WO2018219120A1 - Image display method, image processing method and device, terminal and server - Google Patents

Abstract

The embodiments of the present application belong to the field of image processing, and disclosed thereby are an image display method, an image processing method and device, a terminal and a server. The image display method comprises: uploading a target face image of a target face to a server; sending first image data corresponding to an original image to the server; receiving augmented reality (AR) model data sent by the server, the AR model data being sent when the target face is comprised in the original image; rendering and displaying an AR model according to the AR model data; and sending a selection signal for the target AR model to the server, the server being used for performing image processing on the target face in the original image according to image processing parameters corresponding to the target AR model; and receiving second image data sent by the server, and rendering and displaying the second image data, the second image data being the image data of the original image after image processing. Within the embodiments of the present application, the actual effect of different image processing is displayed by means of an AR model, which is more vivid and accurate than pictures or text descriptions.

Description

Image display method, image processing method, device, terminal, and server

The embodiment of the present application claims the priority of the Chinese patent application submitted by the State Intellectual Property Office of China, the application number is 201710400342.6, and the invention name is "image display method, image processing method and device" on May 31, 2017, the entire content of which is The citations are incorporated in the examples of the present application.

Technical field

The embodiments of the present invention relate to the field of image processing, and in particular, to an image display method, an image processing method device, a terminal, and a server.

Background technique

As image processing technology continues to mature, more and more image processing applications have emerged. While the user is taking a photo or video, the image processing application can be used to visualize the captured image in real time.

Common image processing applications include: Beauty Camera app. After the user selects the beauty function of the beauty camera application, the beauty camera application performs real-time beauty treatment on the characters in the shooting screen, for example, whitening the eyes, magnifying the eyes, etc. To achieve a beauty effect.

In the related art, the beauty camera application provides different beauty schemes for users to select and use in the form of pictures or texts. However, for some beauty schemes, the actual beauty effects cannot be accurately reflected by pictures or texts. For example, for the beauty mode of raising the bridge of the nose, the picture or text cannot accurately reflect the actual beauty effect.

Summary of the invention

The embodiment of the present application provides an image display method, an image processing method, a device, a terminal, and a server, which can solve the problem that the actual effect of the image processing cannot be accurately reflected by the picture or the text. The technical solution is as follows:

According to a first aspect of the embodiments of the present application, an image display method is provided, the method comprising:

Uploading a target face image of the target face to the server;

Sending, to the server, first image data corresponding to the original image;

Receiving enhanced display (Augmented Reality, AR) model data sent by the server, the AR model data is sent when the original image includes the target face, the AR model data is used to render at least one AR model, and the AR model is used to display the image processing effect;

Rendering and displaying an AR model based on the AR model data;

Sending a selection signal to the target AR model to the server, and the server is configured to perform image processing on the target human face in the original image according to the image processing parameter corresponding to the target AR model;

The second image data sent by the server is received and rendered and displayed, and the second image data is image data of the original image after image processing.

According to a second aspect of the embodiments of the present application, an image processing method is provided, the method comprising:

Receiving a target face image of the target face uploaded by the terminal;

Receiving first image data corresponding to the original image sent by the terminal;

When the target image includes the target face, the AR model data is sent to the terminal, and the terminal is configured to render and display at least one AR model according to the AR model data, and the AR model is used to display the image processing effect;

Receiving a selection signal sent by the terminal to the target AR model;

Performing image processing on the first image data according to image processing parameters corresponding to the target AR model;

Sending second image data to the terminal, the second image data is image data of the original image after image processing, and the terminal is configured to render and display the second image data.

According to a third aspect of the embodiments of the present application, an image display apparatus is provided, the apparatus comprising:

An uploading module, configured to upload a target face image of the target face to the server;

a first sending module, configured to send, to the server, first image data corresponding to the original image;

a first receiving module, configured to receive AR model data sent by the server, where the AR model data is sent when the original image includes the target human face, the AR model data is used to render at least one AR model, and the AR model is used to display the image processing effect;

a first display module, configured to render and display an AR model according to the AR model data;

a second sending module, configured to send a selection signal to the target AR model to the server, where the server is configured to perform image processing on the target human face in the original image according to the image processing parameter corresponding to the target AR model;

The second display module is configured to receive second image data sent by the server and perform rendering display, where the second image data is image data of the original image after image processing.

According to a fourth aspect of the embodiments of the present application, there is provided an image processing apparatus, the apparatus comprising:

a fourth receiving module, configured to receive a target face image of the target face uploaded by the terminal;

a second receiving module, configured to receive first image data corresponding to the original image sent by the terminal;

a third sending module, configured to: when the original image includes the target human face, send the AR model data to the terminal, where the terminal is configured to render and display at least one AR model according to the AR model data, where the AR model is used to display the image processing effect;

a third receiving module, configured to receive a selection signal sent by the terminal to the target AR model;

a processing module, configured to perform image processing on the target human face in the original image according to the image processing parameter corresponding to the target AR model;

And a fourth sending module, configured to send second image data to the terminal, where the second image data is image data of the original image after the image processing, and the terminal is configured to perform rendering and displaying the second image data.

According to a fifth aspect of embodiments of the present application, there is provided a terminal, the terminal comprising a processor and a memory, wherein the memory stores at least one instruction, the instruction being loaded and executed by the processor to implement as the first The image display method described in the aspect.

According to a sixth aspect of the embodiments of the present application, there is provided a computer readable storage medium having stored therein at least one instruction loaded by a processor and executed to implement an image as described in the first aspect Display method.

According to a seventh aspect of the embodiments of the present application, there is provided a server, the server comprising a processor and a memory, wherein the memory stores at least one instruction, the instruction being loaded and executed by the processor to implement a second The image processing method described in the aspect.

According to an eighth aspect of the embodiments of the present application, there is provided a computer readable storage medium having stored therein at least one instruction loaded by a processor and executed to implement an image as described in the second aspect Approach.

In the embodiment of the present application, the terminal renders and displays the corresponding AR model according to the AR model data sent by the server, and feeds back the target AR model selected by the user to the server, so that the server responds to the original image according to the image processing effect displayed by the target AR model. Image processing, and the image processed data is fed back to the terminal for rendering and display by the terminal; compared with the image processing effect using image or text, the image processing effect is more intuitive and accurate by using the AR model, which is beneficial to improving the user's selection image. At the same time, based on the pre-uploaded target face image, image processing is performed only on the target face in the original image, thereby achieving the effect of directional beauty.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present invention. Other drawings may also be obtained from those of ordinary skill in the art in light of the inventive work.

FIG. 1 is a schematic diagram showing an implementation environment provided by an embodiment of the present application;

FIG. 2 is a flowchart of an image processing method provided by an embodiment of the present application;

FIG. 3 is a flowchart of an image processing method provided by another embodiment of the present application;

4 is a schematic diagram of an implementation of face recognition and image processing by a web server using dual threads;

FIG. 5 is a flowchart of a process of determining a candidate AR model involved in the image processing method shown in FIG. 4; FIG.

6A and 6B are schematic diagrams showing an interface of a terminal to display an AR model;

FIG. 7 is a block diagram showing the structure of an image display apparatus according to an embodiment of the present application;

FIG. 8 is a block diagram showing the structure of an image processing apparatus according to an embodiment of the present application;

FIG. 9 is a structural block diagram of a server provided by an embodiment of the present application;

FIG. 10 is a schematic structural diagram of a terminal provided by an embodiment of the present application.

detailed description

The embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

"Multiple" as referred to herein means two or more. "and/or", describing the association relationship of the associated objects, indicating that there may be three relationships, for example, A and/or B, which may indicate that there are three cases where A exists separately, A and B exist at the same time, and B exists separately. The character "/" generally indicates that the contextual object is an "or" relationship.

For ease of understanding, the nouns involved in the embodiments of the present application are explained below.

AR: Augmented Reality Technology is a technology that integrates real world information with virtual world information. With AR technology, the built virtual model can be displayed in the real image, and the user can interact with the virtual model. For example, the user can select the virtual model by gesture or perform corresponding operations on the virtual model (such as grabbing, placing, etc. ). In the embodiment of the present application, the terminal displays the image processing effect in the form of an AR model in the displayed original image according to the AR model data sent by the web server, and further acquires the AR model selected by the user, wherein the AR model is a three-dimensional human body. Face model.

Web Graphics Library (webGL): A three-dimensional (3-dimension, 3D) drawing standard that allows Java scripts (JavaScript) to be combined with OpenGL for Embedded Systems (OpenGL ES 2.0). Together. By adding a JavaScript binding to OpenGL ES 2.0, webGL can provide hardware 3D accelerated rendering for HyperText Markup Language 5 (HTML5) web pages, using a graphics processing unit (GPU) on the web page. Render and display 3D scenes and models in the browser.

Vertex Shader: Program code used to render vertices of 3D model shapes. In the embodiment of the present application, the vertex shader is used to render the vertex of each shape in the AR model, thereby drawing the shape contour of the AR model.

Fragment Shader: Program code used to render the surface color and/or surface texture of a 3D model. In the embodiment of the present application, after the vertex shader is used to render the shape vertex of the AR model, the color and texture of the AR model are rendered using the fragment shader.

The image display and image processing method provided by the embodiments of the present application can be used for a local photo/video beautification scene, or a video call scene, or a photo shooting/video recording scene. Of course, it can be applied to other scenarios that need to beautify the face. This embodiment of the present application does not limit this.

Local photo/video landscaping scene

Most of the current image processing applications have beauty features. However, the image processing application usually displays the beauty effect in the form of text or pictures, and the display effect is not intuitive, and the actual beauty effect cannot be accurately expressed. With the method provided by the embodiment of the present application, when the user uses an image processing application to make a face in a local photo or a video, the image processing application uses the AR model to display different beauty effects, so that the beauty effect is achieved. The display is more intuitive and accurate; at the same time, the image processing application can specifically target the face specified in the photo or video to achieve the effect of directed beauty.

Video call scene

When a user uses a video call application (or web page) to make a video call with another person, they can make a beauty of their face through the beauty function provided by the application. However, the video call application usually displays the beauty effect in text form. This display method is not intuitive and accurate, and the user frequently switches between different beauty effects during the video call. With the method provided by the embodiment of the present application, before the video call (or during the video call), the video call application displays different beauty effects in the form of an AR model, so that the user can quickly and accurately select the appropriate beauty mode. Avoid frequent user switching. At the same time, the video data after the beauty is transmitted to the terminal of the video call dual-issue, so that the terminal performs rendering display.

Photo shooting/video recording scene

When a user performs real-time photo shooting or video recording through a webpage or an application, the corresponding beauty effect can be selected to make a beauty of the face in the screen. However, the beauty effect is displayed in the form of text or pictures, and the display effect is not intuitive, which is not conducive to the user to quickly select the appropriate beauty effect. With the method provided by the embodiment of the present application, when the user takes a photo or video in real time, the server feeds back the AR model data to the terminal, so that the terminal renders and displays the AR model according to the AR model data, thereby viewing different beauty effects through the displayed AR model, and Finally, the face in the image is beautifully decorated according to the beauty mode selected by the user. At the same time, by uploading the target face image in advance, when the framing picture includes a plurality of faces, it is possible to perform beauty on the target face.

Different from the prior art, the image processing is performed by the terminal independently. In the embodiment of the present application, the image processing is completed by the terminal and the server. The terminal is responsible for image acquisition, image processing mode selection and image processing after the image is processed, and the server is responsible for providing different image processing methods and processing the image.

Please refer to FIG. 1 , which shows a schematic diagram of an implementation environment provided by an embodiment of the present application, where the implementation environment includes a terminal 110 and a server 120 .

The terminal 110 is an electronic device having an image capturing function. The electronic device is a smart phone, a tablet brain, a personal portable computer, and the like. Optionally, in the embodiment of the present application, a web browser or an image processing application supporting web real-time communication (webRTC) and webGL technology is installed and run in the terminal 110. Taking a web browser as an example, webRTC technology enables users to use a web browser for real-time audio and video conversations or recordings; with webGL technology, when a complex 3D model or scene needs to be displayed on a web page, the web browser can call the terminal. The GPU in 110 performs 3D rendering.

The terminal 110 and the server 120 are connected by a wired or wireless network.

The server 120 is a server cluster or a cloud computing center composed of one server and several servers. In a possible implementation, the server 120 is a background server of the image processing application; in another possible implementation, the server 120 is a web server corresponding to the image processing webpage, and is used to receive the webpage through the image processing. The image is processed image.

In an exemplary application scenario, when a user accesses an image processing webpage and performs video recording using a web browser, the terminal 110 collects the original image through the image capturing component, and sends the original image to the web corresponding to the image processing webpage by using webRTC technology. The server 120 performs corresponding image processing on the original image by the web server 120, and then returns the image processed original image to the terminal 110 by using the webRTC technology, and the terminal 110 performs real-time display.

In the embodiment of the present application, the server 120 is further configured to provide different image processing modes for the user to select and use. Optionally, as shown in FIG. 1 , an AR model database 121 is built in the server 120, and the AR model database 121 stores an AR model for displaying different image processing effects. For example, the AR model is a 3D face model for displaying changes in the face before and after image processing in an animated form. In a possible implementation, after receiving the original image sent by the terminal 110, the server selects several AR models from the AR model database 121 and feeds back to the terminal 110, and the terminal 110 renders and displays several AR models, so that The user selects the corresponding image processing mode according to the image processing effect displayed by the AR model.

In the embodiment of the present application, the server 120 is further configured to provide image processing for a face image of a specific user. Optionally, as shown in FIG. 1 , a server face image database 122 is configured in the server 120, and the face image database 122 stores a face image uploaded by the terminal. In a possible implementation, after receiving the original image sent by the terminal 110, the server 120 acquires the face image of the target user corresponding to the target 110 from the face image database 122, and recognizes that the original image contains multiple faces. At this time, the server 120 performs image processing only on the face image of the target user in the original image.

Optionally, the wireless or wired network described above uses standard communication techniques and/or protocols. The network is usually the Internet, but can also be any network, including but not limited to a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a mobile, a wired or a wireless. Any combination of networks, private networks, or virtual private networks). In some embodiments, data exchanged over a network is represented using techniques and/or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), and the like. In addition, you can use such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec). Regular encryption techniques are used to encrypt all or some of the links. In other embodiments, the above described data communication techniques may also be replaced or supplemented using custom and/or dedicated data communication techniques.

Please refer to FIG. 2, which is a flowchart of an image processing method according to an embodiment of the present application. The image processing method is used in the implementation environment shown in FIG. 1 as an example. The method includes:

Step 201: The terminal uploads a target face image of the target face to the server.

In a possible implementation manner, when the terminal accesses the image processing webpage by using a web browser, the target uploading image corresponding to the target face of the terminal is uploaded to the terminal by the HyperText Transfer Protocol (HTTP) post uploading method. Image processing web page web server.

Optionally, in order to improve the security of image uploading, the terminal encrypts the target face image by using a preset encryption algorithm, and then uploads the encrypted target face image to the server. The preset encryption algorithm is an RSA (Rivest-Shamir-Adleman) algorithm, a Message Digest Algorithm 5 (MD5) algorithm, or a Data Encryption Standard (DES) algorithm.

Step 202: The server receives the target face image of the target face uploaded by the terminal.

Correspondingly, the server receives the target face image uploaded by the terminal, and stores the target face image in association with the terminal, so as to be called when the face recognition is performed subsequently. Illustratively, as shown in FIG. 1, the server 120 stores the received target face image in the face image database 122.

Optionally, in order to improve the accuracy of the subsequent face recognition, the terminal uploads multiple target face images, and correspondingly, the server stores multiple target face images corresponding to the same terminal.

Optionally, at least two target face images are stored in the terminal, and different target face images correspond to target faces of different users.

Step 203: The terminal sends the first image data corresponding to the original image to the server.

In a possible implementation manner, when the server is a web server corresponding to the image processing webpage, and the terminal accesses the image processing webpage through the web browser and performs video recording, the web browser invokes the image capturing component of the terminal (such as a camera). The original image is collected, and the original image is encoded by using a video image coding technology (such as x264 encoding technology) to obtain the first image data, and then the first image data is transmitted to the web server by using webRTC technology. Among them, the image processing webpage and the web browser support webGL technology.

Step 204: The server receives first image data of an original image sent by the terminal.

Step 205: When the target face is included in the original image, the server sends the AR model data to the terminal.

Different from the related art, the user can only know the actual effect of the image processing from the picture or the text description. In the embodiment of the present application, after receiving the first image data, the server provides the AR model data to the terminal for at least one display by the terminal. An AR model showing the effect of image processing.

Optionally, an AR model database is built in the server, and the AR model database stores data corresponding to different AR models. The AR model data is defined using OpenGL and includes vertex shaders and fragment shaders.

In addition, in the embodiment of the present application, when detecting that the original image includes the target face corresponding to the terminal, the terminal sends the AR model data to the terminal; when the original image does not include the target face, the server does not send the terminal to the terminal. Send AR model data.

In a possible implementation manner, after receiving the first image data, the server restores the original image by using a video image decoding technology, and then identifies the face feature of the face in the original image by using image recognition technology, and from the AR model database. The target AR model matching the facial feature is searched, and the AR model data of the target AR model is sent to the terminal for rendering and display by the terminal. Since the AR model displayed by the terminal is highly similar to the user's face, the image processing effect (beauty effect) displayed by the AR model is more realistic.

Step 206: The terminal receives the AR model data sent by the server.

Step 207: The terminal renders and displays at least one AR model according to the AR model data, and the AR model is used to display an image processing effect.

In a possible implementation manner, when the AR model data includes a vertex shader and a fragment shader (defined by OpenGL), and the web browser running by the terminal supports the webGL technology, the web browser invokes the terminal according to the AR model data. The GPU performs AR model rendering, which improves the rendering speed of the AR model, while eliminating the need to develop additional web rendering plugins.

The terminal displays the AR model rendered by the GPU in a web browser, so that the user can intuitively understand the actual effect of different image processing modes through the AR model, and facilitate the user to directly select the image processing mode desired by the user.

Step 208: The terminal sends a selection signal to the target AR model to the server.

In a possible implementation manner, after the terminal displays the AR model on the screen, the terminal receives a touch selection signal of the target AR model, where the touch selection signal is triggered when the user touches the display area where the target AR model is located.

In other possible implementation manners, when the user performs real-time interaction with the virtual AR model by performing a predetermined interaction action, after the terminal sends the interactive image including the interaction action to the server, the server determines, by using the AR identification technology, that the user is selected through the interaction action. The target AR model.

For example, the web server determines the first spatial coordinate of the user's finger in the real three-dimensional space according to the interactive image sent by the terminal, and compares the coordinate position relationship between the first spatial coordinate and the second spatial coordinate of each virtual AR model, the server. Determine the AR model selected by the user's finger.

Step 209: The server receives a selection signal sent by the terminal to the target AR model.

Step 210: The server performs image processing on the target human face in the original image according to the image processing parameter corresponding to the target AR model.

After determining the target AR model selected by the user, the server performs corresponding image processing on the original image according to the image processing parameters corresponding to the target AR model, thereby achieving an image processing effect consistent with the target AR model. Optionally, the image processing parameters include a face adjustment parameter, a skin color adjustment parameter, a face organ size adjustment parameter, and the like.

In addition, in the embodiment of the present application, the server enables the recognition thread to recognize the face image in the original image, thereby performing image processing only on the specific target face in the original image according to the face recognition result, and for the non-target in the original image. The face, the server will not image it, to achieve personalized image processing.

Step 211: The server sends second image data to the terminal, where the second image data is image data of the original image after image processing.

Optionally, after the image processing is completed, the server returns the second image data of the original image after the image processing to the terminal in real time through the webRTC technology, so that the terminal performs real-time rendering display according to the second image data, thereby viewing the effect of real-time beauty.

Step 212: The terminal receives the second image data sent by the server, and performs rendering display.

In this embodiment, the terminal presents the actual effect of different image processing modes to the user in the manner of the AR model according to the AR model data sent by the server, and instructs the server to process the original image according to the image processing mode selected by the user, thereby improving image processing. The efficiency of the selection method improves the user experience.

In summary, in the image processing method provided by the embodiment, the terminal renders and displays the corresponding AR model according to the AR model data sent by the server, and feeds back the target AR model selected by the user to the server, so that the server displays according to the target AR model. The image processing effect, the corresponding image processing is performed on the original image, and the image processed data is fed back to the terminal for rendering and display by the terminal; compared with the image processing effect by using the image or the text, the image processing effect is further improved by using the AR model. Intuitive and accurate, it is beneficial to improve the efficiency of the user's choice of image processing method. At the same time, based on the pre-uploaded target face image, image processing is performed only on the target face in the original image, thereby achieving the effect of oriented beauty.

In a possible implementation manner, when the server is a web server, and the image processing webpage provided by the web server supports webGL, and the web browser running in the terminal also supports webGL, the webGL and the webRTC technology can be used between the terminal and the web server. Real-time image processing is implemented, thereby eliminating the need to install an image processing application in the terminal, which will be described below using an illustrative embodiment.

Please refer to FIG. 3, which is a flowchart of an image processing method according to an embodiment of the present application. The image processing method is used in the implementation environment shown in FIG. 1 as an example. The method includes:

Step 301: The terminal uploads a target face image of the target human face to the web server.

Step 302: The web server receives the target face image of the target face uploaded by the terminal.

For the implementation of the foregoing steps 301 to 302, refer to steps 201 to 202, and details are not described herein again.

Step 303: The terminal accesses the image processing webpage through the browser, the image processing webpage supports the webpage graphics library webGL technology, and the browser supports the webGL technology.

In this embodiment, the web browser running in the terminal supports the webGL technology, and the image processing webpage accessed by the terminal is developed using the webGL technology.

Step 304: The terminal sends the first image data to the web server corresponding to the image processing webpage through the browser.

When the image processing webpage is accessed through a web browser and video recording is performed, the terminal enables the image capturing component to collect the original image, and sends the original image to the web server through webRTC technology.

For the process of the terminal acquiring the original image and converting the original image into the first image data, refer to step 203, which is not described herein again.

Step 305: The web server receives the first image data sent by the terminal through the image processing webpage.

Step 306, the web server stores the first image data into the buffer pool.

In order to perform two high-concurrency operations of face recognition and image processing at the same time, as shown in FIG. 4, the web server receives the first image data, instead of directly processing the first image data, but the first image. The data is stored in the buffer pool, and the original image is subjected to face recognition and image processing by enabling the first thread and the second thread respectively.

Step 307, the web server enables the first thread to read the first image data from the buffer pool.

The web server is configured to identify the target face in the original image by the first thread.

For a way that the web server enables the first thread, in one possible implementation, the web server uses the shell_exec function in a hypertext preprocessor (PHP) to start an independent shell (shell). The PHP script thus independently enables a shell process to perform face recognition.

After the first thread is enabled, the web server reads the first image data from the buffer pool through the first thread, thereby performing target face recognition based on the first image data.

Step 308: The web server identifies, according to the target face image, whether the target face is included in the original image.

In a possible implementation manner, as shown in FIG. 4, under the first thread, the web server obtains the target face image uploaded by the terminal from the face image database, and intercepts the face from the original image by the face recognition technology. Part image. Further, the web server calculates the similarity between the face image and the target face image in the original image, thereby identifying the target face included in the original image based on the similarity.

Optionally, the web server uses a perceptual hash algorithm to calculate the similarity between the facial image and the target facial image in the original image, including the following steps.

1. Generating a first picture of a predetermined size from the face image in the original image; and generating a second picture of a predetermined size according to the target face image.

In order to discard the picture difference caused by different sizes and proportions, the web server scales the face image and the target face image in the original image to generate the first picture and the second picture of the same size.

In a possible implementation manner, the size of the first picture and the second picture generated by the web server are both 8×8 and a total of 64 pixels.

2. Converting the first picture into a first grayscale picture; converting the second picture into a second grayscale picture.

In a possible implementation manner, the first grayscale picture and the second grayscale picture are both 64 grayscale pictures, that is, the gray value of any pixel point in the first grayscale picture and the second grayscale picture belongs to the pre Set 64 preset continuous gray values.

3. Calculating a first gray average value of the first grayscale picture; calculating a second gray level average value of the second grayscale picture.

The web server calculates a first grayscale average value of the first grayscale image according to the grayscale value of each pixel in the first grayscale image; similarly, the web server determines the grayscale value of each pixel in the second degree image. And calculating a second gray average value of the second grayscale picture.

4. generating a first picture fingerprint of the first grayscale picture according to the gray value of each pixel in the first grayscale picture and the first gray level average; according to the gray value of each pixel in the second grayscale picture And a second grayscale average to generate a second picture fingerprint of the second grayscale picture.

The picture fingerprint is used to represent the distribution feature of the pixel in the picture, and the higher the similarity between the two picture fingerprints, the higher the similarity of the picture corresponding to the picture fingerprint. In a possible implementation manner, in a possible implementation manner, when calculating the first picture fingerprint of the first grayscale picture, the web server compares the gray value of each pixel point with the average value of the first gray level. If the gray value of the pixel is greater than or equal to the first gray average, the web server sets the value of the pixel to 1; if the gray value of the pixel is smaller than the first gray average, the web server selects the pixel The value of the point is set to 0. The web server combines the values of the respective pixels to obtain the first picture fingerprint of the first grayscale picture.

For example, when the sizes of the first grayscale picture and the second grayscale picture are both 8×8, the first picture fingerprint and the second picture fingerprint are both 64-bit binary numbers.

5. Calculate the similarity according to the first picture fingerprint and the second picture fingerprint.

After calculating the first picture fingerprint and the second picture fingerprint, the web server counts different digits of the first picture fingerprint and the second picture fingerprint. If the number of different digits is less than the first threshold (for example, 5), the web server determines that the facial image in the original image has a high degree of similarity to the target facial image, that is, the original image includes the target human face; if the different number of digits is greater than the second threshold (eg 10) The web server determines that the facial image in the original image has low similarity to the target facial image, that is, the original image does not include the target human face.

When the target face is included in the original image, the server performs step 309. Optionally, when the original image does not include the target face, the server sends a prompt message to the terminal, prompting the user to upload the target face that needs image processing, or prompting the user to mark the target face that needs to be processed in the current viewfinder image. And store the marked target face.

Step 309, when the target image includes the target face, the web server sends the AR model data to the terminal.

Since the web server performs image processing only on the target face, when it is recognized that the target image includes the target face, the web server sends the AR model data to the terminal, and when the original image is identified as not including the target face, the web server The AR model data is not sent to the terminal.

In order to enable the user to select an image processing mode that conforms to the characteristics of the face, thereby optimizing the effect of the image processing, in one possible implementation, as shown in FIG. 5, the step includes the following steps.

Step 309A, identifying a facial feature of the target human face in the original image by a predetermined image recognition technology, the facial feature including at least one of a skin color, a face shape, or a face organ size.

After the web server determines that the original image contains the target face, the image recognition technology performs face feature recognition on the target face, thereby obtaining features such as skin color, face shape and face organ size.

Optionally, the web server calculates a target size of each face organ in the target face according to the face feature recognition result, so as to determine the adjustment size of each face organ according to the target size and the actual face organ size, so as to follow The face organ is image processed based on the resizing.

Step 309B: Find a matching candidate AR model from the AR model database according to the face feature of the target face, and the similarity of the face features of the target face of the candidate AR model is greater than a threshold.

Optionally, the web server stores an AR model with different facial features, such as an AR model of the face of the face, an AR model of the face of the Chinese character, an AR model of the long face, and the like. In order for the user to view the AR model that is similar to the face feature of the user, the web server searches for the AR model with the similarity greater than the threshold in the AR model database based on the face feature of the target face obtained in the above step 309A.

For example, when the face feature of the target face is a national character face and a dark skin color, the web server determines an AR model satisfying the above face feature in the AR model database as a candidate AR model.

Step 309C: Send AR model data corresponding to the candidate AR model to the terminal.

Further, the terminal sends the AR model data corresponding to the candidate AR model to the terminal for rendering and display.

In the embodiment of the present application, the AR model data is defined by OpenGL, and includes a vertex shader and a fragment shader, wherein the vertex shader is program code for rendering a shape vertex of the AR model, and the fragment shader is used to render the AR model. Program code for color and/or texture.

Step 310: The terminal receives the AR model data sent by the web server.

Step 311: The terminal renders and displays at least one AR model according to the AR model data, and the AR model is used to display an image processing effect.

In a possible implementation manner, when the web browser running by the terminal supports the webGL technology, and the received AR model data is defined by OpenGL, including the vertex shader and the fragment shader, the terminal renders the AR model according to the AR model data. Including the following steps:

First, the AR model data is rendered by the webGL technology to obtain the AR model.

Optionally, for the web browser supporting the webGL technology, when receiving the AR model data sent by the web server, the web browser invokes the GPU of the terminal through the webGL, thereby using the GPU to respectively run the vertex shader and the fragment shader, and render Get the corresponding AR model. Compared with the dedicated webpage rendering plug-in (software) in the web browser for 3D model rendering, the GPU (hardware) is used to perform 3D model rendering faster, and the development of an additional webpage rendering plug-in is eliminated.

Second, draw and display the AR model in the image processing webpage.

In a possible implementation manner, after the web browser renders the AR model according to the AR model data, the AR model is drawn by gldraw, and finally the drawn AR model is displayed on the terminal screen.

Illustratively, as shown in FIG. 6A, the terminal displays the rendered first AR model 62 and the second AR model 63 when displaying the user's face 61, wherein the first AR model 62 is used for 3D animation. The method displays the image processing effect of the enlarged eye, and the second AR model 63 is used to display the image processing effect of pulling the bridge of the nose in a 3D animation manner.

In order to be able to display the virtual AR model into the real three-dimensional space, thereby achieving a more realistic 3D face model display effect, in another possible implementation manner, the terminal drawing the display AR model in the image processing webpage includes the following steps.

First, build a three-dimensional space according to the current picture.

Optionally, the terminal identifies each object included in the current picture, and constructs a three-dimensional space corresponding to the real environment according to the depth of field and the relative positional relationship of each object in the current picture.

Second, determine the display coordinates of the AR model in three-dimensional space.

In a possible implementation manner, the terminal further acquires the head coordinates of the user's head in the three-dimensional space, and determines the display coordinates of the AR model in the three-dimensional space according to the head coordinates, wherein the display coordinates and the head of the AR model The coordinates are adjacent, that is, in the three-dimensional space, the AR model is displayed on the side of the user's head.

3. Display and display the AR model in the current picture according to the display coordinates.

Further, the terminal displays the AR model at the corresponding position of the current screen according to the determined display coordinates, and adjusts the display angle of the AR model, thereby simulating the effect of displaying the virtual model in the real three-dimensional space.

Illustratively, as shown in FIG. 6B, in the current screen displayed by the terminal, the first AR model 62 and the second AR model 63 are displayed on the three-dimensional space side of the user's face 61.

In step 312, the terminal sends a selection signal to the target AR model to the web server.

Illustratively, as shown in FIG. 6A, when the user touches the display area corresponding to the first AR model 62, the terminal transmits a selection signal to the first AR model to the web server; when the user touches the display corresponding to the second AR model 63 In the case of the area, the terminal transmits a selection signal to the second AR model to the web server.

When the virtual AR model is displayed in the real three-dimensional space, the user can select the virtual AR model by gesture in the three-dimensional space. As shown in FIG. 6B, the terminal identifies the three-dimensional space region selected by the user's finger. When it is detected that the three-dimensional spatial region selected by the finger matches the display coordinate corresponding to the first AR model 62, the first AR model 62 is determined to be selected, and The web server sends a selection signal to the first AR model.

Step 313: The web server receives a selection signal sent by the terminal to the target AR model.

Step 314, the web server enables the second thread to read the first image data from the buffer pool.

As shown in FIG. 4, the web server enables the second thread to perform image processing on the original image in parallel while enabling the first thread for face recognition. The manner in which the web server enables the second thread is similar to the manner in which the first thread is enabled. This embodiment is not described herein again.

Under the second thread, the web server reads the first image data from the buffer pool, thereby performing image processing on the target face in the original image based on the first image data and the image processing manner fed back by the terminal.

Step 315: The web server performs image processing on the target human face in the original image according to the image processing parameter corresponding to the target AR model.

In a possible implementation manner, the web server polls the first thread while executing the second thread, and changes the target AR model selected by the user in the first thread, that is, when the user switches the image processing mode, according to the change The image processing effect exhibited by the target AR model is re-image processed.

It should be noted that when the selection signal for the target AR model is not received or the target face is not included in the original image, the web server directly feeds back the original image to the terminal.

In step 316, the web server sends the second image data to the terminal.

In other possible implementation manners, in order to speed up the feedback speed of the original image after the image processing, when the web server detects that the target image includes the target human face, the second thread performs the target face based on the image processing parameters corresponding to each AR model. The image processing is performed to obtain a plurality of sets of second image data, and when the selection signal for the target AR model is received, the target second image data corresponding to the original image processed by the target image processing parameter is directly fed back to the terminal.

Step 317: The terminal receives the second image data sent by the web server, and performs rendering display.

In this embodiment, the web server enables dual-threading, and performs face recognition and image processing on the original image respectively, fully utilizes the processing resources of the web server, maximizes hardware performance, and improves the response speed of the terminal interface; meanwhile, due to high concurrent Face recognition and image processing are performed on the web server side, and the terminal is only responsible for rendering and displaying the original image after image processing, so that even in the case of poor terminal performance, a better image processing effect can be achieved.

Different from the consistency processing of each face in the image, in this embodiment, the server performs image processing only on a specific target face in the original image, and achieves the effect of personalized beauty.

It should be noted that, in the foregoing embodiments, the step of using the terminal as the execution subject may be separately implemented as the image display method on the terminal side, and the step of using the server or the web server as the execution subject may be separately implemented as the image processing method on the server side. This embodiment is not described here.

The following is an embodiment of the apparatus of the present application. For details not specifically described in the apparatus embodiment, reference may be made to the one-to-one corresponding method embodiment.

Please refer to FIG. 7, which is a structural block diagram of an image display apparatus according to an embodiment of the present application. The image display device is implemented as a whole or a part of the terminal 110 in FIG. 1 by hardware or a combination of hardware and software. The device includes: a first sending module 710, a first receiving module 720, a first display module 730, a second sending module 740, and a second display module 750.

The first sending module 710 is configured to implement the function of step 203 above;

The first receiving module 720 is configured to implement the functions of the foregoing step 206 or 310;

The first display module 730 is configured to implement the functions of the foregoing step 207 or 311;

a second sending module 740, configured to implement the functions of the foregoing step 208 or 312;

The second display module 750 is configured to implement the functions of the foregoing step 212 or 317.

Optionally, the first sending module 710 includes: an access unit, and a first sending unit;

An access unit, configured to implement the functions of step 303 above;

a first sending unit, configured to implement the function of step 304 above;

The first display module 730 includes:

a rendering unit, configured to render AR model data by using webGL technology to obtain an AR model;

a display unit for drawing and displaying the AR model in the image processing webpage.

Optionally, a rendering unit is used to:

Calling the GPU through webGL technology;

The vertex shader and the fragment shader are run by the GPU, and the AR model is rendered.

Optionally, the device further includes: an uploading module;

The uploading module is used to implement the functions of step 201 or 301 above.

Please refer to FIG. 8 , which is a structural block diagram of an image processing apparatus according to an embodiment of the present application. The image processing apparatus is implemented as a whole or a part of the server 120 in FIG. 1 by hardware or a combination of hardware and software. The device includes: a second receiving module 810, a third sending module 820, a third receiving module 830, a processing module 840, and a fourth sending module 850;

a second receiving module 810, configured to implement the functions of step 204 above;

a third sending module 820, configured to implement the functions of step 205 above;

The third receiving module 830 is configured to implement the functions of the foregoing step 209 or 313;

The processing module 840 is configured to implement the functions of the foregoing step 210 or 315;

The fourth sending module 850 is configured to implement the functions of the foregoing step 211 or 316.

Optionally, the second receiving module 810 is further configured to implement the function of the foregoing step 305.

Optionally, the device further includes: a fourth receiving module;

a fourth receiving module, configured to implement the functions of the foregoing step 202 or 302;

The device further includes: a storage module, a first reading module, and an identification module;

a storage module, configured to implement the functions of step 306 above;

a first reading module, configured to implement the function of step 307 above;

An identification module, configured to implement the functions of step 308 above;

The third sending module 820 is further configured to implement the function of the foregoing step 309;

The device further includes: a second reading module;

The second reading module is configured to implement the functions of step 314 above.

Optionally, the third sending module 820 includes: an identifying unit, a searching unit, and a sending unit;

An identification unit, configured to implement the function of step 309A above;

a searching unit, configured to implement the function of step 309B above;

The sending unit is configured to implement the function of step 309C.

Please refer to FIG. 9, which is a structural block diagram of a server provided by an embodiment of the present application. The server 900 is implemented as the server 120 of FIG. Specifically:

The server 900 includes a central processing unit (CPU) 901, a system memory 904 including a random access memory (RAM) 902 and a read only memory (ROM) 903, and a system bus 905 that connects the system memory 904 and the central processing unit 901. The server 900 also includes a basic input/output system (I/O system) 906 that facilitates transfer of information between various devices within the computer, and mass storage for storing the operating system 913, applications 914, and other program modules 915. Device 907.

The basic input/output system 906 includes a display 908 for displaying information and an input device 909 such as a mouse or keyboard for user input of information. Both the display 908 and the input device 909 are connected to the central processing unit 901 via an input and output controller 910 that is coupled to the system bus 905. The basic input/output system 906 can also include an input and output controller 910 for receiving and processing input from a plurality of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input and output controller 910 also provides output to a display screen, printer, or other type of output device.

The mass storage device 907 is connected to the central processing unit 901 by a mass storage controller (not shown) connected to the system bus 905. The mass storage device 907 and its associated computer readable medium provide non-volatile storage for the server 900. That is, the mass storage device 907 can include a computer readable medium (not shown) such as a hard disk or a CD-ROM drive.

Without loss of generality, the computer readable medium can include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM, EEPROM, flash memory or other solid state storage technologies, CD-ROM, DVD or other optical storage, tape cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage medium is not limited to the above. The system memory 904 and mass storage device 907 described above may be collectively referred to as a memory.

According to various embodiments of the present application, the server 900 may also be operated by a remote computer connected to the network through a network such as the Internet. That is, the server 900 can be connected to the network 912 through a network interface unit 911 connected to the system bus 905, or can also be connected to other types of networks or remote computer systems (not shown) using the network interface unit 911. .

The memory further includes one or more programs, the one or more programs being stored in a memory, the one or more programs including instructions for performing the image processing methods provided by embodiments of the present invention. A person skilled in the art can understand that all or part of the steps in the image processing method of the above embodiment can be completed by a program to instruct related hardware. The program can be stored in a computer readable storage medium, and the storage medium can include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.

Please refer to FIG. 10, which is a schematic structural diagram of a terminal provided by an embodiment of the present application. The terminal 1000 is the terminal 110 in FIG. Specifically:

The terminal 1000 may include an RF (Radio Frequency) circuit 1010, a memory 1020 including one or more computer readable storage media, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a near field communication module 1070, A processor 1080 having one or more processing cores, and a power supply 1090 and the like are included. It will be understood by those skilled in the art that the terminal structure shown in FIG. 10 does not constitute a limitation to the terminal, and may include more or less components than those illustrated, or combine some components, or different component arrangements. among them:

The RF circuit 1010 can be used for receiving and transmitting signals during and after receiving or transmitting information, in particular, receiving downlink information of the base station and then processing it by one or more processors 1080; in addition, transmitting data related to the uplink to the base station . Generally, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier). , duplexer, etc. In addition, RF circuit 1010 can also communicate with the network and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access). , Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), e-mail, SMS (Short Messaging Service), and the like.

The memory 1020 can be used to store software programs and modules, and the processor 1080 executes various functional applications and data processing by running software programs and modules stored in the memory 1020. The memory 1020 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to The data created by the use of the terminal 1000 (such as audio data, phone book, etc.) and the like. Moreover, memory 1020 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 1020 can also include a memory controller to provide access to memory 1020 by processor 1080 and input unit 1030.

Input unit 1030 can be used to receive input numeric or character information, as well as to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls. Specifically, the input unit 1030 may include an image input device 1031 and other input devices 1032. The image input device 1031 may be a camera or an optical scanning device. In addition to the image input device 1031, the input unit 1030 may also include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.

Display unit 1040 can be used to display information entered by the user or information provided to the user and various graphical user interfaces of terminal 1000, which can be constructed from graphics, text, icons, video, and any combination thereof. The display unit 1040 may include a display panel 1041. Alternatively, the display panel 1041 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like.

Terminal 1000 can also include at least one type of sensor 1050, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1041 according to the brightness of the ambient light, and the proximity sensor may close the display panel 1041 when the terminal 1000 moves to the ear. / or backlight. As a kind of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity. It can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the terminal 1000 can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, not here Let me repeat.

Audio circuit 1060, speaker 1061, and microphone 1062 can provide an audio interface between the user and terminal 1000. The audio circuit 1060 can transmit the converted electrical data of the received audio data to the speaker 1061, and convert it into a sound signal output by the speaker 1061; on the other hand, the microphone 1062 converts the collected sound signal into an electrical signal, by the audio circuit 1060. After receiving, it is converted into audio data, and then processed by the audio data output processor 1080, transmitted to the electronic device such as another electronic device via the RF circuit 1010, or outputted to the memory 1020 for further processing. The audio circuit 1060 may also include an earbud jack to provide communication of the peripheral earphones with the terminal 1000.

The terminal 1000 establishes a near field communication connection with the external device through the near field communication module 1070, and performs data interaction through the near field communication connection. In this embodiment, the near field communication module 1070 specifically includes a Bluetooth module and/or a WiFi module.

The processor 1080 is the control center of the terminal 1000, connecting various portions of the entire handset with various interfaces and lines, by running or executing software programs and/or modules stored in the memory 1020, and recalling data stored in the memory 1020, The various functions and processing data of the terminal 1000 are performed to perform overall monitoring of the mobile phone. Optionally, the processor 1080 may include one or more processing cores; preferably, the processor 1080 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, and the like. The modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 1080.

The terminal 1000 also includes a power source 1090 (such as a battery) for powering various components. Preferably, the power source can be logically coupled to the processor 1080 through a power management system to manage functions such as charging, discharging, and power management through the power management system. The power supply 1090 may also include any one or more of a DC or AC power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

Although not shown, the terminal 1000 may further include a Bluetooth module or the like, and details are not described herein again.

Specifically, in this embodiment, the terminal 1000 further includes a memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors to implement the image display described above. method.

A person skilled in the art can understand that all or part of the steps in the image display method of the above embodiment can be completed by a program instructing related hardware, and the program can be stored in a computer readable storage medium, and the storage medium can include: Read memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk.

The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalents, improvements, etc., which are within the spirit and scope of the present invention, should be included in the protection of the present invention. Within the scope.

Claims (18)

1. An image display method, characterized in that the method comprises:

   Uploading a target face image of the target face to the server;

   Sending, to the server, first image data corresponding to the original image;

   Receiving, by the server, the augmented reality AR model data, where the AR model data is sent when the target image includes the target human face, and the AR model data is used to render at least one AR model, the AR model Used to display image processing effects;

   Rendering and displaying the AR model according to the AR model data;

   Sending a selection signal to the target AR model to the server, the server is configured to perform image processing on the target human face in the original image according to image processing parameters corresponding to the target AR model;

   Receiving, by the server, sending second image data, and performing rendering display, wherein the second image data is image data of the original image after image processing.
2. The method according to claim 1, wherein the server is a webpage web server, and the sending the first image data corresponding to the original image to the server comprises:

   Accessing an image processing webpage through a browser, the image processing webpage supporting a web graphics library webGL technology, and the browser supports webGL technology;

   Transmitting, by the browser, the first image data to the web server corresponding to the image processing webpage;

   The rendering and displaying the AR model according to the AR model data includes:

   Rendering the AR model data by using a webGL technology to obtain the AR model;

   The AR model is displayed and displayed in the image processing web page.
3. The method according to claim 2, wherein said AR model data includes a vertex shader and a fragment shader, said vertex shader being program code for rendering a shape vertex of said AR model, said A fragment shader is program code for rendering colors and/or textures of the AR model;

   The AR model data is rendered by using the webGL technology to obtain the AR model, including:

   Calling the image processor GPU through the webGL technology;

   The AR model is rendered by running the vertex shader and the fragment shader through the GPU.
4. An image processing method, the method comprising:

   Receiving a target face image of the target face uploaded by the terminal;

   Receiving first image data corresponding to the original image sent by the terminal;

   And when the target image includes the target human face, transmitting, by the terminal, augmented reality AR model data, where the terminal is configured to render and display at least one AR model according to the AR model data, where the AR model is used to Display image processing effects;

   Receiving a selection signal sent by the terminal to the target AR model;

   Performing image processing on the target face in the original image according to image processing parameters corresponding to the target AR model;

   Sending second image data to the terminal, the second image data is image data of the original image after image processing, and the terminal is configured to perform rendering display on the second image data.
5. The method according to claim 4, wherein the receiving the first image data corresponding to the original image sent by the terminal comprises:

   Receiving, by the image processing webpage, the first image data sent by the terminal, where the image processing webpage supports the webpage graphics library webGL technology, and the terminal accesses the image processing webpage through a browser supporting the webGL technology, Transmitting the first image data.
6. The method according to claim 4 or 5, wherein after the receiving the first image data of the original image sent by the terminal, the method further comprises:

   Depositing the first image data into a buffer pool;

   Enabling the first thread to read the first image data from the buffer pool;

   Identifying whether the target face is included in the original image according to the target face image;

   Performing the step of transmitting the AR model data to the terminal when the target face is included in the original image;

   Before performing image processing on the target face in the original image according to the image processing parameter corresponding to the target AR model, the method further includes:

   The second thread is enabled to read the first image data from the buffer pool.
7. The method according to claim 6, wherein the transmitting the AR model data to the terminal comprises:

   Recognizing a facial feature of the target human face in the original image by a predetermined image recognition technique, the facial feature including at least one of a skin color, a face shape, or a face organ size;

   Finding a matching candidate AR model from the AR model database according to the face feature of the target face, the face feature of the candidate AR model, the similarity of the face feature of the target face is greater than a threshold;

   Sending AR model data corresponding to the candidate AR model to the terminal.
8. An image display device, characterized in that the device comprises:

   An uploading module, configured to upload a target face image of the target face to the server;

   a first sending module, configured to send, to the server, first image data corresponding to the original image;

   a first receiving module, configured to receive the augmented reality AR model data sent by the server, where the AR model data is sent when the target image includes the target human face, and the AR model data is used to render at least one An AR model for displaying an image processing effect;

   a first display module, configured to render and display the AR model according to the AR model data;

   a second sending module, configured to send, to the server, a selection signal for a target AR model, where the server is configured to perform, according to the image processing parameter corresponding to the target AR model, the target face in the original image Image Processing;

   a second display module, configured to receive second image data sent by the server, and perform rendering display, where the second image data is image data of the original image after image processing.
9. The device according to claim 8, wherein the server is a webpage web server, and the first sending module comprises:

   An access unit for accessing an image processing webpage through a browser, the image processing webpage supporting a web graphics library webGL technology, and the browser supports webGL technology;

   a first sending unit, configured to send, by using the browser, the first image data to the web server corresponding to the image processing webpage;

   The first display module includes:

   a rendering unit, configured to render the AR model data by using a webGL technology to obtain the AR model;

   And a display unit, configured to draw and display the AR model in the image processing webpage.
10. The apparatus according to claim 8, wherein said AR model data includes a vertex shader and a fragment shader, said vertex shader being program code for rendering a shape vertex of said AR model, said A fragment shader is program code for rendering colors and/or textures of the AR model;

    The rendering unit is configured to:

    Calling the image processor GPU through the webGL technology;

    The AR model is rendered by running the vertex shader and the fragment shader through the GPU.
11. An image processing apparatus, characterized in that the apparatus comprises:

    a fourth receiving module, configured to receive a target face image of the target face uploaded by the terminal;

    a second receiving module, configured to receive first image data corresponding to the original image sent by the terminal;

    a third sending module, configured to send, when the target image includes the target human face, augmented reality AR model data, where the terminal is configured to render and display at least one AR model according to the AR model data. The AR model is used to display an image processing effect;

    a third receiving module, configured to receive a selection signal sent by the terminal to the target AR model;

    a processing module, configured to perform image processing on the target human face in the original image according to image processing parameters corresponding to the target AR model;

    a fourth sending module, configured to send second image data to the terminal, where the second image data is image data of the original image after image processing, and the terminal is configured to render the second image data display.
12. The device according to claim 11, wherein the second receiving module is configured to:

    Receiving, by the image processing webpage, the first image data sent by the terminal, where the image processing webpage supports the webpage graphics library webGL technology, and the terminal accesses the image processing webpage through a browser supporting the webGL technology, Transmitting the first image data.
13. The device according to claim 11 or 12, wherein the device further comprises:

    a storage module, configured to store the first image data into a buffer pool;

    a first reading module, configured to enable the first thread to read the first image data from the buffer pool;

    An identification module, configured to identify, according to the target face image, whether the target face is included in the original image;

    The device further includes:

    a second reading module, configured to enable the second thread to read the first image data from the buffer pool.
14. The device according to claim 13, wherein the third sending module comprises:

    a recognition unit, configured to identify a facial feature of the target human face in the original image by a predetermined image recognition technology, the facial feature including at least one of a skin color, a face shape, or a face organ size;

    a searching unit, configured to search, according to the facial features of the target human face, a matching candidate AR model from an AR model database, where the similarity of the facial features of the target facial face of the candidate AR model is greater than a threshold ;

    And a sending unit, configured to send, to the terminal, AR model data corresponding to the candidate AR model.
15. A terminal, comprising: a processor and a memory, wherein the memory stores at least one instruction loaded by the processor and executed to implement the method of any one of claims 1 to 3. The image display method.
16. A computer readable storage medium, characterized in that the storage medium stores at least one instruction loaded by a processor and executed to implement the image display method according to any one of claims 1 to 3.
17. A server, comprising: a processor and a memory, wherein the memory stores at least one instruction loaded by the processor and executed to implement the method of any one of claims 4 to 7. Image processing method.
18. A computer readable storage medium, characterized in that the storage medium stores at least one instruction loaded by a processor and executed to implement the image processing method according to any one of claims 4 to 7.

Images