CN113963111A

CN113963111A - Image processing method and device

Info

Publication number: CN113963111A
Application number: CN202111183167.2A
Authority: CN
Inventors: 阮晓虎
Original assignee: Vivo Mobile Communication Co Ltd
Current assignee: Vivo Mobile Communication Co Ltd
Priority date: 2021-10-11
Filing date: 2021-10-11
Publication date: 2022-01-21

Abstract

The application discloses an image processing method and device, and belongs to the technical field of image processing. The method comprises the following steps: extracting human skeleton feature points of a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image; constructing a portrait three-dimensional image corresponding to the portrait image based on the human body skeleton characteristic point information; and displaying the portrait three-dimensional image and the target image in an overlapping manner.

Description

Image processing method and device

Technical Field

The present application belongs to the field of image processing technology, and in particular, relates to an image processing method and apparatus.

Background

With the rapid development of image technology, more and more users can conveniently download or take portrait pictures.

In the related art, when viewing the portrait picture, a user often views the portrait picture by printing the photo or displays the photo on a screen, but the portrait picture viewed in this way is not vivid enough.

Disclosure of Invention

The embodiment of the application aims to provide an image processing method and device, which can solve the problem that a portrait photo is not vivid enough.

In a first aspect, an embodiment of the present application provides an image processing method, including:

extracting human skeleton feature points of a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image;

constructing a portrait three-dimensional image corresponding to the portrait image based on the human body skeleton characteristic point information;

and displaying the portrait three-dimensional image and the target image in an overlapping manner.

In a second aspect, an embodiment of the present application provides an image processing apparatus, including:

the extraction module is used for extracting human skeleton feature points of a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image;

the construction module is used for constructing a portrait three-dimensional image corresponding to the portrait image based on the human body skeleton characteristic point information;

and the display module is used for displaying the portrait three-dimensional image and the target image in an overlapping mode.

In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, and when executed by the processor, the program or instructions implement the steps of the method according to the first aspect.

In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the method according to the first aspect.

In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method according to the first aspect.

In the embodiment of the application, human skeleton feature points of a portrait image in a target image are extracted, a portrait three-dimensional image corresponding to the portrait image is constructed based on human skeleton feature point information, the portrait three-dimensional image more conforming to the portrait image features can be constructed, the portrait three-dimensional image constructed based on the human skeleton feature point information can be better attached to the target image for display, and the portrait three-dimensional image corresponding to the portrait three-dimensional image is constructed based on the portrait image in the target image and is displayed in an overlapping mode, so that vivid and dynamic portrait image display effects are achieved

Drawings

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

fig. 2 is a schematic diagram of human skeleton motion characteristic point information corresponding to a motion control command provided in an embodiment of the present application;

fig. 3 is a schematic diagram illustrating extraction of human skeletal feature points according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

fig. 6 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described clearly below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present disclosure.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The image processing method and apparatus, the electronic device, and the storage medium provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings by specific embodiments and application scenarios thereof.

Fig. 1 is a schematic flow chart of an image processing method according to an embodiment of the present application, as shown in fig. 1, including:

step 110, extracting human skeleton feature points of a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image;

specifically, the target image described in the embodiments of the present application is an image including a portrait image, specifically, an image of a shooting target object, or a certain video frame in a shooting target object video, the specific information can be shot by the user through the corresponding electronic equipment, or shot by the merchant through the specific electronic equipment, the electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm top computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine or a self-service machine, and the like, and the embodiment of the present application is not particularly limited.

It is understood that the target object described in the embodiment of the present application may specifically be a promotional image of a merchant, such as a portrait card promoting a product, a printed photo, or a portrait image in a display screen, and may also be a specific character.

Ideally, the target image described in the embodiment of the present application should be captured in a front view direction of the target object, and if there is a tilt in the captured angle, the captured image is angle-adjusted to obtain an image in the front view, that is, the target image.

The adjustment method may be to perform perspective correction based on the position information of the target object and to obtain a target image without depth difference.

Optionally, the adjustment mode may further be to correct the target object according to a depth correction model to obtain a target image without depth difference, where the depth correction model is a model with an angle correction function, and specifically may be a model for completing the pre-training of a deep learning network.

The portrait image described in the embodiment of the present application is obtained by analyzing the target image based on the portrait identification method, that is, the portrait image in the target image is obtained by matting the portrait part in the target image, and the specific portrait identification method may be a portrait identification neural network or other portrait identification methods, which is not limited in the embodiment of the present application.

The human skeleton feature points described in the embodiments of the present application can represent the positions of the human feature points in the image, and can also effectively represent human actions and postures.

The extraction of the human skeleton feature points described in the embodiment of the present application may be specifically realized by a human feature point identification model capable of identifying human skeleton feature points, and human image images are input into the human feature point identification model, so that human skeleton feature point information corresponding to the human image images can be obtained.

Since the portrait image in the target object has corresponding motions and postures, the human skeleton feature point information of the portrait image can effectively help to generate a portrait three-dimensional image having the same motions and postures as the portrait.

Step 120, constructing a portrait three-dimensional image corresponding to the portrait image based on the human body skeleton characteristic point information;

specifically, in the embodiment of the application, after the human skeleton feature point information is determined, a human three-dimensional material corresponding to the human image is obtained, and the human three-dimensional image rendering is performed based on the human skeleton feature point information, so that the human three-dimensional image with the same action and posture as the human image is finally obtained.

And step 130, overlapping and displaying the portrait three-dimensional image and the target image.

Specifically, in the embodiment of the present application, the display may be performed on the electronic device of the user, or may be performed on the electronic device that is used by the merchant to perform propaganda in cooperation with the target object.

In the embodiment of the present application, the human skeleton feature point information of the portrait image is identified in the embodiment of the present application, and the portrait three-dimensional image is constructed based on the human skeleton feature point information of the portrait image, that is, the portrait three-dimensional image and the portrait image have the same human skeleton feature point information.

And the portrait image is in the target image, so that when the portrait three-dimensional image and the target image are displayed in a superimposed manner, the feature points in the human skeleton feature point information of the portrait three-dimensional image can be adjusted to the positions of the feature points in the human skeleton feature point information of the portrait image, and the portrait three-dimensional image is displayed in the portrait image in a fitted manner, namely, the superimposed display of the portrait three-dimensional image and the target image is completed.

Optionally, after the three-dimensional coordinate system of the portrait three-dimensional image is identified, other background images except the portrait image in the target image may be further obtained, and the target three-dimensional coordinate system corresponding to the target image is constructed by analyzing line features and depth of field features in the other background images.

After the portrait coordinate system corresponding to the portrait three-dimensional image is aligned with the target three-dimensional coordinate system, the portrait three-dimensional image can be correspondingly superposed and displayed in the target image, and the display position of the portrait three-dimensional image can be further adjusted after the alignment of the coordinate system is completed.

In the embodiment of the application, human skeleton feature points of the portrait image in the target image are extracted, the portrait three-dimensional image corresponding to the portrait image is constructed based on the human skeleton feature point information, the portrait three-dimensional image more conforming to the portrait image features can be constructed, the portrait three-dimensional image constructed based on the human skeleton feature point information can be better attached to the target image for display, the portrait three-dimensional image corresponding to the portrait three-dimensional image is constructed based on the portrait image in the target image and is displayed in an overlapping mode, and therefore the vivid and dynamic portrait image display effect is achieved.

Optionally, the extracting of the human skeleton feature point of the portrait image in the target image to obtain the first human skeleton feature point information corresponding to the portrait image includes:

analyzing the portrait image based on a human body characteristic point identification model to obtain initial human body skeleton characteristic point information;

and correcting the initial human body bone characteristic point information based on the reference human body bone characteristic point information to obtain human body bone characteristic point information corresponding to the portrait image.

Specifically, the human body feature point recognition model described in the embodiment of the present application may specifically be a model capable of implementing a human body feature point recognition function of a portrait image, and specifically may be a neural network model that is previously trained, such as a high resolution network model or a convolutional neural network model.

The human body feature point identification model described in the embodiment of the application can be obtained by training a portrait sample image carrying human body skeleton feature point labels.

In the embodiment of the application, after the portrait image is input into the human body feature point identification model, initial human body bone feature point information obtained by model identification can be obtained, but because the image content of the portrait image is often complex and the identification result of the model may have a certain error, the initial human body bone feature point information may not be accurate enough, so that the reference human body bone feature point information can be introduced to correct the initial human body bone feature point information in the embodiment of the application.

The reference human skeleton feature point information described in the embodiment of the present application may specifically be human skeleton feature point information generated by referring to a medical human skeleton model in advance, and may be used as a standard of the human skeleton feature point information.

In the process of correcting the initial human body bone feature point information based on the reference human body bone feature point information, the initial human body bone key points can be adjusted specifically based on the number of human body feature points in the reference human body bone feature point information.

In the embodiment of the application, the initial human skeleton feature point information corresponding to the portrait image can be effectively identified through the human feature point identification model, and the initial human skeleton feature point information is corrected through the reference human skeleton feature point information, so that the accuracy of human skeleton feature point information identification can be effectively improved.

Optionally, the constructing a three-dimensional portrait image corresponding to the portrait image based on the human body bone feature point information includes:

carrying out face recognition on the portrait image to obtain face image information corresponding to the portrait image;

constructing an initial portrait three-dimensional image based on the portrait three-dimensional material corresponding to the face image information and the human skeleton feature point information;

and performing face rendering on the initial portrait three-dimensional image based on the face image information to obtain the portrait three-dimensional image.

The face recognition of the portrait image described in the embodiment of the present application may be specifically implemented by a face recognition algorithm or a face recognition model, which is not limited in the embodiment of the present application.

In the embodiment of the application, after the face recognition is performed on the portrait image, a face area image corresponding to the portrait image is obtained, and the face area image can be used as face image information corresponding to the portrait image.

Optionally, because the portrait image is often a relatively well-known person, the face region image may also be subjected to face recognition to determine name information corresponding to the face image, and then, the face image corresponding to the name information is acquired from the internet through the name information, and the acquired face image is used as face image information corresponding to the portrait image.

In the embodiment of the application, the process of obtaining the face image from the internet specifically may be to select the image according to recommendation of a search engine or a user click rate in the face image corresponding to the name information.

It can be understood that, because the proportion of corresponding figures of different people is different greatly, for example, some people may have a large figure and some people have a small figure, and in order to better construct a three-dimensional image of a portrait close to a real person, the embodiment of the present application needs to obtain different three-dimensional materials of the portrait according to different people.

In the embodiment of the application, because the number of brand speakers is limited, the portrait three-dimensional materials corresponding to the speakers can be stored in advance, and meanwhile, a set of general portrait three-dimensional materials are stored and used when the corresponding speakers are not matched.

In the embodiment of the application, under the condition that the face image information is the face region image corresponding to the face image, the face image information can be matched with the face image of each speaker, and the corresponding face three-dimensional material is taken according to the matching result.

And under the condition that the face image information is the name information corresponding to the face image, acquiring a corresponding portrait three-dimensional material based on the name information corresponding to the face image information.

When the face image information identification fails, namely the corresponding portrait three-dimensional material is not found, the universal portrait three-dimensional material is adopted at the moment.

The portrait three-dimensional materials can specifically comprise pre-recorded skeleton animation materials, clothing animation materials, hair style animation materials and the like, and each portrait three-dimensional material corresponds to human skeleton characteristic point information, namely the rendering position of each portrait three-dimensional material is associated with the human skeleton characteristic point information.

In the embodiment of the application, face region animation materials, skeleton animation materials, clothes animation materials, hairstyle animation materials and the like can be added to the positions corresponding to the human skeleton feature point information, so that the initial portrait three-dimensional image is constructed.

However, whether the rendering of the face part is vivid or not is decisive for the final effect of the portrait three-dimensional image, so that after the initial portrait three-dimensional image is constructed, the face area can be further subjected to key modeling and rendering, that is, the face image information can be attached to the face area in the initial portrait three-dimensional image, and the face texture of the portrait three-dimensional image after the face attachment is obtained is more detailed.

In the embodiment of the application, the face recognition is carried out on the portrait image, so that the matched portrait three-dimensional materials are determined according to the face recognition result, the initial portrait three-dimensional image which is more in line with the character characteristics corresponding to the portrait image is further generated, finally, the face rendering is carried out on the initial portrait three-dimensional image through the face image information, and finally, the portrait three-dimensional image with the delicate facial texture is obtained.

Optionally, after the superimposing and displaying the portrait three-dimensional image and the target image, further comprising:

acquiring an action control instruction;

determining human skeleton action characteristic point information corresponding to the action control instruction;

and processing the human skeleton feature point information corresponding to the human skeleton three-dimensional image based on the human skeleton action feature point information to obtain a human skeleton three-dimensional image after action adjustment.

Specifically, the motion control command described in the embodiment of the present application may specifically be a preset motion command, for example, a motion command for swinging hands, jumping, hugging, giving flowers, or waving, where the preset motion control command corresponds to one or more pieces of information of human skeleton motion characteristic points.

The motion control instruction described in the embodiment of the present application may also be a motion control instruction generated based on the captured user motion, that is, the three-dimensional portrait image may synchronously move along with the user in real time, where the motion control instruction may be generated by capturing the motion of the user by using a camera or a motion capture sensor, the motion capture sensor or the camera may be installed at a target object, and may be configured in an electronic device of the user by communicating with a display device to synchronize the motion control instruction.

In the embodiment of the application, because the human skeleton feature point information can express human actions and postures, it can be understood that various actions can be controlled by controlling the human skeleton feature points corresponding to the portrait three-dimensional image, specifically, different coordinates of the human skeleton action feature points can be set, and a group of actions can be formed by a series of continuous changes of the human skeleton feature points.

Therefore, in the embodiment of the present application, each motion control command corresponds to a group of human skeleton motion feature point information, which may include one or more coordinates of human skeleton motion feature points, fig. 2 is a schematic diagram of human skeleton motion feature point information corresponding to the motion control command provided in the embodiment of the present application, as shown in fig. 2, a waving motion may correspond to three pieces of human skeleton motion feature point information, and after the waving motion is continuously adjusted to a position corresponding to the human skeleton feature point information, a portrait three-dimensional image may be controlled to complete the waving motion.

The interactive action may be prompted when the user clicks or touches the screen, for example providing a display interface selecting action control instructions in which the user may select the action that he wishes the portrait three-dimensional image to perform.

When a preset action control instruction is executed, the coordinates of key points in the human skeleton characteristic point information corresponding to the portrait three-dimensional image are adjusted according to the coordinates of the key points corresponding to the human skeleton action characteristic point information corresponding to the action control instruction, so that the portrait three-dimensional image is controlled to execute the action.

When executing a motion control instruction generated by captured user motion, the coordinates of the feature points in the human skeleton feature point information corresponding to the three-dimensional portrait image can be adjusted to the coordinates of the motion feature points in the human skeleton motion feature point information corresponding to the user motion, so that motion tracking of the real user through the three-dimensional portrait image is realized, for example, when the user stretches his hand, the three-dimensional portrait image also performs a hand stretching motion.

In the embodiment of the application, after the human skeleton action feature point information corresponding to the action control instruction is obtained, the coordinates of each feature point in the human skeleton feature point information corresponding to the portrait three-dimensional image are adjusted to the coordinates of the action feature point in the human skeleton action feature point information, so that the portrait three-dimensional image can be controlled to make various actions, the portrait three-dimensional image is more vivid, the portrait three-dimensional image can track and imitate the actions of a user, stronger interaction can be brought, and interestingness is enhanced.

Optionally, the initial human bone feature point information includes M initial human bone feature points, the reference human bone feature point information includes N reference human bone feature points, and the initial human bone feature point information is corrected based on the reference human bone feature point information to obtain human bone feature point information corresponding to the portrait image, including:

under the condition that M is larger than N, removing initial human skeleton feature points which are not matched with the reference human skeleton feature points from the initial human skeleton feature point information to obtain human skeleton feature point information corresponding to the portrait image;

or, when M is less than or equal to N, using the initial human bone feature point information as human bone feature point information corresponding to the portrait image, where M and N are positive integers.

Specifically, when the number M of the initial human body feature points in the initial human body bone feature point information is less than or equal to the number N of the reference human body feature points in the reference human body bone feature point information, the identification result is higher in reliability at this time, and the initial human body bone feature point information is directly used as the human body bone feature point information corresponding to the portrait image without modifying the identification result.

Under the condition that the number M of the initial human body feature points in the initial human body bone feature point information is larger than the number N of the reference human body feature points in the reference human body bone feature point information, it is indicated that the human body feature points which are mistakenly identified exist in the initial human body bone feature point information, then the human body feature points which do not correspond to the reference human body bone feature point information in the initial human body bone feature point information are found at the moment, and are combined with the adjacent human body feature points or are directly deleted, and finally the human body bone feature point information corresponding to the portrait image is obtained.

In the embodiment of the application, the initial human body bone characteristic point information extracted by the algorithm model is further corrected by taking the reference human body bone characteristic point information with the standard human body bone characteristic point information as a standard, so that the accuracy of the human body bone characteristic point information corresponding to the portrait image is ensured.

Optionally, in the embodiment of the present application, a human-shaped card is taken as an example to further describe the scheme of the present application, that is, the target image in the embodiment of the present application is an image of a captured human-shaped card, and the human-shaped image is an image of a human-shaped card area.

In the embodiment of the present application, a portrait image in a target image is obtained by performing cutout processing on a portrait image in the target image, fig. 3 is a schematic diagram of human skeleton feature point extraction provided in the embodiment of the present application, as shown in fig. 3, human skeleton feature point extraction is performed on the portrait image in the target image to obtain human skeleton feature point information corresponding to the portrait image, portrait three-dimensional image construction is completed based on the human skeleton feature point information, and then the portrait three-dimensional image and the target image are displayed in a superimposed manner.

As an optional embodiment, a rendering background may also be added to the target image described in the embodiment of the present application, and at this time, the three-dimensional portrait image may be displayed in an overlapping manner with the rendering background.

It should be noted that, in the image processing method provided in the embodiment of the present application, the execution subject may be an image processing apparatus, or a control module in the image processing apparatus for executing the image processing method. The image processing apparatus provided in the embodiment of the present application is described with an example in which an image processing apparatus executes an image processing method.

Fig. 4 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application, as shown in fig. 4, including: an extraction module 410, a construction module 420 and a display module 430; the extraction module 410 is configured to perform human skeleton feature point extraction on a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image; the construction module 420 is configured to construct a three-dimensional portrait image corresponding to the portrait image based on the human skeleton feature point information; the display module 430 is configured to display the portrait three-dimensional image and the target image in a superimposed manner.

Optionally, the extracting module is specifically configured to:

Optionally, the building module is specifically configured to:

Optionally, the apparatus further comprises:

the acquisition module is used for acquiring an action control instruction;

the determining module is used for determining human skeleton action characteristic point information corresponding to the action control instruction;

and the adjusting module is used for processing the human skeleton characteristic point information corresponding to the human three-dimensional image based on the human skeleton action characteristic point information to obtain a human three-dimensional image after action adjustment.

Optionally, the initial human bone feature point information includes M initial human bone feature points, the reference human bone feature point information includes N reference human bone feature points, and the extraction module is specifically configured to:

The image processing apparatus in the embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal. The device can be mobile electronic equipment or non-mobile electronic equipment. By way of example, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm top computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine or a self-service machine, and the like, and the embodiments of the present application are not particularly limited.

The image processing apparatus in the embodiment of the present application may be an apparatus having an operating system. The operating system may be an Android operating system (Android), an iOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.

The image processing apparatus provided in the embodiment of the present application can implement each process implemented by the method embodiments of fig. 1 to fig. 3, and is not described herein again to avoid repetition.

Optionally, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 5, an electronic device 500 according to an embodiment of the present application is further provided, and includes a processor 501, a memory 502, and a program or an instruction stored in the memory 502 and capable of being executed on the processor 501, and when the program or the instruction is executed by the processor 501, the process of the embodiment of the image processing method is implemented, and the same technical effect can be achieved, and details are not repeated here to avoid repetition.

It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.

The electronic device 600 includes, but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, a processor 610, and the like.

Those skilled in the art will appreciate that the electronic device 600 may further comprise a power source (e.g., a battery) for supplying power to the various components, and the power source may be logically connected to the processor 610 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The electronic device structure shown in fig. 6 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than those shown, or combine some components, or arrange different components, and thus, the description is omitted here.

The processor 610 is configured to perform human skeleton feature point extraction on a portrait image in a target image to obtain human skeleton feature point information corresponding to the portrait image;

the processor 610 is configured to construct a portrait three-dimensional image corresponding to the portrait image based on the human body bone feature point information;

the display unit 606 is configured to display the three-dimensional portrait image and the target image in a superimposed manner.

Optionally, the processor 610 is configured to analyze the portrait image based on a human body feature point identification model to obtain initial human body bone feature point information;

the processor 610 is configured to correct the initial human body bone feature point information based on the reference human body bone feature point information, so as to obtain human body bone feature point information corresponding to the portrait image.

Optionally, the processor 610 is configured to perform face recognition on the portrait image to obtain face image information corresponding to the portrait image;

the processor 610 is configured to construct an initial portrait three-dimensional image based on the portrait three-dimensional material corresponding to the facial image information and the human skeleton feature point information;

the processor 610 is configured to perform face rendering on the initial three-dimensional portrait image based on the face image information, so as to obtain a three-dimensional portrait image.

Optionally, the user input unit 607 is used for acquiring a motion control instruction;

the processor 610 is configured to determine human skeleton motion feature point information corresponding to the motion control instruction;

the processor 610 is configured to process the human skeleton feature point information corresponding to the human skeleton three-dimensional image based on the human skeleton action feature point information, so as to obtain a human skeleton three-dimensional image with an adjusted action.

Optionally, the processor 610 is configured to, in the initial human bone feature point information, remove an initial human bone feature point that is not matched with the reference human bone feature point from the initial human bone feature point information to obtain human bone feature point information corresponding to the portrait image when M is greater than N;

It is to be understood that, in the embodiment of the present application, the input Unit 604 may include a Graphics Processing Unit (GPU) 6041 and a microphone 6042, and the Graphics Processing Unit 6041 processes image data of a still picture or a video obtained by an image capturing apparatus (such as a camera) in a video capturing mode or an image capturing mode. The display unit 606 may include a display panel 6061, and the display panel 6061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 607 includes a touch panel 6071 and other input devices 6072. A touch panel 6071, also referred to as a touch screen. The touch panel 6071 may include two parts of a touch detection device and a touch controller. Other input devices 6072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail herein. The memory 609 may be used to store software programs as well as various data including, but not limited to, application programs and an operating system. The processor 610 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 610.

The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the embodiment of the image processing method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and so on.

The embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to execute a program or an instruction to implement each process of the embodiment of the image processing method, and can achieve the same technical effect, and the details are not repeated here to avoid repetition.

It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as system-on-chip, system-on-chip or system-on-chip, etc.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present application.

While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. An image processing method, comprising:

2. The image processing method according to claim 1, wherein the extracting human skeleton feature points from the portrait image in the target image to obtain first human skeleton feature point information corresponding to the portrait image comprises:

3. The image processing method according to claim 1, wherein the constructing a three-dimensional portrait image corresponding to the portrait image based on the human skeleton feature point information comprises:

4. The image processing method according to claim 1, further comprising, after said superimposed display of said portrait three-dimensional image and said target image:

acquiring an action control instruction;

5. The image processing method according to claim 2, wherein the initial human bone feature point information includes M initial human bone feature points, the reference human bone feature point information includes N reference human bone feature points, and the correcting the initial human bone feature point information based on the reference human bone feature point information to obtain human bone feature point information corresponding to the portrait image includes:

6. An image processing apparatus characterized by comprising:

7. The image processing apparatus according to claim 6, wherein the extraction module is specifically configured to:

8. The image processing apparatus according to claim 6, wherein the construction module is specifically configured to:

9. The apparatus according to claim 6, characterized by further comprising:

the acquisition module is used for acquiring an action control instruction;

10. The image processing device according to claim 7, wherein the initial human bone feature point information includes M initial human bone feature points, the reference human bone feature point information includes N reference human bone feature points, and the extraction module is specifically configured to: