore, those skilled in the art can understand the device according to the method described in the first embodiment of the present invention. The specific structure and deformation are not described here. The apparatus used in the method of the first embodiment of the present invention is within the scope of the present invention.

The technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device. The instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

While the preferred embodiment of the invention has been described, it will be understood that Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and the modifications and

It is apparent that those skilled in the art can make various modifications and variations to the embodiments of the invention without departing from the spirit and scope of the embodiments of the invention. Thus, it is intended that the present invention cover the modifications and modifications of the embodiments of the invention.

Claims

A method for implementing a filter, comprising:

Acquiring a face area in the target image, the face area being an area including a face image;

Determining whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, and N is an integer greater than 1;

When the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image and is displayed.
The method according to claim 1, wherein when the target image is an image in a video, the acquiring a face region in the target image comprises:

The face detection algorithm and the face tracking algorithm are alternately used to acquire a face region of the target image in the video.
The method of claim 1, further comprising: after determining whether the partition image on the target image belongs to the face region,

When the partition image belongs to the face region, after the partition image is processed by using a dermabrasion algorithm and/or a toning algorithm, the obtained foreground image replaces the partition image and is displayed.
The method of claim 1 wherein

The acquiring a face region in the target image includes: detecting and acquiring a face image in the target image; and using the circular region including the face image as the face region;

Determining whether the partition image on the target image belongs to the face region comprises: determining a distance between the partition image and a center of the face region; and when the distance is less than or equal to a radius of the face region And determining that the partition image belongs to the face region; when the distance is greater than a radius of the face region, determining that the partition image does not belong to the face region.
The method of claim 4 wherein:

Determining that the partition image does not belong to the face region when the distance is greater than a radius of the face region, including: when the distance is greater than a radius of the face region, and less than or equal to a preset radius Determining that the partition image belongs to a transition region, wherein the preset radius is greater than or equal to a radius of the face region; and when the distance is greater than the preset radius, determining that the partition image belongs to a background region;

When the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, including: when the partition image belongs to the transition region And replacing the partition image with a mixed image of (1 - v) times the foreground image and v times the blurred image, wherein v = (dis - r) / (Rr), wherein dis is a distance, where r is the radius of the face region, and R is the predetermined radius, wherein the foreground image is an image obtained by processing the partition image by using a microdermabrasion algorithm and/or a toning algorithm; When the partition image belongs to the background area, the partition image is replaced with the blurred image.
The method according to claim 1, wherein the blurring the partition image by using a blur algorithm comprises:

Performing downsampling processing on the partition image;

The partition image after the downsampling process is blurred by using a fuzzy algorithm;

Performing upsampling processing on the blurred partition image.
A device for implementing a filter, comprising:

An acquiring module, configured to acquire a face area in the target image, where the face area is an area including a face image;

a determining module, configured to determine whether the partition image on the target image belongs to the face region, wherein the target image is divided into N partition images, where N is an integer greater than one;

And a fuzzy module, configured to: when the partition image does not belong to the face region, after the partition image is blurred by using a blur algorithm, the obtained blurred image replaces the partition image, and is displayed.
The device according to claim 7, wherein the obtaining module is further configured to:

The face detection algorithm and the face tracking algorithm are alternately used to acquire a face region of the target image in the video.
The device of claim 7 further comprising:

And a beautification module, configured to replace the partition image with the foreground image after the partition image is processed by the dermabrasion algorithm and/or the color grading algorithm, and display the partition image after the partition image belongs to the face region.
The method of claim 1 wherein

The acquiring module is further configured to: detect and acquire a face image in the target image; and use a circular area including the face image as the face area;

The determining module is further configured to: determine a distance between the partition image and a center of the face region; and when the distance is less than or equal to a radius of the face region, determine that the partition image belongs to the face region When the distance is greater than a radius of the face region, determining that the partition image does not belong to the face region;

The determining module is further configured to: when the distance is greater than a radius of the face region and less than or equal to a preset radius, determine that the partition image belongs to a transition region, where the preset radius is greater than the face a radius of the region; when the distance is greater than the preset radius, determining that the partition image belongs to a background region;

The blurring module is further configured to replace the partition image with a mixed image of (1-v) times the foreground image and v times the blurred image when the partition image belongs to the transition region, wherein , v=(dis-r)/(Rr), where dis is the distance, r is the radius of the face region, and R is the predetermined radius, wherein the foreground image is a microdermabrasion algorithm And/or an image obtained by the toning algorithm after processing the partition image; when the partition image belongs to the background area, replacing the partition image with the blurred image.