WO2018010700A1 - Image processing method and device - Google Patents

Image processing method and device Download PDF

Info

Publication number
WO2018010700A1
WO2018010700A1 PCT/CN2017/099414 CN2017099414W WO2018010700A1 WO 2018010700 A1 WO2018010700 A1 WO 2018010700A1 CN 2017099414 W CN2017099414 W CN 2017099414W WO 2018010700 A1 WO2018010700 A1 WO 2018010700A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
terminal
central office
virtual
face
Prior art date
Application number
PCT/CN2017/099414
Other languages
French (fr)
Chinese (zh)
Inventor
陈军
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2018010700A1 publication Critical patent/WO2018010700A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/40—Network security protocols
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/14—Systems for two-way working
    • H04N7/15—Conference systems

Definitions

  • the present application relates to, but is not limited to, the field of communications, and in particular, to an image processing method and apparatus.
  • Video communication is becoming more and more popular, and video privacy issues are highlighted. For example, you don't want the other party to judge your location through your own scene. For example, you don't want the other party to see that you are not wearing clothes.
  • the traditional form of multi-party video communication is multi-window, one end of each window, can not be expressed as everyone in a venue.
  • the embodiment of the present application provides an image processing method and device, and the image display conforms to user requirements during video communication.
  • an image processing method including: a terminal acquiring an image; the terminal acquiring a first image, wherein the first image is a pre-filling of the image in addition to a face position An image obtained by the image is set; the terminal and the central office communicate by using the first image.
  • the acquiring, by the terminal, the first image may include one of the following:
  • the terminal identifies a face position from the collected image, and fills a preset image in the image in addition to the face position to obtain the first image;
  • the terminal sends the image to the central office; the terminal receives the first image obtained by the central office according to the image, wherein the central office identifies a face position from the image, and Will A preset image is filled in the image in addition to the face position.
  • the method may further include: the terminal sending the first image to a central office, where the central office is in the first image
  • the human face is supplemented with a pre-stored character body image, a virtual portrait is obtained, the virtual portrait is added to the preset scene image, a virtual venue image is obtained, and the virtual venue image is sent to the terminal; the terminal receives the virtual Venue image.
  • the method may further include: the terminal filling the preset scene image in addition to the location of the face in the image, Obtaining a second image; the terminal transmitting the second image to the central office.
  • an image processing method including: an image transmitted by a central office receiving terminal, wherein a position of the image other than a face position has been filled by a preset image; A pre-stored character body image is added to the face in the image to obtain a virtual portrait.
  • the method may further include: displaying the virtual portrait in a preset scene, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal.
  • an image processing method including: receiving, by an office, an image sent by a terminal, and identifying a face position in the image; the central office supplementing a face in the image Store the image of the person's body and get a virtual portrait.
  • the method may further include: displaying the virtual portrait in a preset scene, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal.
  • an image processing apparatus which is applied to a terminal, including: an acquisition module configured to acquire an image; and an acquisition module configured to acquire a first image, wherein the first image is a An image obtained by filling a preset image in addition to a face position in the image; the communication module is configured to perform communication with the central office by using the first image.
  • the acquiring module may be configured to identify a face position from the collected images, and fill a preset image in the image in addition to the face position to obtain the first An image; or the acquisition module may be configured to send the image to a central office; Determining, according to the image, the first image obtained by the central office, wherein the central office identifies a face position from the image, and fills the preset image in the image except the face position .
  • the acquiring module may be configured to send the first image to the central office after acquiring the first image, wherein the central office supplements the face in the first image
  • the central office supplements the face in the first image
  • the acquiring module may be further configured to: after identifying the face position from the acquired image, filling the image with a preset scene image other than the face position to obtain a second image
  • the acquisition module may be further configured to send the second image to the central office.
  • an image processing apparatus which is applied to a central office, and includes: a first receiving module configured to receive an image sent by a terminal, where the image has a position other than a face position Filled with a preset image; the first processing module is configured to add a pre-stored body image of the person to the face in the image to obtain a virtual portrait.
  • the first processing module may be further configured to: after obtaining the virtual portrait, display the virtual portrait in a preset scene, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
  • an image processing apparatus which is applied to a central office, and includes: a second receiving module configured to receive an image sent by the terminal and identify a face position in the image; and a second processing module And configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
  • the second processing module may be further configured to: after obtaining the virtual portrait, display the virtual portrait in a preset scene, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
  • a storage medium is also provided.
  • the storage medium is configured to store program code for performing: the terminal acquiring an image; the terminal acquiring the first image, wherein the first image is to fill the preset image in addition to the face position in the image The obtained image; the terminal and the central office communicate by using the first image.
  • the storage medium is further configured to store program code for performing the step of: receiving, by the central office, an image transmitted by the terminal, wherein the location of the image other than the location of the face has been filled with the preset image; The central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait.
  • the storage medium is further configured to store program code for performing the following steps: the central office receives an image transmitted by the terminal, and identifies a face position in the image; the central office is a person in the image The face is complemented with a pre-stored body image to obtain a virtual portrait.
  • the terminal or the central office recognizes the location of the face, and fills the preset image with the location other than the location of the face, so that when the terminal and the central office perform image display, only The location of the face is displayed, and there is not much environmental description to protect user privacy.
  • the central office can also add a face to a preset scene for display, so that the image display meets the user's needs during video communication, and the effect of flexibly setting the displayed image according to the user's needs is realized.
  • FIG. 1 is a block diagram showing the hardware structure of a mobile terminal that runs an image processing method according to an embodiment of the present application
  • FIG. 2 is a flowchart 1 of an image processing method according to an embodiment of the present application.
  • FIG. 3 is a second flowchart of an image processing method according to an embodiment of the present application.
  • FIG. 4 is a third flowchart of an image processing method according to an embodiment of the present application.
  • Figure 5 is a schematic diagram of a screen display portrait mode
  • FIG. 6 is an exemplary schematic diagram 1 of a screen display portrait mode according to an embodiment of the present application.
  • FIG. 7 is an exemplary schematic diagram 2 of a screen display portrait mode according to an embodiment of the present application.
  • FIG. 8 is a structural block diagram of an image processing apparatus applied to a terminal according to an embodiment of the present application.
  • FIG. 9 is a structural block diagram 1 of an image processing apparatus applied to a central office according to an embodiment of the present application.
  • FIG. 10 is a structural block diagram 2 of an image processing apparatus applied to a central office according to an embodiment of the present application.
  • the central office is the party that provides terminal access, such as telecommunications bureaus, network providers, and so on.
  • FIG. 1 is a block diagram of a hardware structure of a mobile terminal running an image processing method according to an embodiment of the present application.
  • the mobile terminal 10 may include one or more (only in the figure).
  • a processor 102 is shown (the processor 102 may include, but is not limited to, a processing device such as a microprocessor (Microcontroller Unit) or a programmable logic device (FPGA)), and a memory for storing data. 104.
  • a transmission device 106 for communication functions. It will be understood by those skilled in the art that the structure shown in FIG. 1 is merely illustrative and does not limit the structure of the above electronic device.
  • the mobile terminal 10 may also include more or fewer components than those shown in FIG. 1, or have a different configuration than that shown in FIG.
  • the memory 104 can be configured as a software program and a module for storing application software, such as program instructions/modules corresponding to an image processing method in the embodiment, and the processor 102 executes by executing a software program and a module stored in the memory 104.
  • application software such as program instructions/modules corresponding to an image processing method in the embodiment
  • the processor 102 executes by executing a software program and a module stored in the memory 104.
  • Various functional applications and data processing, that is, the above image processing methods are implemented.
  • Memory 104 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 104 can include memory remotely located relative to processor 102, which can be connected to mobile terminal 10 over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • Transmission device 106 is configured to receive or transmit data via a network.
  • the network instance described above may include a wireless network provided by a communication provider of the mobile terminal 10.
  • the transmission device 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet.
  • NIC Network Interface Controller
  • pass The transmission device 106 can be a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • RF Radio Frequency
  • FIG. 2 is a flowchart 1 of an image processing method according to an embodiment of the present application. As shown in FIG. 2, the process includes the following steps:
  • Step S202 the terminal collects an image.
  • Step S204 the terminal acquires a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
  • Step S206 the terminal and the central office use the first image to communicate.
  • the terminal collects an image, acquires a first image that has been filled by the preset image, uses the first image to communicate with the central office, and performs a session on the network, so that the image display conforms to the user's needs during video communication, and the user is implemented according to the user. Flexibly set the effect of the displayed image.
  • the execution body of the above steps may be a mobile terminal or the like, but is not limited thereto.
  • the terminal identifies a face position from the acquired image, and fills a preset image in the image in addition to the face position to obtain the first image;
  • the terminal sends the image to the central office; the terminal receives the first image obtained by the central office according to the image, wherein the central office identifies the location of the face from the image, and the face is removed from the image
  • the preset image is filled outside the location.
  • the face recognition algorithm is used when recognizing the face position in the image. What is described in the above embodiments is that the position of the face is recognized, and the position other than the face is filled, similar to the mosaic of the body part of the person.
  • the first image is added to the preset. In the scene, a virtual meeting site is formed.
  • the terminal sends the first image to the central office, where the central office adds a pre-stored human body image to the human face in the first image to obtain a virtual portrait.
  • the face is first filled with a body image for the face, which can be a formal dress, and then the image after the body is added to the preset scene image to obtain a virtual scene image, which can be a meeting scene or the like.
  • the terminal receives the virtual conference site image.
  • the virtual portrait is added to the preset scene image, and the image overlay technology may be used to replace the virtual portrait copy to the corresponding position of the virtual scene.
  • the terminal after the terminal identifies the location of the face from the acquired image, the terminal fills the preset scene image with the image in addition to the location of the face to obtain a second image; the terminal sends the second image to Bureau.
  • the foregoing embodiment describes another method of populating a preset scene, and the step of populating the preset scene is performed by the terminal.
  • FIG. 3 is a second flowchart of an image processing method according to an embodiment of the present application. As shown in FIG. 3, the steps are as follows:
  • Step S302 the central office receives an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
  • step S304 the central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait.
  • the virtual portrait is displayed in a preset scene to obtain a virtual conference site image, and the virtual conference site image is sent to the terminal.
  • FIG. 4 is a third flowchart of an image processing method according to an embodiment of the present application. As shown in FIG. 4, the steps are as follows:
  • the central office receives an image sent by the terminal, and identifies a location of the face in the image.
  • the central office adds a pre-stored human body image to the face in the image to obtain a virtual portrait.
  • the virtual portrait is displayed in a preset scene to obtain a virtual conference site image, and the virtual conference site image is sent to the terminal.
  • the first step after the terminal collects the image, the face recognition algorithm is used to identify the face position;
  • Step 2 Fill the part outside the face with specific data, such as filled with blue;
  • the third step encoding the image data that has been filled in the background, and then sending it to the central office;
  • the fourth step according to the face data extracted by all the terminals, the central office fills each person's face with the body image of the person, and puts all the added characters in a scene image to form a virtual meeting place image;
  • Step 5 encoding the virtual conference site image data formed in the fourth step, and then transmitting the data to the terminal;
  • Step 6 After the terminal receives the image, it decodes and sees the virtual site image.
  • Step 1 After the terminal collects the image, it encodes it and sends it to the central office;
  • Step 2 The central office decodes the data sent by the terminal and decodes it into video data.
  • the third step the central office extracts the face data by using the face recognition algorithm in the video data obtained in the second step;
  • the fourth step according to the extracted face data, the central office fills each person's face with the body image of the person, and puts all the added characters in a scene image to form a virtual meeting place image;
  • Step 5 encoding the virtual conference site image data formed in the fourth step, and then transmitting the data to the terminal;
  • Step 6 After the terminal receives the image, it decodes and sees the virtual site image.
  • the first step after the terminal collects the image, the face recognition algorithm is used to identify the face position;
  • Step 2 Fill the part other than the face with the preset scene, such as filling the pre-shooting scene that was shot in advance;
  • Step 3 Encode the image data that has been filled in the background and send it to the remote end.
  • the telepresence environment uses a large TV display, adjusts the camera layout, and finally restores the human body image with the original human body size to achieve a real sense of communication.
  • FIG. 5 is a schematic diagram of a screen display portrait mode, as shown in FIG. 5, there are two portraits in the screen.
  • FIG. 6 is an exemplary diagram of a screen display portrait mode according to an embodiment of the present application. Schematic 1, as shown in Figure 6, there are multiple portraits in the screen. The processing steps are as follows:
  • Step 1 After the terminal collects the image, the face recognition algorithm is used to identify the face position. There are many face recognition algorithms. The following is the implementation flow of the simplest skin color model algorithm, which is divided into 4 steps:
  • YUV also known as YcrCb
  • YcrCb is a color coding method adopted by European television systems. It belongs to the TV standard PAL.
  • YUV is mainly used to optimize the transmission of color video signals, making it backward compatible with old-fashioned Black and white TV
  • Y is the brightness, which is the gray level value
  • U and V are the chromaticity, which is used to describe the image color and saturation
  • the position of the face is determined by the fact that the width of the Unicom area is close to the size of the face in accordance with the size of the face.
  • Step 2 Fill the part outside the face with a specific color, such as blue.
  • Step 3 Encode the image data that has been filled in the background and send it to the central office.
  • Step 4 The central office will select the face data extracted by all terminals according to the number of people.
  • the single-row portrait is displayed for 3 or less people, and the double-row display for 4 to 6 people. More faces are reduced and placed at the far end. Onlookers.
  • Each person's face is filled with a character body image, and all the filled characters are placed in a scene image to form a virtual meeting place image.
  • FIG. 7 is an exemplary schematic diagram 2 of a screen display portrait mode according to an embodiment of the present application. As shown in FIG. 7 , a virtual conference site image that has been processed by the central office is displayed.
  • Step 5 Encode the virtual conference site image data formed in the fourth step, and then send the data to the terminal.
  • Step 6 After the terminal receives the image, it decodes and sees the virtual site image.
  • FIG. 5 a manner of displaying a portrait in the screen is as shown in FIG. 5.
  • FIG. 6 The manner in which the screen displays a portrait in the exemplary embodiment of the present application is as shown in FIG. 6.
  • Step 1 After the terminal collects the image, it encodes it and sends it to the central office;
  • Step 2 The central office decodes the data sent by the terminal and decodes it into video data.
  • the third step uses the face recognition algorithm to extract the face data in the video data obtained in the second step.
  • face recognition algorithms There are many face recognition algorithms, the following is the simplest skin color model algorithm implementation:
  • the position of the face is determined by the width of the Unicom area conforming to the size of the face and the size of the face.
  • Step 4 The central office will select the face data extracted by all terminals according to the number of people.
  • the single-row portrait is displayed for 3 or less people, and the double-row display for 4 to 6 people. More faces are reduced and placed at the far end. Onlookers.
  • Each face is filled with the body image of the character, and all the filled characters are placed in a scene image to form a virtual meeting place image, as shown in FIG.
  • Step 5 Encode the virtual conference site image data formed in the fourth step, and then send the data to the terminal.
  • Step 6 After the terminal receives the image, it decodes and sees the virtual site image.
  • Solution 3 can be used in the following scenarios. Assume that the end user participates in the video conference without finishing the costumes. By selecting the function of scheme three, the body is replaced with the scene wearing the formal costume. The processing steps are as follows:
  • Step 1 After the terminal collects the image, the face recognition algorithm is used to identify the face position.
  • face recognition algorithms There are many face recognition algorithms, the following is the simplest skin color model algorithm implementation:
  • the position of the face is determined by the fact that the width of the Unicom area is close to the size of the face in accordance with the size of the face.
  • Step 2 Scale the face image to a custom size
  • the third step filling the zoomed face into a previously photographed scene, such as a costume scene;
  • Step 4 Encode the filled dress scene and send it to the remote end.
  • the embodiment further provides an image processing device, which is used to implement the above-mentioned embodiments and exemplary embodiments, and has not been described again.
  • the term "module” may implement software, hardware, or a combination of software and hardware for a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • FIG. 8 is a structural block diagram of an image processing apparatus applied to a terminal according to an embodiment of the present application. As shown in FIG. 8, the apparatus includes:
  • the acquiring module 82 is configured to collect an image
  • the obtaining module 84 is connected to the collecting module 82 and configured to acquire a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
  • the communication module 86 is connected to the acquisition module 84 and configured to communicate with the central office by using the first image.
  • the obtaining module 84 may be configured to identify a face position from the acquired image, and fill the preset image in the image in addition to the face position to obtain the first image; or
  • the obtaining module 84 may be configured to send the image to the central office; receive the first image obtained by the central office according to the image, where the central office identifies the location of the face from the image, and divides the image The preset image is filled outside the face position.
  • the obtaining module 84 may be further configured to send the first image to the central office after acquiring the first image, wherein the central office supplements the face in the first image with a pre-stored character body image Obtaining a virtual portrait, adding the virtual portrait to a preset scene image, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal;
  • the obtaining module 84 is further configured to receive the virtual meeting site image.
  • the acquiring module 84 may be further configured to: after the terminal identifies the location of the face from the acquired image, fill the preset scene image with the image other than the location of the face to obtain a second image;
  • the acquisition module 84 can also be configured to send the second image to the central office.
  • FIG. 9 is a structural block diagram 1 of an image processing apparatus applied to a central office according to an embodiment of the present application. As shown in FIG. 9, the apparatus includes:
  • the first receiving module 92 is configured to receive an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
  • the first processing module 94 is connected to the first receiving module 92 and configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
  • the first processing module 94 may be configured to display the virtual portrait in a preset scene after the virtual portrait is obtained, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
  • FIG. 10 is a structural block diagram 2 of an image processing apparatus applied to a central office according to an embodiment of the present application. As shown in FIG. 10, the apparatus includes:
  • the second receiving module 1002 is configured to receive an image sent by the terminal, and identify a location of the face in the image;
  • the second processing module 1004 is connected to the second receiving module 1002 and configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
  • the second processing module 1004 is further configured to display the virtual portrait in a preset scene after obtaining the virtual portrait, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
  • modules may be implemented by software or hardware.
  • the foregoing may be implemented by, but not limited to, by the same processor; or by different processors.
  • the embodiment of the present application also provides a storage medium.
  • the above storage medium may be configured to store program code for performing the following steps:
  • the terminal acquires a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
  • the terminal and the central office use the first image to communicate.
  • the storage medium may also be arranged to store program code for performing the following steps:
  • the central office receives an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
  • the central office adds a pre-stored body image of the person in the image to obtain a virtual portrait.
  • the storage medium may also be arranged to store program code for performing the following steps:
  • the central office receives an image sent by the terminal, and identifies a location of the face in the image.
  • the central office adds a pre-stored body image of the person in the image to obtain a virtual portrait.
  • the foregoing storage medium may include, but not limited to, a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • mobile hard disk a magnetic disk
  • magnetic disk a magnetic disk
  • optical disk a variety of media that can store program code.
  • the processor executes the method steps described in the above embodiments according to the program code stored in the storage medium.
  • computer storage medium includes volatile and nonvolatile, implemented in any method or technology for storing information, such as computer readable instructions, data structures, program modules or other data. Sex, removable and not Remove the media.
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridge, magnetic tape, magnetic disk storage or other magnetic storage device, or may Any other medium used to store the desired information and that can be accessed by the computer.
  • communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and can include any information delivery media. .
  • the embodiment of the present application provides an image processing method and device, which realizes an effect of flexibly setting an image displayed according to user requirements.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Multimedia (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Processing Or Creating Images (AREA)
  • Image Processing (AREA)

Abstract

An image processing method comprises: a terminal acquiring an image; the terminal obtaining a first image, wherein the first image is obtained by filling regions in the image other than a region where a face is located with a preset image; and the terminal and a local side using the first image to conduct communication.

Description

图像处理方法及装置Image processing method and device 技术领域Technical field
本申请涉及但不限于通信领域，尤其涉及一种图像处理方法及装置。The present application relates to, but is not limited to, the field of communications, and in particular, to an image processing method and apparatus.
背景技术Background technique
视频通信越来越普及，视频隐私问题就凸显出来，比如，不想对方通过自己的场景判断出自己所在地，比如，不想对方看到自己没穿衣服。Video communication is becoming more and more popular, and video privacy issues are highlighted. For example, you don't want the other party to judge your location through your own scene. For example, you don't want the other party to see that you are not wearing clothes.
另外，多方视频通信的表现形式上，传统做法是多窗口，每个窗口一个端，无法表现成大家在一个会场的样子。In addition, the traditional form of multi-party video communication, the traditional approach is multi-window, one end of each window, can not be expressed as everyone in a venue.
针对视频通信时图像显示不符合用户需求的问题，目前还没有有效的解决方案。There is no effective solution for the problem that the image display does not meet the user's needs during video communication.
发明概述Summary of invention
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.
本申请实施例提供了一种图像处理方法及装置，实现视频通信时图像显示符合用户需求。The embodiment of the present application provides an image processing method and device, and the image display conforms to user requirements during video communication.
根据本申请的一个方面，提供了一种图像处理方法，包括：终端采集图像；所述终端获取第一图像，其中，所述第一图像为将所述图像中除人脸位置之外填充预设图像得到的图像；所述终端与局端采用所述第一图像进行通信。According to an aspect of the present application, an image processing method is provided, including: a terminal acquiring an image; the terminal acquiring a first image, wherein the first image is a pre-filling of the image in addition to a face position An image obtained by the image is set; the terminal and the central office communicate by using the first image.
在示例性实施方式中，所述终端获取第一图像可以包括以下之一：In an exemplary embodiment, the acquiring, by the terminal, the first image may include one of the following:
所述终端从采集的所述图像中识别出人脸位置，将所述图像中除所述人脸位置之外填充预设图像，得到所述第一图像；The terminal identifies a face position from the collected image, and fills a preset image in the image in addition to the face position to obtain the first image;
所述终端将所述图像发送到局端；所述终端接收所述局端依据所述图像得到的所述第一图像，其中，所述局端从所述图像中识别出人脸位置，并将 所述图像中除所述人脸位置之外填充预设图像。The terminal sends the image to the central office; the terminal receives the first image obtained by the central office according to the image, wherein the central office identifies a face position from the image, and Will A preset image is filled in the image in addition to the face position.
在示例性实施方式中，在所述终端获取第一图像之后，上述方法还可以包括：所述终端将所述第一图像发送到局端，其中，所述局端为所述第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将所述虚拟人像添加至预设场景图像，得到虚拟会场图像，并将所述虚拟会场图像发送至终端；所述终端接收所述虚拟会场图像。In an exemplary embodiment, after the acquiring the first image by the terminal, the method may further include: the terminal sending the first image to a central office, where the central office is in the first image The human face is supplemented with a pre-stored character body image, a virtual portrait is obtained, the virtual portrait is added to the preset scene image, a virtual venue image is obtained, and the virtual venue image is sent to the terminal; the terminal receives the virtual Venue image.
在示例性实施方式中，所述终端从采集的所述图像中识别出人脸位置之后，上述方法还可以包括：所述终端将所述图像中除人脸位置之外填充预设场景图像，得到第二图像；所述终端将所述第二图像发送到局端。In an exemplary embodiment, after the terminal identifies the location of the face from the collected image, the method may further include: the terminal filling the preset scene image in addition to the location of the face in the image, Obtaining a second image; the terminal transmitting the second image to the central office.
根据本申请的另一个方面，提供了一种图像处理方法，包括：局端接收终端发送的图像，其中，所述图像除人脸位置之外的位置已经被预设图像填充；所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。According to another aspect of the present application, an image processing method is provided, including: an image transmitted by a central office receiving terminal, wherein a position of the image other than a face position has been filled by a preset image; A pre-stored character body image is added to the face in the image to obtain a virtual portrait.
在示例性实施方式中，在得到虚拟人像之后，上述方法还可以包括：将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。In an exemplary embodiment, after the virtual portrait is obtained, the method may further include: displaying the virtual portrait in a preset scene, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal.
根据本申请的另一个方面，提供了一种图像处理方法，包括：局端接收终端发送的图像，并识别所述图像中人脸位置；所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。According to another aspect of the present application, an image processing method is provided, including: receiving, by an office, an image sent by a terminal, and identifying a face position in the image; the central office supplementing a face in the image Store the image of the person's body and get a virtual portrait.
在示例性实施方式中，在得到虚拟人像之后，上述方法还可以包括：将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。In an exemplary embodiment, after the virtual portrait is obtained, the method may further include: displaying the virtual portrait in a preset scene, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal.
根据本申请的另一个方面，提供了一种图像处理装置，应用于终端，包括：采集模块，配置为采集图像；获取模块，配置为获取第一图像，其中，所述第一图像为将所述图像中除人脸位置之外填充预设图像得到的图像；通信模块，配置为采用所述第一图像与局端进行通信。According to another aspect of the present application, an image processing apparatus is provided, which is applied to a terminal, including: an acquisition module configured to acquire an image; and an acquisition module configured to acquire a first image, wherein the first image is a An image obtained by filling a preset image in addition to a face position in the image; the communication module is configured to perform communication with the central office by using the first image.
在示例性实施方式中，所述获取模块可以配置为从采集的所述图像中识别出人脸位置，将所述图像中除所述人脸位置之外填充预设图像，得到所述第一图像；或者，所述获取模块可以配置为将所述图像发送到局端；接收所 述局端依据所述图像得到的所述第一图像，其中，所述局端从所述图像中识别出人脸位置，并将所述图像中除所述人脸位置之外填充预设图像。In an exemplary embodiment, the acquiring module may be configured to identify a face position from the collected images, and fill a preset image in the image in addition to the face position to obtain the first An image; or the acquisition module may be configured to send the image to a central office; Determining, according to the image, the first image obtained by the central office, wherein the central office identifies a face position from the image, and fills the preset image in the image except the face position .
在示例性实施方式中，所述获取模块可以配置为在获取第一图像之后，将所述第一图像发送到局端，其中，所述局端为所述第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将所述虚拟人像添加至预设场景图像，得到虚拟会场图像，并将所述虚拟会场图像发送至终端；所述获取模块还可以配置为接收所述虚拟会场图像。In an exemplary embodiment, the acquiring module may be configured to send the first image to the central office after acquiring the first image, wherein the central office supplements the face in the first image The stored human body image, the virtual portrait is obtained, the virtual portrait is added to the preset scene image, the virtual venue image is obtained, and the virtual venue image is sent to the terminal; the obtaining module may be further configured to receive the virtual Venue image.
在示例性实施方式中，所述获取模块还可以配置为在从采集的所述图像中识别出人脸位置之后，将所述图像除人脸位置之外填充预设场景图像，得到第二图像；所述获取模块还可以配置为将所述第二图像发送到局端。In an exemplary embodiment, the acquiring module may be further configured to: after identifying the face position from the acquired image, filling the image with a preset scene image other than the face position to obtain a second image The acquisition module may be further configured to send the second image to the central office.
根据本申请的另一个方面，提供了一种图像处理装置，应用于局端，包括：第一接收模块，配置为接收终端发送的图像，其中，所述图像除人脸位置之外的位置已经被预设图像填充；第一处理模块，配置为给所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。According to another aspect of the present application, an image processing apparatus is provided, which is applied to a central office, and includes: a first receiving module configured to receive an image sent by a terminal, where the image has a position other than a face position Filled with a preset image; the first processing module is configured to add a pre-stored body image of the person to the face in the image to obtain a virtual portrait.
在示例性实施方式中，所述第一处理模块还可以配置为在得到虚拟人像之后，将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。In an exemplary embodiment, the first processing module may be further configured to: after obtaining the virtual portrait, display the virtual portrait in a preset scene, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
根据本申请的另一个方面，提供了一种图像处理装置，应用于局端，包括：第二接收模块，配置为接收终端发送的图像，并识别所述图像中人脸位置；第二处理模块，配置为给所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。According to another aspect of the present application, an image processing apparatus is provided, which is applied to a central office, and includes: a second receiving module configured to receive an image sent by the terminal and identify a face position in the image; and a second processing module And configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
在示例性实施方式中，所述第二处理模块还可以配置为在得到虚拟人像之后，将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。In an exemplary embodiment, the second processing module may be further configured to: after obtaining the virtual portrait, display the virtual portrait in a preset scene, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
根据本申请的又一个方面，还提供了一种存储介质。该存储介质设置为存储用于执行以下步骤的程序代码：终端采集图像；所述终端获取第一图像，其中，所述第一图像为将所述图像中除人脸位置之外填充预设图像得到的图像；所述终端与局端采用所述第一图像进行通信。 According to still another aspect of the present application, a storage medium is also provided. The storage medium is configured to store program code for performing: the terminal acquiring an image; the terminal acquiring the first image, wherein the first image is to fill the preset image in addition to the face position in the image The obtained image; the terminal and the central office communicate by using the first image.
在示例性实施方式中，存储介质还设置为存储用于执行以下步骤的程序代码：局端接收终端发送的图像，其中，所述图像除人脸位置之外的位置已经被预设图像填充；所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。In an exemplary embodiment, the storage medium is further configured to store program code for performing the step of: receiving, by the central office, an image transmitted by the terminal, wherein the location of the image other than the location of the face has been filled with the preset image; The central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait.
在示例性实施方式中，存储介质还设置为存储用于执行以下步骤的程序代码：局端接收终端发送的图像，并识别所述图像中人脸位置；所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。In an exemplary embodiment, the storage medium is further configured to store program code for performing the following steps: the central office receives an image transmitted by the terminal, and identifies a face position in the image; the central office is a person in the image The face is complemented with a pre-stored body image to obtain a virtual portrait.
通过本申请，终端在采集到图像之后，由终端或者局端识别出人脸位置，并将除人脸位置之外的地方填充预设图像，如此，在终端与局端进行图像显示时，只显示了人脸位置，没有过多的环境描写，保护了用户隐私。示例性地，局端还可以将人脸添加到预设场景下进行显示，使得视频通信时图像显示符合用户需求，实现了依据用户需求灵活设置显示的图像的效果。Through the application, after the terminal collects the image, the terminal or the central office recognizes the location of the face, and fills the preset image with the location other than the location of the face, so that when the terminal and the central office perform image display, only The location of the face is displayed, and there is not much environmental description to protect user privacy. For example, the central office can also add a face to a preset scene for display, so that the image display meets the user's needs during video communication, and the effect of flexibly setting the displayed image according to the user's needs is realized.
在阅读并理解了附图和详细描述后，可以明白其他方面。Other aspects will be apparent upon reading and understanding the drawings and detailed description.
附图概述BRIEF abstract
图1是运行本申请实施例的一种图像处理方法的移动终端的硬件结构框图；1 is a block diagram showing the hardware structure of a mobile terminal that runs an image processing method according to an embodiment of the present application;
图2是根据本申请实施例的一种图像处理方法的流程图一；2 is a flowchart 1 of an image processing method according to an embodiment of the present application;
图3是根据本申请实施例的一种图像处理方法的流程图二；3 is a second flowchart of an image processing method according to an embodiment of the present application;
图4是根据本申请实施例的一种图像处理方法的流程图三；4 is a third flowchart of an image processing method according to an embodiment of the present application;
图5是一种屏幕显示人像方式的示意图；Figure 5 is a schematic diagram of a screen display portrait mode;
图6是根据本申请实施例的屏幕显示人像方式的示例性示意图一；6 is an exemplary schematic diagram 1 of a screen display portrait mode according to an embodiment of the present application;
图7是根据本申请实施例的屏幕显示人像方式的示例性示意图二；FIG. 7 is an exemplary schematic diagram 2 of a screen display portrait mode according to an embodiment of the present application; FIG.
图8是根据本申请实施例的应用于终端的一种图像处理装置的结构框图；FIG. 8 is a structural block diagram of an image processing apparatus applied to a terminal according to an embodiment of the present application; FIG.
图9是根据本申请实施例的应用于局端的图像处理装置的结构框图一；9 is a structural block diagram 1 of an image processing apparatus applied to a central office according to an embodiment of the present application;
图10是根据本申请实施例的应用于局端的图像处理装置的结构框图二。 FIG. 10 is a structural block diagram 2 of an image processing apparatus applied to a central office according to an embodiment of the present application.
详述Detailed
下文中将参考附图并结合实施例来详细说明本申请。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。The present application will be described in detail below with reference to the drawings in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or order.
局端是提供终端接入的一方，比如，电信局、网络供应商等。The central office is the party that provides terminal access, such as telecommunications bureaus, network providers, and so on.
本申请实施例所提供的方法实施例可以在移动终端、计算机终端或者类似的运算装置中执行。以运行在移动终端上为例，图1是运行本申请实施例的一种图像处理方法的移动终端的硬件结构框图，如图1所示，移动终端10可以包括一个或多个(图中仅示出一个)处理器102(处理器102可以包括但不限于微处理器(MCU，Microcontroller Unit)或可编程逻辑器件(FPGA，Field Programmable Gate Array)等的处理装置)、用于存储数据的存储器104、以及用于通信功能的传输装置106。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述电子装置的结构造成限定。例如，移动终端10还可包括比图1中所示更多或者更少的组件，或者具有与图1所示不同的配置。The method embodiments provided by the embodiments of the present application may be implemented in a mobile terminal, a computer terminal, or the like. 1 is a block diagram of a hardware structure of a mobile terminal running an image processing method according to an embodiment of the present application. As shown in FIG. 1, the mobile terminal 10 may include one or more (only in the figure). A processor 102 is shown (the processor 102 may include, but is not limited to, a processing device such as a microprocessor (Microcontroller Unit) or a programmable logic device (FPGA)), and a memory for storing data. 104. A transmission device 106 for communication functions. It will be understood by those skilled in the art that the structure shown in FIG. 1 is merely illustrative and does not limit the structure of the above electronic device. For example, the mobile terminal 10 may also include more or fewer components than those shown in FIG. 1, or have a different configuration than that shown in FIG.
存储器104可配置为存储应用软件的软件程序以及模块，如本实施例中的一种图像处理方法对应的程序指令/模块，处理器102通过运行存储在存储器104内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的图像处理方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至移动终端10。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。The memory 104 can be configured as a software program and a module for storing application software, such as program instructions/modules corresponding to an image processing method in the embodiment, and the processor 102 executes by executing a software program and a module stored in the memory 104. Various functional applications and data processing, that is, the above image processing methods are implemented. Memory 104 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, memory 104 can include memory remotely located relative to processor 102, which can be connected to mobile terminal 10 over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
传输装置106配置为经由一个网络接收或者发送数据。上述的网络实例可包括移动终端10的通信供应商提供的无线网络。在一个实例中，传输装置106包括一个网络适配器(Network Interface Controller，简称为NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通信。在一个实例中，传 输装置106可以为射频(Radio Frequency，简称为RF)模块，其用于通过无线方式与互联网进行通信。Transmission device 106 is configured to receive or transmit data via a network. The network instance described above may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In one instance, pass The transmission device 106 can be a Radio Frequency (RF) module for communicating with the Internet wirelessly.
在本实施例中提供了一种运行于上述移动终端的图像处理方法，图2是根据本申请实施例的一种图像处理方法的流程图一，如图2所示，该流程包括如下步骤：In the embodiment, an image processing method is performed on the mobile terminal. FIG. 2 is a flowchart 1 of an image processing method according to an embodiment of the present application. As shown in FIG. 2, the process includes the following steps:
步骤S202，终端采集图像；Step S202, the terminal collects an image.
步骤S204，该终端获取第一图像，其中，该第一图像为将该图像中除人脸位置之外填充预设图像得到的图像；Step S204, the terminal acquires a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
步骤S206，该终端与局端采用该第一图像进行通信。Step S206, the terminal and the central office use the first image to communicate.
通过上述步骤，终端采集图像，获取已经被预设图像填充过的第一图像，使用第一图像与局端进行通信，在网络上会话，使得视频通信时图像显示符合用户需求，实现了依据用户灵活设置显示的图像的效果。Through the above steps, the terminal collects an image, acquires a first image that has been filled by the preset image, uses the first image to communicate with the central office, and performs a session on the network, so that the image display conforms to the user's needs during video communication, and the user is implemented according to the user. Flexibly set the effect of the displayed image.
示例性地，上述步骤的执行主体可以为移动终端等，但不限于此。Exemplarily, the execution body of the above steps may be a mobile terminal or the like, but is not limited thereto.
在终端采集到图像之后，在一个示例性实施例中提供了以下两种获取第一图像的方式：After the terminal acquires the image, the following two ways of obtaining the first image are provided in one exemplary embodiment:
该终端从采集的该图像中识别出人脸位置，将该图像中除该人脸位置之外填充预设图像，得到该第一图像；The terminal identifies a face position from the acquired image, and fills a preset image in the image in addition to the face position to obtain the first image;
该终端将该图像发送到局端；该终端接收该局端依据该图像得到的该第一图像，其中，该局端从该图像中识别出人脸位置，并将该图像中除该人脸位置之外填充预设图像。The terminal sends the image to the central office; the terminal receives the first image obtained by the central office according to the image, wherein the central office identifies the location of the face from the image, and the face is removed from the image The preset image is filled outside the location.
在上述实施例中，不论是终端还是局端，识别图像中的人脸位置时采用的是人脸识别算法。上述实施例中记载的都是识别出人脸位置，将除人脸之外的位置进行填充，类似于为人物身体部位打上马赛克，在后续实施例中记载了将第一图像中添加到预设场景之中，形成虚拟会议现场。In the above embodiment, whether it is the terminal or the central office, the face recognition algorithm is used when recognizing the face position in the image. What is described in the above embodiments is that the position of the face is recognized, and the position other than the face is filled, similar to the mosaic of the body part of the person. In the following embodiment, the first image is added to the preset. In the scene, a virtual meeting site is formed.
示例性地，在该终端获取第一图像之后，该终端将该第一图像发送到局端，其中，该局端为该第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将该虚拟人像添加至预设场景图像，得到虚拟会场图像，并将该虚拟会场图像发送至终端。在局端接收到第一图像之后，由于第一图像中只有 人脸，先为人脸补上身体图像，可以是穿正装，然后将补上身体后的图像添加到预设场景图像，得到虚拟场景图像，可以是开会场景等。该终端接收该虚拟会场图像。上述实施例中将虚拟人像添加至预设场景图像，可以采用图像叠加技术，将虚拟人像复制替换到虚拟场景对应位置。Illustratively, after the terminal acquires the first image, the terminal sends the first image to the central office, where the central office adds a pre-stored human body image to the human face in the first image to obtain a virtual portrait. Adding the virtual portrait to the preset scene image, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal. After receiving the first image at the central office, since only the first image The face is first filled with a body image for the face, which can be a formal dress, and then the image after the body is added to the preset scene image to obtain a virtual scene image, which can be a meeting scene or the like. The terminal receives the virtual conference site image. In the above embodiment, the virtual portrait is added to the preset scene image, and the image overlay technology may be used to replace the virtual portrait copy to the corresponding position of the virtual scene.
示例性地，该终端从采集的该图像中识别出人脸位置之后，该终端将该图像除人脸位置之外填充预设场景图像，得到第二图像；该终端将该第二图像发送到局端。上述实施例记载了另一个填充预设场景的方法，由终端执行填充预设场景的步骤。Illustratively, after the terminal identifies the location of the face from the acquired image, the terminal fills the preset scene image with the image in addition to the location of the face to obtain a second image; the terminal sends the second image to Bureau. The foregoing embodiment describes another method of populating a preset scene, and the step of populating the preset scene is performed by the terminal.
上述所有的实施例都是在终端一侧进行描述的，下面从局端一侧进行描述。All of the above embodiments are described on the terminal side, and are described below from the central office side.
图3是根据本申请实施例的一种图像处理方法的流程图二，如图3所示，步骤如下：FIG. 3 is a second flowchart of an image processing method according to an embodiment of the present application. As shown in FIG. 3, the steps are as follows:
步骤S302，局端接收终端发送的图像，其中，该图像除人脸位置之外的位置已经被预设图像填充；Step S302, the central office receives an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
步骤S304，该局端为该图像中人脸补上预存储的人物身体图像，得到虚拟人像。In step S304, the central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait.
示例性地，在得到虚拟人像之后，将该虚拟人像在预设场景显示，得到虚拟会场图像，并将该虚拟会场图像发送至该终端。Exemplarily, after the virtual portrait is obtained, the virtual portrait is displayed in a preset scene to obtain a virtual conference site image, and the virtual conference site image is sent to the terminal.
图4是根据本申请实施例的一种图像处理方法的流程图三，如图4所示，步骤如下：FIG. 4 is a third flowchart of an image processing method according to an embodiment of the present application. As shown in FIG. 4, the steps are as follows:
S402，局端接收终端发送的图像，并识别该图像中人脸位置；S402. The central office receives an image sent by the terminal, and identifies a location of the face in the image.
S404，该局端为该图像中人脸补上预存储的人物身体图像，得到虚拟人像。S404. The central office adds a pre-stored human body image to the face in the image to obtain a virtual portrait.
示例性地，在得到虚拟人像之后，将该虚拟人像在预设场景显示，得到虚拟会场图像，并将该虚拟会场图像发送至该终端。Exemplarily, after the virtual portrait is obtained, the virtual portrait is displayed in a preset scene to obtain a virtual conference site image, and the virtual conference site image is sent to the terminal.
在本申请的一个示例性实施例记载了三种详细方案，下面进行详细描述。Three detailed schemes are described in an exemplary embodiment of the present application, which are described in detail below.
方案一描述如下： Scheme 1 is described as follows:
第一步：终端采集到图像后，用人脸识别算法识别出人脸位置；The first step: after the terminal collects the image, the face recognition algorithm is used to identify the face position;
第二步：将人脸以外的部分用特定数据填充，比如用蓝色填充；Step 2: Fill the part outside the face with specific data, such as filled with blue;
第三步：将背景已填充的图像数据进行编码，然后发送给局端；The third step: encoding the image data that has been filled in the background, and then sending it to the central office;
第四步：局端根据所有终端提取的人脸数据，给每个人脸补上人物身体图像，将所有补好的人物放在一个场景图像中，形成虚拟会场图像；The fourth step: according to the face data extracted by all the terminals, the central office fills each person's face with the body image of the person, and puts all the added characters in a scene image to form a virtual meeting place image;
第五步：将第四步形成的虚拟会场图像数据进行编码，然后发送给终端；Step 5: encoding the virtual conference site image data formed in the fourth step, and then transmitting the data to the terminal;
第六步：终端收到图像后解码看到虚拟会场图像。Step 6: After the terminal receives the image, it decodes and sees the virtual site image.
方案二描述如下：Option 2 is described as follows:
第一步：终端采集到图像后，进行编码，然后发送给局端；Step 1: After the terminal collects the image, it encodes it and sends it to the central office;
第二步：局端将终端发来的数据进行解码，解码成视频数据；Step 2: The central office decodes the data sent by the terminal and decodes it into video data.
第三步：局端在第二步得到的视频数据中用人脸识别算法提取人脸数据；The third step: the central office extracts the face data by using the face recognition algorithm in the video data obtained in the second step;
第四步：局端根据提取的人脸数据，给每个人脸补上人物身体图像，将所有补好的人物放在一个场景图像中，形成虚拟会场图像；The fourth step: according to the extracted face data, the central office fills each person's face with the body image of the person, and puts all the added characters in a scene image to form a virtual meeting place image;
第五步：将第四步形成的虚拟会场图像数据进行编码，然后发送给终端；Step 5: encoding the virtual conference site image data formed in the fourth step, and then transmitting the data to the terminal;
第六步：终端收到图像后解码看到虚拟会场图像。Step 6: After the terminal receives the image, it decodes and sees the virtual site image.
方案三描述如下：Option 3 is described as follows:
第一步：终端采集到图像后，用人脸识别算法识别出人脸位置；The first step: after the terminal collects the image, the face recognition algorithm is used to identify the face position;
第二步：将人脸以外的部分用事先设定好的场景填充，比如填充事先拍摄好的正装场景；Step 2: Fill the part other than the face with the preset scene, such as filling the pre-shooting scene that was shot in advance;
第三步：将背景已填充的图像数据进行编码，然后发送给远端。Step 3: Encode the image data that has been filled in the background and send it to the remote end.
下面对上述三种方案进行详细描述。The above three schemes are described in detail below.
针对方案一，描述如下：For scenario 1, the description is as follows:
先描述下网真环境，网真环境是采用大电视显示，调整摄像头布局，最终以原始人体大小还原人体图像，实现真实交流的现场感。First describe the telepresence environment. The telepresence environment uses a large TV display, adjusts the camera layout, and finally restores the human body image with the original human body size to achieve a real sense of communication.
在网真环境中，图5是一种屏幕显示人像方式的示意图，如图5所示，屏幕内有两个人像。图6是根据本申请实施例的屏幕显示人像方式的示例性 示意图一，如图6所示，屏幕内有多个人像。处理步骤如下：In the telepresence environment, FIG. 5 is a schematic diagram of a screen display portrait mode, as shown in FIG. 5, there are two portraits in the screen. FIG. 6 is an exemplary diagram of a screen display portrait mode according to an embodiment of the present application. Schematic 1, as shown in Figure 6, there are multiple portraits in the screen. The processing steps are as follows:
第一步：终端采集到图像后，用人脸识别算法识别出人脸位置。人脸识别算法很多，以下是最简单的肤色模型算法的实现流程，共分为4步：Step 1: After the terminal collects the image, the face recognition algorithm is used to identify the face position. There are many face recognition algorithms. The following is the implementation flow of the simplest skin color model algorithm, which is divided into 4 steps:
1、输入采集到的YUV数据(YUV亦称YcrCb，是被欧洲电视***所采用的一种颜色编码方法，属于电视标准PAL，YUV主要用于优化彩***信号的传输，使其向后兼容老式黑白电视，Y表示明亮度，也就是灰阶值，而U和V表示的则是色度，作用是描述影像色彩及饱和度)；1. Input the collected YUV data (YUV, also known as YcrCb, is a color coding method adopted by European television systems. It belongs to the TV standard PAL. YUV is mainly used to optimize the transmission of color video signals, making it backward compatible with old-fashioned Black and white TV, Y is the brightness, which is the gray level value, and U and V are the chromaticity, which is used to describe the image color and saturation);
2、通过肤色模型二值化图像，即将非肤色部分置为0，将肤色部分置为1，其中，肤色取值范围可以通过在实际设备中统计学习得到；2. Binarize the image through the skin color model, that is, set the non-skinning part to 0, and set the skin color part to 1, wherein the skin color value range can be obtained by statistical learning in the actual device;
3、调用腐蚀膨胀算法滤波；3. Calling the corrosion expansion algorithm to filter;
4、使用联通区域检测，以联通区域宽符合人脸大小比例接近人脸大小为标准，判断出人脸位置。4. Using the Unicom area detection, the position of the face is determined by the fact that the width of the Unicom area is close to the size of the face in accordance with the size of the face.
第二步：将人脸以外的部分用特定颜色填充，比如蓝色。Step 2: Fill the part outside the face with a specific color, such as blue.
第三步：将背景已填充的图像数据进行编码，然后发送给局端。Step 3: Encode the image data that has been filled in the background and send it to the central office.
第四步：局端将所有终端提取的人脸数据，按照人数选择布局方式，3人以下采用单排人像显示，4至6人采用双排显示，更多的人脸缩小后放在远端围观人群。给每个人脸补上人物身体图像，将所有补好的人物放在一个场景图像中，形成虚拟会场图像。图7是根据本申请实施例的屏幕显示人像方式的示例性示意图二，如图7所示，显示的是已经被局端处理后的虚拟会场图像。Step 4: The central office will select the face data extracted by all terminals according to the number of people. The single-row portrait is displayed for 3 or less people, and the double-row display for 4 to 6 people. More faces are reduced and placed at the far end. Onlookers. Each person's face is filled with a character body image, and all the filled characters are placed in a scene image to form a virtual meeting place image. FIG. 7 is an exemplary schematic diagram 2 of a screen display portrait mode according to an embodiment of the present application. As shown in FIG. 7 , a virtual conference site image that has been processed by the central office is displayed.
第五步：将第四步形成的虚拟会场图像数据进行编码，然后发送给终端。Step 5: Encode the virtual conference site image data formed in the fourth step, and then send the data to the terminal.
第六步：终端收到图像后解码看到虚拟会场图像。Step 6: After the terminal receives the image, it decodes and sees the virtual site image.
针对方案二，描述如下：For scenario two, the description is as follows:
在网真环境中，一种屏幕内显示人像的方式如图5所示，本申请示例性实施例中屏幕显示人像的方式如图6所示。In the telepresence environment, a manner of displaying a portrait in the screen is as shown in FIG. 5. The manner in which the screen displays a portrait in the exemplary embodiment of the present application is as shown in FIG. 6.
处理步骤如下：The processing steps are as follows:
第一步：终端采集到图像后，进行编码，然后发送给局端； Step 1: After the terminal collects the image, it encodes it and sends it to the central office;
第二步：局端将终端发来的数据进行解码，解码成视频数据；Step 2: The central office decodes the data sent by the terminal and decodes it into video data.
第三步：局端在第二步得到的视频数据中用人脸识别算法取出人脸数据。人脸识别算法很多，如下是最简单的肤色模型算法实现：The third step: the central office uses the face recognition algorithm to extract the face data in the video data obtained in the second step. There are many face recognition algorithms, the following is the simplest skin color model algorithm implementation:
1、输入采集到的YUV数据；1. Input the collected YUV data;
2、通过肤色模型二值化图像，即将非肤色部分置为0，将肤色部分置为1，其中，肤色取值范围可以通过在实际设备中统计学习得到；2. Binarize the image through the skin color model, that is, set the non-skinning part to 0, and set the skin color part to 1, wherein the skin color value range can be obtained by statistical learning in the actual device;
3、调用腐蚀膨胀算法滤波；3. Calling the corrosion expansion algorithm to filter;
4、使用联通区域检测，以联通区域宽符合人脸大小比例接近人脸大小为标准，判断出人脸位置；4. Using the Unicom area detection, the position of the face is determined by the width of the Unicom area conforming to the size of the face and the size of the face.
5、根据上面得到的人脸位置，设定人脸边界，取出人脸数据。5. According to the position of the face obtained above, set the face boundary and take out the face data.
第四步：局端将所有终端提取的人脸数据，按照人数选择布局方式，3人以下采用单排人像显示，4至6人采用双排显示，更多的人脸缩小后放在远端围观人群。每个人脸补上人物身体图像，将所有补好的人物放在一个场景图像中，形成虚拟会场图像，如图7所示。Step 4: The central office will select the face data extracted by all terminals according to the number of people. The single-row portrait is displayed for 3 or less people, and the double-row display for 4 to 6 people. More faces are reduced and placed at the far end. Onlookers. Each face is filled with the body image of the character, and all the filled characters are placed in a scene image to form a virtual meeting place image, as shown in FIG.
第五步：将第四步形成的虚拟会场图像数据进行编码，然后发送给终端。Step 5: Encode the virtual conference site image data formed in the fourth step, and then send the data to the terminal.
第六步：终端收到图像后解码看到虚拟会场图像。Step 6: After the terminal receives the image, it decodes and sees the virtual site image.
针对方案三，描述如下：For scenario three, the description is as follows:
方案三可以用于以下场景，假设终端用户没有整理好服装就参加视频会议，通过选用方案三的功能，将身体替换成穿好正装的场景。处理步骤如下：Solution 3 can be used in the following scenarios. Assume that the end user participates in the video conference without finishing the costumes. By selecting the function of scheme three, the body is replaced with the scene wearing the formal costume. The processing steps are as follows:
第一步：终端采集到图像后，用人脸识别算法识别出人脸位置。人脸识别算法很多，如下是最简单的肤色模型算法实现：Step 1: After the terminal collects the image, the face recognition algorithm is used to identify the face position. There are many face recognition algorithms, the following is the simplest skin color model algorithm implementation:
1、输入采集到的YUV数据；1. Input the collected YUV data;
2、通过肤色模型二值化图像，即将非肤色部分置为0，将肤色部分置为1，其中，肤色取值范围可以通过在实际设备中统计学习得到；2. Binarize the image through the skin color model, that is, set the non-skinning part to 0, and set the skin color part to 1, wherein the skin color value range can be obtained by statistical learning in the actual device;
3、调用腐蚀膨胀算法滤波；3. Calling the corrosion expansion algorithm to filter;
4、使用联通区域检测，以联通区域宽符合人脸大小比例接近人脸大小为标准，判断出人脸位置。 4. Using the Unicom area detection, the position of the face is determined by the fact that the width of the Unicom area is close to the size of the face in accordance with the size of the face.
第二步：将人脸图像缩放至定制大小；Step 2: Scale the face image to a custom size;
第三步：将缩放好的人脸填充到事先拍摄好的场景中，例如正装场景中；The third step: filling the zoomed face into a previously photographed scene, such as a costume scene;
第四步：将填充好的正装场景编码后发送给远端。Step 4: Encode the filled dress scene and send it to the remote end.
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，也可以通过硬件，但很多情况下前者是更佳的实施方式。Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform, or by hardware, but in many cases, the former is more Good implementation.
本实施例还提供了一种图像处理装置，该装置用于实现上述实施例及示例性实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件、硬件、或者软件和硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。The embodiment further provides an image processing device, which is used to implement the above-mentioned embodiments and exemplary embodiments, and has not been described again. As used hereinafter, the term "module" may implement software, hardware, or a combination of software and hardware for a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
图8是根据本申请实施例的应用于终端的一种图像处理装置的结构框图，如图8所示，该装置包括：FIG. 8 is a structural block diagram of an image processing apparatus applied to a terminal according to an embodiment of the present application. As shown in FIG. 8, the apparatus includes:
采集模块82，配置为采集图像；The acquiring module 82 is configured to collect an image;
获取模块84，与采集模块82连接，配置为获取第一图像，其中，该第一图像为将该图像中除人脸位置之外填充预设图像得到的图像；The obtaining module 84 is connected to the collecting module 82 and configured to acquire a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
通信模块86，与获取模块84连接，配置为采用该第一图像与局端进行通信。The communication module 86 is connected to the acquisition module 84 and configured to communicate with the central office by using the first image.
示例性地，该获取模块84可以配置为从采集的该图像中识别出人脸位置，将该图像中除该人脸位置之外填充预设图像，得到该第一图像；或者，Exemplarily, the obtaining module 84 may be configured to identify a face position from the acquired image, and fill the preset image in the image in addition to the face position to obtain the first image; or
该获取模块84可以配置为将该图像发送到局端；接收该局端依据该图像得到的该第一图像，其中，该局端从该图像中识别出人脸位置，并将该图像中除该人脸位置之外填充预设图像。The obtaining module 84 may be configured to send the image to the central office; receive the first image obtained by the central office according to the image, where the central office identifies the location of the face from the image, and divides the image The preset image is filled outside the face position.
示例性地，该获取模块84还可以配置为在获取第一图像之后，将该第一图像发送到局端，其中，该局端为该第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将该虚拟人像添加至预设场景图像，得到虚拟会场图像，并将该虚拟会场图像发送至终端；Exemplarily, the obtaining module 84 may be further configured to send the first image to the central office after acquiring the first image, wherein the central office supplements the face in the first image with a pre-stored character body image Obtaining a virtual portrait, adding the virtual portrait to a preset scene image, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal;
该获取模块84还可以配置为接收该虚拟会场图像。 The obtaining module 84 is further configured to receive the virtual meeting site image.
示例性地，该获取模块84还可以配置为在该终端从采集的该图像中识别出人脸位置之后，将该图像除人脸位置之外填充预设场景图像，得到第二图像；For example, the acquiring module 84 may be further configured to: after the terminal identifies the location of the face from the acquired image, fill the preset scene image with the image other than the location of the face to obtain a second image;
该获取模块84还可以配置为将该第二图像发送到局端。The acquisition module 84 can also be configured to send the second image to the central office.
图9是根据本申请实施例的应用于局端的图像处理装置的结构框图一，如图9所示，该装置包括：FIG. 9 is a structural block diagram 1 of an image processing apparatus applied to a central office according to an embodiment of the present application. As shown in FIG. 9, the apparatus includes:
第一接收模块92，配置为接收终端发送的图像，其中，该图像除人脸位置之外的位置已经被预设图像填充；The first receiving module 92 is configured to receive an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
第一处理模块94，与第一接收模块92模块连接，配置为给该图像中人脸补上预存储的人物身体图像，得到虚拟人像。The first processing module 94 is connected to the first receiving module 92 and configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
示例性地，该第一处理模块94还可以配置为在得到虚拟人像之后，将该虚拟人像在预设场景显示，得到虚拟会场图像，并将该虚拟会场图像发送至该终端。For example, the first processing module 94 may be configured to display the virtual portrait in a preset scene after the virtual portrait is obtained, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
图10是根据本申请实施例应用于局端的图像处理装置的结构框图二，如图10所示，该装置包括：FIG. 10 is a structural block diagram 2 of an image processing apparatus applied to a central office according to an embodiment of the present application. As shown in FIG. 10, the apparatus includes:
第二接收模块1002，配置为接收终端发送的图像，并识别该图像中人脸位置；The second receiving module 1002 is configured to receive an image sent by the terminal, and identify a location of the face in the image;
第二处理模块1004，与第二接收模块1002连接，配置为给该图像中人脸补上预存储的人物身体图像，得到虚拟人像。The second processing module 1004 is connected to the second receiving module 1002 and configured to add a pre-stored human body image to the face in the image to obtain a virtual portrait.
示例性地，该第二处理模块1004还可以配置为在得到虚拟人像之后，将该虚拟人像在预设场景显示，得到虚拟会场图像，并将该虚拟会场图像发送至该终端。Exemplarily, the second processing module 1004 is further configured to display the virtual portrait in a preset scene after obtaining the virtual portrait, obtain a virtual conference site image, and send the virtual conference site image to the terminal.
需要说明的是，上述模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：由同一处理器实现；或者，由不同的处理器实现。It should be noted that the above modules may be implemented by software or hardware. For the latter, the foregoing may be implemented by, but not limited to, by the same processor; or by different processors.
本申请实施例还提供了一种存储介质。在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的程序代码：The embodiment of the present application also provides a storage medium. In this embodiment, the above storage medium may be configured to store program code for performing the following steps:
S1，终端采集图像； S1, the terminal collects an image;
S2，该终端获取第一图像，其中，该第一图像为将该图像中除人脸位置之外填充预设图像得到的图像；S2, the terminal acquires a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
S3，该终端与局端采用该第一图像进行通信。S3. The terminal and the central office use the first image to communicate.
示例性地，存储介质还可以设置为存储用于执行以下步骤的程序代码：Illustratively, the storage medium may also be arranged to store program code for performing the following steps:
S4，局端接收终端发送的图像，其中，该图像除人脸位置之外的位置已经被预设图像填充；S4. The central office receives an image sent by the terminal, where the location of the image other than the location of the face has been filled by the preset image;
S5，该局端为该图像中人脸补上预存储的人物身体图像，得到虚拟人像。S5, the central office adds a pre-stored body image of the person in the image to obtain a virtual portrait.
示例性地，存储介质还可以设置为存储用于执行以下步骤的程序代码：Illustratively, the storage medium may also be arranged to store program code for performing the following steps:
S6，局端接收终端发送的图像，并识别该图像中人脸位置；S6. The central office receives an image sent by the terminal, and identifies a location of the face in the image.
S7，该局端为该图像中人脸补上预存储的人物身体图像，得到虚拟人像。S7, the central office adds a pre-stored body image of the person in the image to obtain a virtual portrait.
在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。In this embodiment, the foregoing storage medium may include, but not limited to, a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk. A variety of media that can store program code.
在本实施例中，处理器根据存储介质中已存储的程序代码执行上述实施例记载的方法步骤。In this embodiment, the processor executes the method steps described in the above embodiments according to the program code stored in the storage medium.
本实施例中的示例可以参考上述实施例及示例性实施方式中所描述的示例，本实施例在此不再赘述。For examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and exemplary embodiments, and details are not described herein again.
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、***、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施方式中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些组件或所有组件可以被实施为由处理器，如数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可 移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and functional blocks/units of the methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be composed of several physical The components work together. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer readable medium, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and nonvolatile, implemented in any method or technology for storing information, such as computer readable instructions, data structures, program modules or other data. Sex, removable and not Remove the media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridge, magnetic tape, magnetic disk storage or other magnetic storage device, or may Any other medium used to store the desired information and that can be accessed by the computer. Moreover, it is well known to those skilled in the art that communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and can include any information delivery media. .
以上所述仅为本申请的示例性实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above description is only an exemplary embodiment of the present application, and is not intended to limit the present application, and various changes and modifications may be made to the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application are intended to be included within the scope of the present application.
工业实用性Industrial applicability
本申请实施例提供一种图像处理方法及装置，实现了依据用户需求灵活设置显示的图像的效果。 The embodiment of the present application provides an image processing method and device, which realizes an effect of flexibly setting an image displayed according to user requirements.

Claims (19)

  1. 一种图像处理方法，包括：An image processing method comprising:
    终端采集图像(S202)；The terminal collects an image (S202);
    所述终端获取第一图像，其中，所述第一图像为将所述图像中除人脸位置之外填充预设图像得到的图像(S204)；The terminal acquires a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image (S204);
    所述终端与局端采用所述第一图像进行通信(S206)。The terminal communicates with the central office by using the first image (S206).
  2. 根据权利要求1所述的方法，其中，所述终端获取第一图像(S204)包括以下之一：The method of claim 1, wherein the acquiring the first image by the terminal (S204) comprises one of the following:
    所述终端从采集的所述图像中识别出人脸位置，将所述图像中除所述人脸位置之外填充预设图像，得到所述第一图像；The terminal identifies a face position from the collected image, and fills a preset image in the image in addition to the face position to obtain the first image;
    所述终端将所述图像发送到局端；所述终端接收所述局端依据所述图像得到的所述第一图像，其中，所述局端从所述图像中识别出人脸位置，并将所述图像中除所述人脸位置之外填充预设图像。The terminal sends the image to the central office; the terminal receives the first image obtained by the central office according to the image, wherein the central office identifies a face position from the image, and A preset image is filled in the image in addition to the face position.
  3. 根据权利要求2所述的方法，在所述终端获取第一图像(S204)之后，所述方法还包括：The method according to claim 2, after the terminal acquires the first image (S204), the method further includes:
    所述终端将所述第一图像发送到局端，其中，所述局端为所述第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将所述虚拟人像添加至预设场景图像，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端；Sending, by the terminal, the first image to the central office, where the central office adds a pre-stored human body image to the face in the first image, obtains a virtual portrait, and adds the virtual portrait to the pre-prepared Setting a scene image, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal;
    所述终端接收所述虚拟会场图像。The terminal receives the virtual conference site image.
  4. 根据权利要求2所述的方法，所述终端从采集的所述图像中识别出人脸位置之后，所述方法还包括：The method of claim 2, after the terminal identifies the location of the face from the acquired image, the method further includes:
    所述终端将所述图像中除人脸位置之外填充预设场景图像，得到第二图像；The terminal fills the preset scene image in addition to the face position in the image to obtain a second image;
    所述终端将所述第二图像发送到局端。The terminal transmits the second image to the central office.
  5. 一种图像处理方法，包括：An image processing method comprising:
    局端接收终端发送的图像，其中，所述图像除人脸位置之外的位置已经被预设图像填充(S302)； The central office receives an image sent by the terminal, where the position of the image other than the face position has been filled by the preset image (S302);
    所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像(S304)。The central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait (S304).
  6. 根据权利要求5所述的方法，在得到虚拟人像之后，所述方法还包括：将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。The method of claim 5, after the virtual portrait is obtained, the method further comprises: displaying the virtual portrait in a preset scene, obtaining a virtual venue image, and transmitting the virtual venue image to the terminal.
  7. 一种图像处理方法，包括：An image processing method comprising:
    局端接收终端发送的图像，并识别所述图像中人脸位置(S402)；Receiving, by the central office, an image sent by the terminal, and identifying a face position in the image (S402);
    所述局端为所述图像中人脸补上预存储的人物身体图像，得到虚拟人像(S404)。The central office adds a pre-stored character body image to the face in the image to obtain a virtual portrait (S404).
  8. 根据权利要求7所述的方法，在得到虚拟人像之后，所述方法还包括：将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。The method of claim 7, after the virtual portrait is obtained, the method further comprises: displaying the virtual portrait in a preset scene, obtaining a virtual conference site image, and transmitting the virtual conference site image to the terminal.
  9. 一种图像处理装置，应用于终端，包括：An image processing apparatus is applied to a terminal, including:
    采集模块(82)，配置为采集图像；An acquisition module (82) configured to acquire an image;
    获取模块(84)，配置为获取第一图像，其中，所述第一图像为将所述图像中除人脸位置之外填充预设图像得到的图像；An obtaining module (84) configured to acquire a first image, where the first image is an image obtained by filling a preset image in addition to a face position in the image;
    通信模块(86)，配置为采用所述第一图像与局端进行通信。The communication module (86) is configured to communicate with the central office using the first image.
  10. 根据权利要求9所述的装置，其中，所述获取模块(84)配置为从采集的所述图像中识别出人脸位置，将所述图像中除所述人脸位置之外填充预设图像，得到所述第一图像；或者，The apparatus according to claim 9, wherein the acquisition module (84) is configured to recognize a face position from the acquired images, and to fill a predetermined image in the image in addition to the face position Getting the first image; or,
    所述获取模块(84)配置为将所述图像发送到局端；接收所述局端依据所述图像得到的所述第一图像，其中，所述局端从所述图像中识别出人脸位置，并将所述图像中除所述人脸位置之外填充预设图像。The obtaining module (84) is configured to send the image to the central office; receive the first image obtained by the central office according to the image, wherein the central office identifies a human face from the image Positioning and filling a predetermined image in the image in addition to the face position.
  11. 根据权利要求10所述的装置，其中，所述获取模块(84)还配置为在获取第一图像之后，将所述第一图像发送到局端，其中，所述局端为所述第一图像中人脸补上预存储的人物身体图像，得到虚拟人像，将所述虚拟人像添加至预设场景图像，得到虚拟会场图像，并将所述虚拟会场图像发送至终端； The apparatus according to claim 10, wherein the obtaining module (84) is further configured to send the first image to a central office after acquiring the first image, wherein the central office is the first The virtual face is added to the pre-stored character body image to obtain a virtual portrait, and the virtual portrait is added to the preset scene image to obtain a virtual conference site image, and the virtual conference site image is sent to the terminal;
    所述获取模块(84)还配置为接收所述虚拟会场图像。The obtaining module (84) is further configured to receive the virtual venue image.
  12. 根据权利要求10所述的装置，其中，所述获取模块(84)还配置为在从采集的所述图像中识别出人脸位置之后，将所述图像除人脸位置之外填充预设场景图像，得到第二图像；The apparatus of claim 10, wherein the acquisition module (84) is further configured to fill the image with a preset scene other than a face position after recognizing a face position from the acquired image Image, obtaining a second image;
    所述获取模块(84)还配置为将所述第二图像发送到局端。The acquisition module (84) is further configured to send the second image to the central office.
  13. 一种图像处理装置，应用于局端，包括：An image processing apparatus is applied to a central office, including:
    第一接收模块(92)，配置为接收终端发送的图像，其中，所述图像除人脸位置之外的位置已经被预设图像填充；The first receiving module (92) is configured to receive an image sent by the terminal, where the position of the image other than the face position has been filled by the preset image;
    第一处理模块(94)，配置为给所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。The first processing module (94) is configured to add a pre-stored character body image to the face in the image to obtain a virtual portrait.
  14. 根据权利要求13所述的装置，其中，所述第一处理模块(94)还配置为在得到虚拟人像之后，将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。The apparatus according to claim 13, wherein the first processing module (94) is further configured to display the virtual portrait in a preset scene after obtaining the virtual portrait, to obtain a virtual venue image, and to The venue image is sent to the terminal.
  15. 一种图像处理装置，应用于局端，包括：An image processing apparatus is applied to a central office, including:
    第二接收模块(1002)，配置为接收终端发送的图像，并识别所述图像中人脸位置；a second receiving module (1002) configured to receive an image sent by the terminal and identify a location of the face in the image;
    第二处理模块(1004)，配置为给所述图像中人脸补上预存储的人物身体图像，得到虚拟人像。The second processing module (1004) is configured to add a pre-stored character body image to the face in the image to obtain a virtual portrait.
  16. 根据权利要求15所述的装置，其中，所述第二处理模块(1004)还配置为在得到虚拟人像之后，将所述虚拟人像在预设场景显示，得到虚拟会场图像，并将所述虚拟会场图像发送至所述终端。The apparatus according to claim 15, wherein the second processing module (1004) is further configured to: after obtaining the virtual portrait, display the virtual portrait in a preset scene, obtain a virtual venue image, and The venue image is sent to the terminal.
  17. 一种存储介质，存储有图像处理程序，所述图像处理程序被处理器执行时实现如权利要求1至4中任一项所述的图像处理方法的步骤。A storage medium storing an image processing program, the image processing program being executed by a processor to implement the steps of the image processing method according to any one of claims 1 to 4.
  18. 一种存储介质，存储有图像处理程序，所述图像处理程序被处理器执行时实现如权利要求5至6中任一项所述的图像处理方法的步骤。A storage medium storing an image processing program, the image processing program being executed by a processor to implement the steps of the image processing method according to any one of claims 5 to 6.
  19. 一种存储介质，存储有图像处理程序，所述图像处理程序被处理器执行时实现如权利要求7至8中任一项所述的图像处理方法的步骤。 A storage medium storing an image processing program, the image processing program being executed by a processor to implement the steps of the image processing method according to any one of claims 7 to 8.
PCT/CN2017/099414 2016-07-11 2017-08-29 Image processing method and device WO2018010700A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610541902.5A CN107612869A (en) 2016-07-11 2016-07-11 Image processing method and device
CN201610541902.5 2016-07-11

Publications (1)

Publication Number Publication Date
WO2018010700A1 true WO2018010700A1 (en) 2018-01-18

Family

ID=60952788

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/099414 WO2018010700A1 (en) 2016-07-11 2017-08-29 Image processing method and device

Country Status (2)

Country Link
CN (1) CN107612869A (en)
WO (1) WO2018010700A1 (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102521865A (en) * 2011-12-23 2012-06-27 广东威创视讯科技股份有限公司 Method, device and system for simulating video scene
CN103489107A (en) * 2013-08-16 2014-01-01 北京京东尚科信息技术有限公司 Method and device used for manufacturing virtual fit model image
US20150029216A1 (en) * 2013-07-25 2015-01-29 Morphotrust Usa Inc. System and Method for Creating a Virtual Backdrop
CN104349111A (en) * 2013-07-24 2015-02-11 华为技术有限公司 Meeting place creating method and system of video conference
CN104933694A (en) * 2014-03-17 2015-09-23 华为技术有限公司 Method and equipment for segmenting foreground and background
CN105469379A (en) * 2014-09-04 2016-04-06 广东中星电子有限公司 Video target area shielding method and device
CN105701756A (en) * 2014-12-16 2016-06-22 佳能株式会社 Image processing apparatus and image processing method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103607554B (en) * 2013-10-21 2017-10-20 易视腾科技股份有限公司 It is a kind of based on full-automatic face without the image synthesizing method being stitched into
EP2919142B1 (en) * 2014-03-14 2023-02-22 Samsung Electronics Co., Ltd. Electronic apparatus and method for providing health status information

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102521865A (en) * 2011-12-23 2012-06-27 广东威创视讯科技股份有限公司 Method, device and system for simulating video scene
CN104349111A (en) * 2013-07-24 2015-02-11 华为技术有限公司 Meeting place creating method and system of video conference
US20150029216A1 (en) * 2013-07-25 2015-01-29 Morphotrust Usa Inc. System and Method for Creating a Virtual Backdrop
CN103489107A (en) * 2013-08-16 2014-01-01 北京京东尚科信息技术有限公司 Method and device used for manufacturing virtual fit model image
CN104933694A (en) * 2014-03-17 2015-09-23 华为技术有限公司 Method and equipment for segmenting foreground and background
CN105469379A (en) * 2014-09-04 2016-04-06 广东中星电子有限公司 Video target area shielding method and device
CN105701756A (en) * 2014-12-16 2016-06-22 佳能株式会社 Image processing apparatus and image processing method

Also Published As

Publication number Publication date
CN107612869A (en) 2018-01-19

Similar Documents

Publication Publication Date Title
CN112449120B (en) High dynamic range video generation method and device
US10728510B2 (en) Dynamic chroma key for video background replacement
WO2016101883A1 (en) Method for face beautification in real-time video and electronic equipment
WO2016110188A1 (en) Method and electronic device for aesthetic enhancements of face in real-time video
US20210258482A1 (en) Background replacement from video images captured by a plenoptic camera
US20140118475A1 (en) Information processing device, conference system and storage medium
US20150188970A1 (en) Methods and Systems for Presenting Personas According to a Common Cross-Client Configuration
CN110619610B (en) Image processing method and device
KR101989842B1 (en) Terminal and image processing method thereof
CN114786040B (en) Data communication method, system, electronic device and storage medium
CN109040654B (en) Method and device for identifying external shooting equipment and storage medium
CN107527072B (en) Method and device for determining similar head portrait and electronic equipment
CN106375787B (en) Video playing method and device
WO2018010700A1 (en) Image processing method and device
KR102162102B1 (en) Video call mediating apparatus, method and computer readable recording medium thereof
CN116095513B (en) Photographing method and related device
US20200210682A1 (en) Skin color identification method, skin color identification apparatus and storage medium
CN115760879A (en) Image processing method, image processing system, image processing apparatus, device, and medium
US10791307B2 (en) Image details processing method, apparatus, terminal, and storage medium
WO2017101570A1 (en) Photo processing method and processing system
CN106656725B (en) Intelligent terminal, server and information updating system
EP3273437A1 (en) Method and device for enhancing readability of a display
KR101823035B1 (en) Compensation value-sharing system based social and method of the same
WO2023025020A1 (en) Video call method, user terminal, data server, computer device, and computer readable storage medium
CN115955611B (en) Image processing method and electronic equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17827036

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017827036

Country of ref document: EP

Effective date: 20190211