WO2022193466A1

WO2022193466A1 - Image processing method and apparatus, and electronic device and storage medium

Info

Publication number: WO2022193466A1
Application number: PCT/CN2021/102171
Authority: WO
Inventors: 苏柳
Original assignee: 北京市商汤科技开发有限公司
Priority date: 2021-03-19
Filing date: 2021-06-24
Publication date: 2022-09-22
Also published as: CN112767288A; CN112767288B

Abstract

The present disclosure relates to an image processing method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring a key point of a human body object in an image to be processed and a target region of the human body object, wherein the target region comprises a neck region and/or a head region; according to the positions of at least some of the pixel points in the target region and the position of the key point in the target region, respectively adjusting a plurality of pixel points in the target region, so as to determine an adjusted target region; and generating a target image according to said image and the adjusted target region.

Description

Image processing method and device, electronic device and storage medium

This application claims the priority of the Chinese patent application with the application number 202110297088.8 and the application title "Image Processing Method and Device, Electronic Device and Storage Medium" filed with the China Patent Office on March 19, 2021, the entire contents of which are incorporated by reference in this application.

technical field

The present disclosure relates to the field of computer vision, and in particular, to an image processing method and apparatus, an electronic device and a storage medium.

Background technique

With the development of computer vision technology, beautifying people in images has become an increasingly common operation. However, the function of beautification is often limited to the modification of facial makeup, or the slimming of legs and waist. How to beautify the human body in a comprehensive and natural way has become an urgent problem to be solved.

SUMMARY OF THE INVENTION

The present disclosure proposes an image processing scheme.

According to an aspect of the present disclosure, an image processing method is provided, comprising:

Acquiring key points of a human object in the image to be processed and a target area of the human object, wherein the target area includes a neck area and/or a head area; according to the positions of at least some of the pixels in the target area, and The positions of the key points in the target area are adjusted respectively for a plurality of pixel points in the target area to determine the adjusted target area; according to the to-be-processed image and the adjusted target area, generate target image.

In a possible implementation manner, according to the positions of at least part of the pixel points in the target area and the positions of the key points in the target area, the multiple pixel points in the target area are respectively performed Adjusting, determining the adjusted target area, including: dividing the to-be-processed image into a plurality of image grids; using pixels located on any of the image grids in the target area as target pixels; The position of the target pixel point and the position of the key point in the target area are adjusted, and a plurality of pixel points in the target area are adjusted to determine the adjusted target area.

In a possible implementation manner, the adjustment is performed on a plurality of pixels in the target area according to the position of the target pixel and the position of the key point in the target area, and the adjusted pixel is determined. The target area includes: determining the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area; adjusting the target area according to the first adjustment distance Adjust a plurality of pixels in the target area to determine the adjusted target area; or, according to the first adjustment distance, determine the second adjustment distance of the pixels located in the image grid in the target area; The second adjustment distance adjusts a plurality of pixels in the target area to determine the adjusted target area; or, according to the first adjustment distance or the second adjustment distance, adjusts the pixels in the target area Adjust multiple pixels to determine the adjusted target area.

In a possible implementation manner, the determining the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area includes: according to the target pixel point The relevant key points of the neck in the area are used to determine the first target position in the human object; according to the actual distance between the target pixel point and the first target position, the adjustment ratio of the target pixel point is determined; According to the adjustment ratio of the target pixel point and the preset distance, the first adjustment distance of the target pixel point is obtained.

In a possible implementation manner, the determining, according to the first adjustment distance, the second adjustment distance of the pixel points located in the image grid in the target area includes: adjusting the target pixel point The first adjustment distance is interpolated to obtain the second adjustment distance of the pixel point in the image grid where the target pixel point is located.

In a possible implementation manner, the adjustment is performed on a plurality of pixels in the target area according to the position of the target pixel and the position of the key point in the target area, and the adjusted pixel is determined. The target area includes: determining the second target position in the human object according to the outline key points in the key points of the human object; according to the position of the target pixel point and the key point in the target area position, respectively adjusting a plurality of pixel points in the target area to the second target position to obtain an adjusted target area.

In a possible implementation manner, the determining the second target position in the human object according to the contour key points in the key points of the human object includes: adding the left shoulder included in the contour key points The center position of the area formed by the key point, the right shoulder key point, the left underarm key point, and the right underarm key point is taken as the second target position.

In a possible implementation manner, the acquiring the key points of the human object in the image to be processed and the target area of the human object includes: performing limb key point recognition and/or outline key point recognition on the image to be processed, and obtaining the object to be processed. Process the key points of the human object in the image, wherein the key points of the human object include limb key points and/or outline key points; according to the key points of the human object, the human object in the to-be-processed image is subjected to a region analysis. Divide to obtain a plurality of human body regions; extract a neck region and/or a head region from the plurality of human body regions to obtain the target region.

In a possible implementation manner, the generating the target image according to the to-be-processed image and the adjusted target area includes: rendering the material of the target area in the to-be-processed image to the adjusted target area. The location of the target area to generate the target image.

According to an aspect of the present disclosure, an image processing apparatus is provided, including:

an acquisition module, used to acquire key points of the human object in the image to be processed and a target area of the human object, wherein the target area includes a neck area and/or a head area; an adjustment module, used for according to the target area The positions of at least part of the pixel points in the area, and the positions of the key points in the target area, respectively adjust a plurality of pixel points in the target area to determine the adjusted target area; the target image generation module, using generating a target image according to the to-be-processed image and the adjusted target area.

In a possible implementation manner, the adjustment module is configured to: divide the image to be processed into a plurality of image grids; use a pixel point located on any of the image grids in the target area as a target pixel point; according to the position of the target pixel point and the position of the key point in the target area, adjust a plurality of pixel points in the target area to determine the adjusted target area.

In a possible implementation manner, the adjustment module is further configured to: determine the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area; Adjust a plurality of pixels in the target area according to the first adjustment distance to determine the adjusted target area; or, according to the first adjustment distance, determine that the image grid in the target area is located in the image grid the second adjustment distance of the pixels in the target area; adjust a plurality of pixels in the target area according to the second adjustment distance to determine the adjusted target area; or, according to the first adjustment distance or the The second adjustment distance is to adjust a plurality of pixel points in the target area to determine the adjusted target area.

In a possible implementation manner, the adjustment module is further configured to: determine the first target position in the human object according to the relevant key points of the neck in the target area; According to the actual distance between the first target positions, the adjustment ratio of the target pixel is determined; according to the adjustment ratio of the target pixel and the preset distance, the first adjustment distance of the target pixel is obtained.

In a possible implementation manner, the adjustment module is further configured to: perform interpolation processing on the first adjustment distance of the target pixel to obtain the second adjustment distance of the pixel in the image grid where the target pixel is located. Adjust the distance.

In a possible implementation manner, the adjustment module is configured to: determine the second target position in the human object according to the contour key points in the key points of the human object; according to the position of the target pixel point According to the position of the key point in the target area, a plurality of pixel points in the target area are respectively adjusted to the second target position to obtain an adjusted target area.

In a possible implementation manner, the adjustment module is further configured to: combine the left shoulder key point, the right shoulder key point, the left underarm key point and the right underarm key point included in the outline key points into the area formed by the key point The center position of , as the second target position.

In a possible implementation manner, the acquisition module is configured to: perform body key point recognition and/or outline key point recognition on the image to be processed, and obtain the key points of the human object in the image to be processed, wherein the The key points include limb key points and/or contour key points; according to the key points of the human body object, the human body objects in the to-be-processed image are divided into regions to obtain multiple human body regions; from the multiple human body regions The neck region and/or head region are extracted to obtain the target region.

In a possible implementation manner, the target image generation module is configured to: render the material of the target area in the to-be-processed image to the adjusted position of the target area to generate the target image.

According to an aspect of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to: execute the above image processing method.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions implementing the above-mentioned image processing method when executed by a processor.

According to an aspect of the present disclosure, a computer program product is provided, comprising computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in an electronic device When running in the processor, the processor in the electronic device executes the image processing method described above.

In the embodiment of the present disclosure, the key points of the human object in the image to be processed and the target area of the human object are acquired, and the position of at least a part of the pixel points in the target area and the positions of the key points in the target area are adjusted to the target area. A plurality of pixel points are adjusted respectively to determine an adjusted target area, so as to generate a target image based on the adjusted target area and the image to be processed. Through the above process, on the one hand, the target area such as the head and neck of the human object in the target image can be beautified, so as to improve the comprehensiveness and naturalness of the human body beautification; It can reduce the amount of data processed in the adjustment process and improve the efficiency and effect of beautification.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Description of drawings

The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the technical solutions of the present disclosure.

FIG. 1 shows a flowchart of an image processing method according to an embodiment of the present disclosure.

FIG. 2 shows a schematic diagram of a limb key point according to an embodiment of the present disclosure.

FIG. 3 shows a schematic diagram of contour key points according to an embodiment of the present disclosure.

FIG. 4 shows a schematic diagram of region division of a human object according to an embodiment of the present disclosure.

FIG. 5 shows a flowchart of an image processing method according to an embodiment of the present disclosure.

FIG. 6 shows a flowchart of an image processing method according to an embodiment of the present disclosure.

FIG. 7 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure.

FIG. 8 shows a schematic diagram of an application example according to the present disclosure.

FIG. 9 shows a schematic diagram of an application example according to the present disclosure.

FIG. 10 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

FIG. 11 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures denote elements that have the same or similar functions. While various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, and A and B exist independently B these three cases. In addition, the term "at least one" herein refers to any combination of any one of the plurality or at least two of the plurality, for example, including at least one of A, B, and C, and may mean including from A, B, and C. Any one or more elements selected from the set of B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are set forth in the following detailed description. It will be understood by those skilled in the art that the present disclosure may be practiced without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art have not been described in detail so as not to obscure the subject matter of the present disclosure.

1 shows a flowchart of an image processing method according to an embodiment of the present disclosure. The method can be applied to an image processing apparatus or an image processing system, and the image processing apparatus can be a terminal device, a server, or other processing devices. Wherein, the terminal device may be user equipment (User Equipment, UE), mobile device, user terminal, terminal, cellular phone, cordless phone, Personal Digital Assistant (PDA), handheld device, computing device, in-vehicle device, available wearable devices, etc. In one example, the image processing method may be applied to a cloud server or a local server, and the cloud server may be a public cloud server or a private cloud server, which can be flexibly selected according to actual conditions.

In some possible implementations, the image processing method can also be implemented by the processor calling computer-readable instructions stored in the memory.

As shown in FIG. 1, in a possible implementation manner, the image processing method may include:

Step S11: Acquire key points of the human object in the image to be processed and a target area of the human object, where the target area includes a neck area and/or a head area.

The image to be processed may be any image including a human body object, and the number of human body objects included in the to-be-processed image is not limited in the embodiments of the present disclosure, and may include one human body object or multiple human body objects. Human objects can be the same object or different objects.

The number of images to be processed is not limited in the embodiments of the present disclosure, and may be one or multiple. In the case of multiple images to be processed, the image processing method proposed in the embodiments of the present disclosure can simultaneously The image to be processed is processed.

The key points of the human object in the image to be processed, and the number and types of key points included in the key points are not limited in the embodiments of the present disclosure. In a possible implementation, the key points of the human object may include limb key points and/or contour key points.

The limb key points may be key points used for locating various parts of the human body, and the implementation manner thereof may be flexibly selected according to the actual situation, and is not limited to the following disclosed embodiments. FIG. 2 shows a schematic diagram of a limb key point according to an embodiment of the present disclosure. As shown in the figure, in a possible implementation manner, the limb key point may include a head key point 0, a neck key point 1, and a left shoulder key point Point 2, Right Shoulder Key Point 3, Left Elbow Key Point 4, Right Elbow Key Point 5, Left Hand Key Point 6, Right Key Point 7, Left Hip Key Point 8, Right Hip Key Point 9, Left Knee Key Point 10, Right One or more of the key points such as the knee key point 11 , the left foot key point 12 , and the right foot key point 13 .

The contour key point may be a key point used for locating each part of the edge of the human body contour, and the implementation manner thereof may be flexibly selected according to the actual situation, and is not limited to the following disclosed embodiments. 3 shows a schematic diagram of a contour key point according to an embodiment of the present disclosure. As shown in the figure, in a possible implementation manner, the contour key point may include at least one of 59 key points distributed along the body contour or multiple points.

The target area of the human object may be one or more areas in the image to be processed that have processing requirements, and the implementation method may be flexibly selected according to the actual situation. In a possible implementation, the target area may only include the head area or the neck area; in a possible implementation, the target area may include both the head area and the neck area. The division manner of the head area and the neck area can be flexibly selected according to the actual situation, and is not limited to the following disclosed embodiments. In a possible implementation manner, the area between the head key point and the neck key point in the body key points may be divided into the head area, and the body key points located above the left shoulder key point and the right shoulder key point , and the area below the neck key point is divided into the neck area; in some possible implementations, it can also be divided into the head area and the neck area according to the assistance of the outline key points, for example, according to the left neck key in Figure 3 The area between point 0 and the right neck key point 58 is divided into neck area and so on. In a possible implementation manner, the target area may not consider key points, but may be divided by other methods, such as directly performing area range recognition on the target area in the image to be processed.

The implementation manner of step S11 can be flexibly selected according to the actual situation, which is not limited in this embodiment of the present disclosure. In some possible implementations, the key points of the human object and the target area of the human object can be acquired at the same time; in some possible implementations, the key points of the human object can also be acquired first, and the target area is determined according to the key points; In some possible implementations, the target area can also be extracted from the human object first, and then the key points of the target area are identified to obtain the key points of the human object located in the target area. Some possible implementation manners of step S11 are detailed in the following disclosed embodiments, which are not expanded here.

Step S12, according to the positions of at least part of the pixel points in the target area and the positions of key points in the target area, respectively adjust a plurality of pixel points in the target area to determine the adjusted target area.

Wherein, at least some of the pixels in the target area may be one or more pixels in the target area, and the at least some of the pixels may be used for subsequent adjustment of the entire target area. The implementation of at least some of the pixels can be flexibly determined. In some possible implementations, at least some of the pixels can be sampling points obtained by sampling the target area, or on the division boundary obtained by further dividing the target area. point and so on. How to obtain at least part of the pixel points, the implementation of which can be found in the following disclosed embodiments, which will not be expanded here.

The key points in the target area may be the key points located within the target area among the multiple key points obtained in step S11, such as the head key points or neck key points in the limb key points, and the outline key points. The key points of the left neck or the right neck can be flexibly selected according to the actual situation.

According to the positions of at least some of the pixel points and the key points in the target area, a plurality of pixel points in the target area may be adjusted respectively to obtain the adjusted target area. The number and type of pixels included in the plurality of pixels in the target area are not limited in the embodiments of the present disclosure. In a possible implementation, the multiple pixels may be each pixel in the target area; in a possible implementation, the multiple pixels may include at least some of the pixels mentioned in the above disclosed embodiments point; in some possible implementations, the plurality of pixel points may also include other pixel points other than at least some of the pixel points in the target area, and the like.

How to adjust multiple pixels in the target area according to the positions of at least some of the pixels and key points in the target area, and the adjustment method can be flexibly determined according to the actual situation, for example, according to at least some of the pixels and the target area. The position of the key point determines the adjustment direction and/or adjustment distance of multiple pixel points, etc., so as to realize operations such as stretching or deformation of the target area. For detailed adjustment methods, refer to the following disclosed embodiments, which will not be described here.

Since the positions of multiple pixels in the target area may change during the adjustment process, in a possible implementation manner, the adjusted target area may deform or move relative to the target area of the image to be processed. Compared with the target area in the image to be processed, the adjusted target area has a better visual effect.

Step S13, generating a target image according to the image to be processed and the adjusted target area.

The target image may be an image with better visual effect obtained after processing. The method of generating the target image based on the image to be processed and the adjusted target area can be flexibly selected according to the actual situation, such as rendering the texture of the target area in the image to be processed to the position of the adjusted target area, or The target area is fused or superimposed with the image to be processed. For some possible implementation manners of step S13, please refer to the subsequent disclosed embodiments, which will not be expanded here.

In a possible implementation manner, step S11 may include:

Perform body key point recognition and/or outline key point recognition on the image to be processed to obtain the key points of the human object in the image to be processed;

According to the key points of the human object, the human object in the image to be processed is divided into regions to obtain multiple human regions;

The neck region and/or head region are extracted from multiple body regions to obtain the target region.

The implementation of the limb key points and the outline key points can be found in the above disclosed embodiments. The manner of performing limb key point identification and/or contour key point identification is not limited in the embodiments of the present disclosure. In a possible implementation, it can be implemented through a neural network. For example, the images to be processed can be input into the limb key point recognition neural network and the contour key point recognition neural network respectively, so as to obtain the limb key points and contour key points respectively. Process the position in the image; in a possible implementation, the image to be processed can also be directly input into the key point recognition neural network to obtain the limb key points and contour key points output by the key point recognition neural network in the image to be processed location, etc.

The manner of dividing the area of the human object in the image to be processed can be flexibly determined according to the actual situation. For some possible implementation manners, reference may be made to the manner of dividing the head area and the neck area in the above disclosed embodiments. 4 shows a schematic diagram of region division of a human object according to an embodiment of the present disclosure (in order to protect the object in the image, part of the face in the figure is subjected to mosaic processing, and the same is true for subsequent images), as shown in the figure In a possible implementation manner, a plurality of limb key points and outline key points of the human object in the image to be processed can be obtained by identifying them as the key points of the human object, and some or all of the key points are formed by connecting them. Rectangular or other shaped regions to obtain multiple body regions of a human subject.

The method of extracting the neck region and/or head region from multiple human body regions can be flexibly determined according to the actual situation. As shown in FIG. 4, in some possible implementations, the head region can be extracted from the multiple human body regions. The rectangular area formed by connecting the key points and the neck key points is used as the head area, and the rectangle formed by connecting the neck key points, left shoulder key points, right shoulder key points, left armpit key points, and right armpit key points, etc. area as the neck area.

Through the embodiments of the present disclosure, key point recognition can be used to determine the position of each key point in the human body on the one hand, and provide an adjustment basis for the subsequent adjustment of the target area; The target area is easily determined from the image to be processed and the overall efficiency of image processing is improved.

5 shows a flowchart of an image processing method according to an embodiment of the present disclosure. As shown in the figure, in a possible implementation, step S12 may include:

Step S121: Divide the image to be processed into a plurality of image grids.

Wherein, dividing the image to be processed into a plurality of image grids may be the image grid division of the entire image to be processed, or the image grid division of a part of the image to be processed (such as the target area, etc.).

The shape of the image grid can also be flexibly determined according to the actual situation, and can be a triangle, a rectangle, or other polygons, etc., and in some possible implementations, it can also be divided into a fan shape or a circle, and the like.

The grid division method can be flexibly determined according to the actual situation. In a possible implementation method, the to-be-processed image or target area can be divided into a preset number of image grids, and the preset number of values can be determined according to the actual situation. Flexible settings, such as certain numerical values in the range of 10 to 90,000, etc., are not limited in the embodiments of the present disclosure. In one example, the image to be processed may be evenly divided into a 112×112 rectangular image grid.

In some possible implementations, the image grid can also be divided by pixel sampling. For example, one or more sampling points can be extracted from the image to be processed by averaging or random sampling. As the vertices of the image grid, the adjacent sampling points in the one or more sampling points are connected to form any shape mentioned in the above disclosed embodiments, and then a plurality of image grids can be obtained.

In step S122, a pixel point located on any image grid in the target area is used as a target pixel point.

Based on the divided image grid, at least part of the pixels from the target area may be determined as target pixels. In a possible implementation manner, vertices on each image grid and/or points located on the edge of each image grid included in the target area may be used as target pixel points. In some possible implementations, some of the image meshes included in the target area may be selected as the target image meshes, and then the vertices and/or the vertices of these target image meshes and/or located in the target image meshes may be selected. The point on the edge of the image grid is used as the target pixel point. The selection method of the target image grid is not limited in the embodiments of the present disclosure, and the target image grid can be determined by random sampling or sampling at specific intervals from all the image grids included in the target area; The image grid to which the key points in the target area belong can be used as the target image grid, etc.

Step S123 , according to the position of the target pixel point and the position of the key point in the target area, adjust a plurality of pixel points in the target area, and determine the adjusted target area.

Based on the target pixel points and the positions of key points in the target area in the image to be processed, a plurality of pixel points in the target area can be adjusted to determine the adjusted target area. As described in the above disclosed embodiments, the adjustment method can be flexibly determined according to the actual situation. For details, please refer to the following disclosed embodiments, which will not be expanded here.

Through the embodiments of the present disclosure, representative target pixels in the target area can be obtained by screening in a convenient way, reducing the computational complexity of data processing in image processing, and improving the overall speed and efficiency of image processing.

In a possible implementation, step S123 may include:

Determine the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area; adjust a plurality of pixel points in the target area according to the first adjustment distance to determine the adjusted target area.

The first adjustment distance may be the distance that the target pixel needs to move during the adjustment process, and the method for determining the first adjustment distance can be flexibly changed according to different key points in the selected target area. The disclosed embodiments are not expanded here.

The multiple pixels in the target area are adjusted according to the first adjustment distance, and the adjustment method can be flexibly changed. In a possible implementation, a plurality of target pixels in the target area may be moved by a first adjustment distance, and the remaining pixels are not adjusted to obtain an adjusted target area; in a possible implementation, , it is also possible to move multiple target pixels in the target area by the first adjustment distance, and move the pixels in the image grid where the target pixels are located with the movement of the target pixels, and then obtain the adjusted target area.

Since the number of target pixels can be multiple, and the positions of different target pixels are different from the positions of key points in the target area, the corresponding first adjustment distances of different target pixels can vary, Therefore, after the adjustment based on the first adjustment distance, the multiple pixels in the target area still have a relatively natural overall effect on the basis of deformation, which realizes the gradual adjustment of the target area, and improves the effect and naturalness of image processing. degree.

In a possible implementation manner, step S123 may further include: determining, according to the first adjustment distance, a second adjustment distance of the pixels located in the image grid in the target area; pixel points are adjusted to determine the adjusted target area.

The second adjustment distance may be the distance that other pixels in the target area other than the target pixel need to move during the adjustment process, and the determination method of the second adjustment distance can be flexibly selected according to the actual situation, The adjustment distance is interpolated, or the first adjustment distance corresponding to the target pixel that is closest to the remaining pixels is used as the adjustment distance of the remaining pixels. For some possible implementation manners of determining the second adjustment distance, please refer to the following disclosed embodiments, which will not be described here.

The multiple pixels in the target area are adjusted according to the second adjustment distance, and the adjustment method can also be flexibly changed. In a possible implementation, each pixel in the target area may be adjusted according to the second adjustment distance to obtain an adjusted target area; in a possible implementation, the target area may also be adjusted from the target Among the remaining pixels in the area except the target pixel, select some of the pixels by random or specific interval sampling, and adjust the selected part of the pixels according to the second adjustment distance to obtain the adjusted pixel. target area.

By introducing the second adjustment distance, the continuity of pixel point adjustment in the target area can be further improved, thereby further improving the effect and naturalness of image processing.

In a possible implementation, step S123 may further include:

According to the first adjustment distance or the second adjustment distance, multiple pixels in the target area are adjusted to determine the adjusted target area.

Wherein, according to the first adjustment distance or the second adjustment distance, the adjustment of multiple pixels in the target area may be to adjust the target pixels in the target area according to the first adjustment distance, and adjust the remaining pixels according to the second adjustment distance. Adjust the distance to make adjustments to determine the adjusted target area. In some possible implementations, multiple pixels in the target area are adjusted according to the first adjustment distance or the second adjustment distance, and the adjustment method may be the fusion of the above disclosed embodiments, which will not be repeated here.

By adjusting the target area based on the first adjustment distance or the second adjustment distance, the overall progressive adjustment of most of the pixels in the target area can be achieved, which can further improve the effect and naturalness of image processing, and at the same time ensure the image Adjusted comprehensiveness and completeness.

6 shows a flowchart of an image processing method according to an embodiment of the present disclosure. As shown in the figure, in a possible implementation manner, according to the position of the target pixel point and the position of the key point in the target area, determine The first adjustment distance of the target pixel point, which may include:

Step S1231, determining the first target position in the human object according to the relevant key points of the neck in the target area;

Step S1232, according to the actual distance between the target pixel point and the first target position, determine the adjustment ratio of the target pixel point;

Step S1233: Obtain the first adjustment distance of the target pixel according to the adjustment ratio of the target pixel and the preset distance.

The relevant key points of the neck may include the neck key points among the limb key points mentioned in the above disclosed embodiments, and may also include the left neck key points and the contour key points mentioned in the above disclosed embodiments. Right neck key point.

The first target position may be the position coordinates used to calculate the first adjustment distance, and the first target position may be determined according to some key points in the relevant key points, or may be jointly determined by the relevant key points, and is not limited to the following disclosures. Example.

In a possible implementation manner, the first target position may be the middle position of the left neck key point and the right neck key point; in a possible implementation manner, the first target position may also be the position of the neck key point ; In a possible implementation manner, the first target position may also be the center position of the area determined by the three points of the left neck key point, the right neck key point and the neck key point.

According to the position coordinates of the target pixel in the image to be processed and the position coordinates of the first target position determined in step S1232, the actual distance between the target pixel and the first target position can be determined. The actual distance can be used to determine the adjustment ratio of the target pixel, wherein the adjustment ratio can reflect the degree of adjustment of the target pixel. How to determine the adjustment ratio according to the actual distance can be flexibly selected according to the actual situation. In some possible In the implementation mode, the adjustment ratio can be inversely related to the actual distance, that is, the closer the pixel is to the first target position, the farther it moves during the adjustment process, so that the human object in the image to be processed can be stretched more naturally. The length of the head and neck can achieve better human beautification.

Based on the adjustment ratio of the target pixel point and the preset distance, the first adjustment distance of the target pixel point can be obtained. The length of the preset distance can be flexibly set according to the actual situation. In one possible implementation, the preset distance can be a fixed value; in some possible implementations, the preset distance can also be based on The actual situation in the image to be processed is determined flexibly. In an example, the preset distance can be determined according to the length of the neck in the image to be processed, such as 0.1 to 2 times the length of the neck in the image to be processed, or other values range etc.

Based on the above disclosed embodiments, in an example, the manner of determining the first adjustment distance can be expressed by the following formula (1) and formula (2):

move=ratio×preset distance (1)

Among them, move is the first adjustment distance, ratio is the adjustment ratio, and the first target position is the middle position of the left neck key point and the right neck key point. It can be seen from the above formula that, in an example, the adjustment ratio is inverse to the actual distance. Therefore, the first adjustment distance is also inversely related to the actual distance.

Through the embodiments of the present disclosure, the distance between the target pixel point and the neck related key points in the target area can be used to flexibly adjust different target pixel points by using different first adjustment distances, thereby further improving the adjustment of the target area. The progressive nature of the process improves the naturalness and effect of the stretching effect while stretching the head and neck of the human subject in the image to be processed.

In a possible implementation manner, determining the second adjustment distance of the pixels located in the image grid in the target area according to the first adjustment distance may include:

Interpolate the first adjustment distance of the target pixel to obtain the second adjustment distance of the pixel in the image grid where the target pixel is located.

As described in the above disclosed embodiments, the target pixel can be the vertex of the image grid or the pixel on the edge of the image grid. Therefore, in a possible implementation manner, the image grid where the target pixel is located The pixels in the image grid can be located between the vertices or edge points of the image grid. Based on the positional relationship between these pixels and the target pixel, these pixels can be determined by performing interpolation calculation through interpolation processing. the second adjustment distance.

The method of interpolation processing is not limited in the embodiments of the present disclosure, and any method that can realize interpolation calculation, such as Lagrangian interpolation, piecewise interpolation, etc., can be used as the realization method of interpolation processing.

Through the embodiments of the present disclosure, interpolation processing can be used to quickly and conveniently determine the second adjustment distances of multiple pixels in the target area, thereby effectively reducing the computational complexity of image processing and improving the efficiency of image processing.

In some possible implementations, in addition to determining the adjustment distances of multiple pixels in the target area, the adjustment directions of these pixels can also be determined. Therefore, in a possible implementation, step S123 may include:

Determine the second target position in the human object according to the contour key points in the key points of the human object;

According to the position of the target pixel point and the position between the key points in the target area, the plurality of pixel points in the target area are respectively adjusted to the second target position to obtain the adjusted target area.

Wherein, the second target position may be a position used to determine the moving direction of a plurality of pixel points in the target area, and the position may be determined according to one or some key points in the contour key points. The selection of the second target position can be flexibly determined according to the actual situation, and is not limited to the following disclosed embodiments.

In a possible implementation manner, the center position of the area formed by the left shoulder key point, the right shoulder key point, the left underarm key point and the right underarm key point included in the contour key points may be used as the second target position .

Wherein, the left shoulder key point, the right shoulder key point, the left underarm key point and the right underarm key point may respectively correspond to the points 1, 57, 12 and 46 in FIG. 3 mentioned in the above disclosed embodiments. It can be seen that the center position determined by the above points can be the center position of the chest in the human body object, and the center position is taken as the second target position, and the plurality of pixels in the target area of the head and neck are directed to the second target position. The adjustment can naturally stretch the head and neck of the human object, increase the overall proportion of the length of the head and neck in the upper body of the human object, and effectively optimize the proportion of the upper body of the human object.

According to the position of the target pixel point and the position of the key point in the target area, the method of adjusting the plurality of pixel points in the target area to the second target position respectively can refer to the above-mentioned various disclosed embodiments for determining the adjustment distance, and this is not the case here. Repeat. Various implementation manners of step S123 in the embodiments of the present disclosure may be implemented by combining with each other, and the combining manners and sequences are not limited in the embodiments of the present disclosure.

Through the embodiment of the present disclosure, the adjustment direction of each pixel point in the target area can be determined by using the second target position determined by the contour points of the human body, thereby effectively increasing the proportion of the adjusted target area in the human body object, and achieving better Effects optimized for human objects.

In a possible implementation manner, step S13 may include:

Render the material in the target area of the to-be-processed image to the adjusted target area position to generate the target image.

The material of the target area in the image to be processed may be image textures corresponding to multiple pixels in the target area in the image to be processed, such as color or shape, and its implementation can be flexibly based on the actual situation of the image to be processed Decide.

The manner of rendering the material of the target area to the position of the adjusted target area is not limited in the embodiments of the present disclosure. In a possible implementation manner, the adjusted target area may be directly combined with the target area in the image to be processed. The corresponding relationship between pixel points is used to realize the rendering of the corresponding texture; in some possible implementations, each target pixel point contained in the target area can also be connected into a triangular mesh, and then based on the triangular mesh, the material rendering is realized, etc. .

Through the embodiments of the present disclosure, the original image form of the target area can be maintained while adjusting the target area, so that the obtained target image is more natural and real, and the effect of image processing is improved.

FIG. 7 shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure. As shown in the figure, the image processing apparatus 20 may include:

The acquiring module 21 is configured to acquire the key points of the human object in the image to be processed and the target area of the human object, wherein the target area includes the neck area and/or the head area.

The adjustment module 22 is configured to adjust a plurality of pixel points in the target area according to the positions of at least some of the pixel points in the target area and the positions of key points in the target area to determine the adjusted target area.

The target image generation module 23 is configured to generate a target image according to the image to be processed and the adjusted target area.

In a possible implementation manner, the adjustment module is used to: divide the image to be processed into a plurality of image grids; use the pixels located on any image grid in the target area as target pixels; The position and the position of the key points in the target area are adjusted to multiple pixel points in the target area to determine the adjusted target area.

In a possible implementation manner, the adjustment module is further configured to: determine the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area; A plurality of pixel points are adjusted to determine the adjusted target area; or, according to the first adjustment distance, the second adjustment distance of the pixel points located in the image grid in the target area is determined; Adjusting multiple pixels to determine the adjusted target area; or, adjusting multiple pixels in the target area according to the first adjustment distance or the second adjustment distance to determine the adjusted target area.

In a possible implementation manner, the adjustment module is further configured to: determine the first target position in the human object according to the relevant key points of the neck in the target area; according to the actual distance between the target pixel point and the first target position , determine the adjustment ratio of the target pixel point; obtain the first adjustment distance of the target pixel point according to the adjustment ratio of the target pixel point and the preset distance.

In a possible implementation manner, the adjustment module is further configured to: perform interpolation processing on the first adjustment distance of the target pixel point to obtain the second adjustment distance of the pixel point in the image grid where the target pixel point is located.

In a possible implementation manner, the adjustment module is used to: determine the second target position in the human object according to the contour key points in the key points of the human object; according to the position of the target pixel point and the position of the key point in the target area , respectively adjusting a plurality of pixel points in the target area to the second target position to obtain an adjusted target area.

In a possible implementation manner, the adjustment module is further used to: set the center position of the area formed by the left shoulder key point, the right shoulder key point, the left underarm key point and the right underarm key point included in the contour key points, as the second target location.

In a possible implementation manner, the acquisition module is used to: perform limb key point recognition and/or outline key point recognition on the image to be processed, and obtain key points of the human object in the image to be processed, wherein the key points of the human object include limbs key points and/or contour key points; according to the key points of the human object, the human object in the image to be processed is divided into regions to obtain multiple human body regions; the neck region and/or head region are extracted from the multiple human body regions, Get the target area.

In a possible implementation manner, the target image generation module is used for: rendering the material of the target area in the to-be-processed image to the adjusted position of the target area to generate the target image.

Application Scenario Example

8 and 9 show schematic diagrams of an application example of the present disclosure. As shown in the figures, the application example of the present disclosure proposes an image processing method, and the image processing method may include the following processes:

As shown in FIG. 8 , the image to be processed is divided into 112*112 rectangular image grids (the grid in the figure is only an exemplary division, and the actual division method is more dense).

Identify the limb key points and contour key points in the image to be processed as the key points of the human body object; obtain the part to be processed according to the key points above the head and the chest in the key points of the human body object (that is, in the above disclosed embodiments In the application example of the present disclosure, the target area may be the area where the head and neck are located.

As shown in Figure 3, according to the coordinates of the left shoulder key point 1, the right shoulder key point 57, the left underarm key point 12 and the right underarm key point 46 in the outline key points, the center position of the area formed by these key points is obtained, as the second target location.

The vertices of the image grid contained in the target area are used as target pixels. As shown in Figure 8, some solid points in the figure are some exemplary representations of target pixels, and these target pixels are respectively directed to the second target position. When the direction moves, the moving distance of the target pixel point (ie, the first adjustment distance) can be calculated by formula (1) and formula (2) in the above disclosed embodiments.

Move the pixels within the image grid in the target area to the second target position, and the moving distance (ie the second adjustment distance) of the pixels within the image grid can be determined according to the first position of the vertex of the image grid to which it belongs. Adjust the distance to interpolate.

The texture corresponding to the target area in the image to be processed is rendered to the position of the adjusted target area, and the processed target image can be obtained, as shown in Figure 9. It can be seen from the comparison that the processed target image, Human subjects have better head-to-neck ratios, and the overall look of the image is very natural.

The image processing method proposed in the application example of the present disclosure can not only stretch the head and neck of the human object in the target image, but also can be extended to other parts of the human object. For the implementation method, refer to the above disclosed embodiments. It is not repeated here.

It can be understood that the above-mentioned method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle and logic.

Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.

Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented. The computer-readable storage medium may be a volatile computer-readable storage medium or a non-volatile computer-readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to perform the above method.

Embodiments of the present disclosure also provide a computer program product, including computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in a processor of an electronic device When running, the processor in the electronic device executes the above method.

In practical applications, the above-mentioned memory can be a volatile memory (volatile memory), such as RAM; or a non-volatile memory (non-volatile memory), such as ROM, flash memory (flash memory), hard disk (Hard Disk Drive) , HDD) or solid-state drive (Solid-State Drive, SSD); or a combination of the above types of memory, and provide instructions and data to the processor.

The above-mentioned processor may be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. It can be understood that, for different devices, the electronic device used to implement the function of the processor may also be other, which is not specifically limited in the embodiment of the present disclosure.

The electronic device may be provided as a terminal, server or other form of device.

Based on the same technical concept as the foregoing embodiments, an embodiment of the present disclosure further provides a computer program, which implements the above method when the computer program is executed by a processor.

FIG. 10 is a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc. terminal.

10, an electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814 , and the communication component 816 .

The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 can include one or more processors 820 to execute instructions to perform all or some of the steps of the methods described above. Additionally, processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

Memory 804 is configured to store various types of data to support operation at electronic device 800 . Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. Memory 804 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

Power supply assembly 806 provides power to various components of electronic device 800 . Power supply components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800 .

Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 808 includes a front-facing camera and/or a rear-facing camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.

Audio component 810 is configured to output and/or input audio signals. For example, audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 800 is in operating modes, such as calling mode, recording mode, and voice recognition mode. The received audio signal may be further stored in memory 804 or transmitted via communication component 816 . In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

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

Sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of electronic device 800 . For example, the sensor assembly 814 can detect the on/off state of the electronic device 800, the relative positioning of the components, such as the display and the keypad of the electronic device 800, the sensor assembly 814 can also detect the electronic device 800 or one of the electronic device 800 Changes in the position of components, presence or absence of user contact with the electronic device 800 , orientation or acceleration/deceleration of the electronic device 800 and changes in the temperature of the electronic device 800 . Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 may access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related personnel information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.

In an exemplary embodiment, a non-volatile computer-readable storage medium, such as a memory 804 comprising computer program instructions executable by the processor 820 of the electronic device 800 to perform the above method is also provided.

FIG. 11 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server. 11, electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource, represented by memory 1932, for storing instructions executable by processing component 1922, such as applications. An application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Additionally, the processing component 1922 is configured to execute instructions to perform the above-described methods.

The electronic device 1900 may also include a power supply assembly 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 . Electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as memory 1932 comprising computer program instructions executable by processing component 1922 of electronic device 1900 to perform the above-described method.

The present disclosure may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.

A computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above. Computer-readable storage media, as used herein, are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.

The computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages. Source or object code, written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect). In some embodiments, electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state personnel information of computer readable program instructions. Computer readable program instructions can be executed to implement various aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

Various embodiments of the present disclosure have been described above, and the foregoing descriptions are exemplary, not exhaustive, and not limiting of the disclosed embodiments. Numerous modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

An image processing method, comprising:

Acquiring the key points of the human object in the image to be processed and the target area of the human object, wherein the target area includes the neck area and/or the head area;

According to the positions of at least some of the pixel points in the target area and the positions of the key points in the target area, respectively adjust a plurality of pixel points in the target area to determine the adjusted target area;

A target image is generated according to the to-be-processed image and the adjusted target area.
The method according to claim 1, wherein, according to the positions of at least some of the pixel points in the target area and the positions of the key points in the target area Pixel points are adjusted separately to determine the adjusted target area, including:

dividing the to-be-processed image into a plurality of image grids;

Taking the pixel points located on any of the image grids in the target area as the target pixel points;

According to the position of the target pixel point and the position of the key point in the target area, a plurality of pixel points in the target area are adjusted to determine the adjusted target area.
The method according to claim 2, wherein the adjusting a plurality of pixel points in the target area according to the position of the target pixel point and the position of the key point in the target area, Determine the adjusted target area, including:

Determine the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area; Click to adjust to determine the adjusted target area; or,

According to the first adjustment distance, determine the second adjustment distance of the pixel points in the image grid in the target area; adjust a plurality of pixel points in the target area according to the second adjustment distance , to determine the adjusted target area; or,

According to the first adjustment distance or the second adjustment distance, a plurality of pixels in the target area are adjusted to determine an adjusted target area.
The method according to claim 3, wherein the determining the first adjustment distance of the target pixel point according to the position of the target pixel point and the position of the key point in the target area comprises:

Determine the first target position in the human object according to the relevant key points of the neck in the target area;

Determine the adjustment ratio of the target pixel point according to the actual distance between the target pixel point and the first target position;

According to the adjustment ratio of the target pixel point and the preset distance, the first adjustment distance of the target pixel point is obtained.
The method according to claim 3 or 4, wherein the determining, according to the first adjustment distance, the second adjustment distance of the pixels located in the image grid in the target area, comprising:

Interpolating the first adjustment distance of the target pixel point to obtain the second adjustment distance of the pixel point in the image grid where the target pixel point is located.
The method according to any one of claims 2 to 5, characterized in that, according to the position of the target pixel point and the position of the key point in the target area, the plurality of Adjust the pixel points to determine the adjusted target area, including:

determining the second target position in the human object according to the contour key points in the key points of the human object;

According to the position of the target pixel point and the position of the key point in the target area, a plurality of pixel points in the target area are respectively adjusted to the second target position to obtain an adjusted target area.
The method according to claim 6, wherein the determining the second target position in the human object according to the contour key points in the key points of the human object comprises:

The center position of the area formed by the left shoulder key point, the right shoulder key point, the left underarm key point and the right underarm key point included in the outline key points is taken as the second target position.
The method according to any one of claims 1 to 7, wherein the acquiring the key points of the human object in the image to be processed and the target area of the human object comprises:

Performing limb key point identification and/or contour key point identification on the image to be processed, to obtain the key points of the human object in the to-be-processed image, wherein the key points of the human object include limb key points and/or contour key points;

According to the key points of the human object, the human object in the to-be-processed image is divided into regions to obtain a plurality of human regions;

The target region is obtained by extracting a neck region and/or a head region from the plurality of body regions.
The method according to any one of claims 1 to 8, wherein the generating a target image according to the to-be-processed image and the adjusted target area comprises:

Rendering the material of the target area in the to-be-processed image to the adjusted target area position to generate a target image.
An image processing device, comprising:

an acquisition module, configured to acquire the key points of the human object in the image to be processed and the target area of the human object, wherein the target area includes the neck area and/or the head area;

The adjustment module is configured to adjust a plurality of pixel points in the target area according to the positions of at least part of the pixel points in the target area and the positions of the key points in the target area, and determine the adjusted pixel points. target area;

A target image generation module, configured to generate a target image according to the to-be-processed image and the adjusted target area.
An electronic device, comprising:

processor;

memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any one of claims 1-9.
A computer-readable storage medium on which computer program instructions are stored, characterized in that, when the computer program instructions are executed by a processor, the method described in any one of claims 1 to 9 is implemented.
A computer program product comprising computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, which when executed in a processor of an electronic device, the electronic A processor in the device executes the method for implementing any of claims 1-9.