WO2021047069A1 - Face recognition method and electronic terminal device - Google Patents

Face recognition method and electronic terminal device Download PDF

Info

Publication number
WO2021047069A1
WO2021047069A1 PCT/CN2019/122508 CN2019122508W WO2021047069A1 WO 2021047069 A1 WO2021047069 A1 WO 2021047069A1 CN 2019122508 W CN2019122508 W CN 2019122508W WO 2021047069 A1 WO2021047069 A1 WO 2021047069A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
face recognition
recognized
recognition method
display information
Prior art date
Application number
PCT/CN2019/122508
Other languages
French (fr)
Chinese (zh)
Inventor
张台峰
周凡贻
尚国强
Original Assignee
深圳传音控股股份有限公司
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 深圳传音控股股份有限公司 filed Critical 深圳传音控股股份有限公司
Publication of WO2021047069A1 publication Critical patent/WO2021047069A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Definitions

  • face recognition technology has been widely used in enterprise and residential security and management due to its advantages, such as face recognition access control and attendance systems, face recognition anti-theft doors, etc., as well as public security, judicial and criminal investigations (for example, the use of human Facial recognition systems and networks hunt down fugitives across the country); self-service (for example, bank ATMs. If facial recognition is applied at the same time, it will largely avoid the occurrence of cash stolen by others, and information security ( For example, computer login, e-government and e-commerce) and enhancing the fun of taking pictures with cameras.
  • Face recognition technology includes at least the following advantages: non-contact, that is, the user does not need to directly contact the device; non-mandatory, that is, the recognized face image information can be actively obtained; concurrency, that is, multiple people can be used in actual application scenarios. Sorting, judgment and recognition of faces.
  • the age of the faces appearing in the pictures will be estimated, and the age will be displayed on the face detection frame information.
  • the recognition of the user's age in the prior art is limited to the correction between the face template database and its own age estimation algorithm, lacks the ability to learn and update the adaptive feature database, and is inaccurate for the user's age recognition;
  • the positioning accuracy of the face template database positioning algorithm used in the prior art is affected by the photographing environment in which the camera is located, that is, the brightness of the photographing environment, the posture of the collected face image, and the difference of the face image. Changes in external photographing conditions such as facial expression changes will reduce the positioning accuracy of the face template database positioning algorithm, which in turn will reduce the accuracy of user age recognition.
  • the purpose of this application is to provide a face recognition method and electronic terminal equipment to solve the lack of adaptive feature database learning and updating capabilities of the face template database in the prior art, and the positioning of the face template database positioning algorithm.
  • the accuracy is affected by the photographing environment in which the camera is located, which leads to a problem that the accuracy of the user's age identification is reduced.
  • the judging whether the portrait pose in the target portrait image to be recognized is a standard pose; if so, matching the target portrait image to be recognized with the face image samples in the feature database to obtain The identification information,
  • the identification information is a matching face image sample.
  • the method further includes: using an age estimation method to estimate the portrait image of the target to be recognized User age.
  • the display information is user information, including one or any combination of age information, hobby information, facial features information, skin color information, and skin state information of the user.
  • the step of correcting the display information includes: manually modifying the display information when the error of the age information is not within a preset range.
  • this application also provides a face recognition method.
  • it includes: acquiring a target portrait image to be recognized; identifying and displaying the display information of the target portrait; when the terminal receives the display information Error signal; capture new input information, import the new input information into the feature database to update.
  • the manner in which the terminal captures the new input information includes one or any combination of voice input, file import, and text input.
  • the specific steps of the terminal capturing and judging the user's emotional information to obtain the display information error signal include:
  • the terminal After the terminal displays the display information of the target portrait, it calls the terminal shooting component, voice input component or infrared sensor to obtain the user's expression and sound after seeing the display information, and judge the user's emotional information.
  • this application also provides a face recognition method. As one of the implementation manners, it includes:
  • the display information of the object to be identified is generated according to the identification information.
  • the method further includes a step of classifying the object to be identified according to the pixel set, and the object to be identified is a portrait image of the object to be identified.
  • the present application also provides an electronic terminal device, including: a processor, a memory, and a computer program stored on the memory and running on the processor, and the processor executes the program When realizing the face recognition method as described above.
  • this application also provides a computer-readable storage medium.
  • the computer-readable storage medium stores a face recognition program
  • the face recognition program is processed by a processor.
  • the steps of the face recognition method as described above are realized.
  • the face recognition method provided by the present application includes: a terminal receives a display information error signal, captures new input information, and imports the new input information into the feature database to update. It can be seen that the face recognition method of the present application has learning capabilities, which can be an adaptive feature database that can be continuously updated. When the face recognition method described above is used to recognize a face, it can improve face recognition. Accuracy, improve user experience.
  • the present application also provides a face recognition method, including: acquiring a target portrait image to be recognized; extracting identification information of the target portrait image according to a judgment rule, and generating display information of the target portrait based on the identification information. That is to say, the posture of the target portrait image to be recognized is specifically judged. When the judgment result is a free posture, the posture of the target portrait image to be recognized can be corrected, and the corrected target portrait image to be recognized and the feature database are used.
  • the matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition. At the same time, it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
  • FIG. 1 is a schematic flowchart of a face recognition method provided by an embodiment of this application.
  • the recognition of the user’s age in the prior art is limited to the correction between the face template database and its own age estimation algorithm, and lacks the ability to learn and update the self-adaptive feature database.
  • Recognition is not accurate; on the other hand, the positioning accuracy of the face template database positioning algorithm used in the prior art is affected by the photographing environment in which the camera is located, that is, the brightness of the photographing environment and the difference between the collected face images Changes in external photographing conditions, such as postures and facial expression changes in facial images, will reduce the positioning accuracy of the facial template database positioning algorithm, which in turn will reduce the accuracy of user age recognition.
  • the age estimation schemes when taking pictures are based on image vision algorithms, which extract facial appearance features, establish a regression or classification relationship model between features and age values, and then use this relationship model to predict the age of the newly photographed face
  • image vision algorithms which extract facial appearance features, establish a regression or classification relationship model between features and age values, and then use this relationship model to predict the age of the newly photographed face
  • the image is greatly affected by factors such as light, hairstyle, occlusion, image resolution, makeup, etc.
  • the age estimation algorithm based purely on image vision has a large deviation in age display, and the same person takes pictures in different poses, or Taking pictures under different light will show different ages, which will make users feel that the age algorithm of the camera is not reliable, and affect the user experience.
  • the present application provides a face recognition method through an embodiment, which includes the following processes: obtain a target portrait image to be recognized; extract the recognition information of the target portrait image according to the judgment rule, and generate a face recognition method based on the recognition information. Describes the display information of the target portrait. Specifically, the posture of the target image to be recognized is judged. When the result of the judgment is a free posture, the posture of the target image to be recognized can be corrected, and the corrected image of the target person to be recognized and the feature database can be used. Matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition.
  • the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
  • the present application also provides a face recognition method through another embodiment, including: acquiring a target portrait image to be recognized; identifying and displaying display information of the target portrait; when the terminal receives a display information error signal; Capture new input information and import the new input information into the feature database to update.
  • the face recognition method of the present application has learning capabilities, which can be an adaptive feature database that can be continuously updated.
  • a face recognition method of this embodiment includes the following processes: acquiring a target portrait image to be recognized; extracting recognition information of the target portrait image according to a judgment rule, and generating display information of the target portrait according to the recognition information.
  • the feature database is searched to obtain the user information corresponding to the matched face image sample.
  • the identification information is a matching face image sample.
  • the method further includes: using an age estimation method to estimate the age of the user based on the to-be-recognized target portrait image.
  • the display information is user information, including one or any combination of the user's age information, hobby information, facial features information, skin color information, and skin state information.
  • the display information is corrected and the characteristic database is updated.
  • the step of correcting the display information includes: manually modifying the display information when the error of the age information is not within a preset range.
  • the posture of the target portrait image to be recognized when the result of the determination is a free posture, the posture of the target portrait image to be recognized can be corrected, and the corrected target portrait image to be recognized and the feature database can be used
  • Matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition.
  • it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
  • step S1 is to obtain a portrait image of a target to be recognized.
  • step S2 It is judged whether the portrait posture in the target portrait image to be recognized is a standard posture; if yes, go to step S3, if not, go to step S4.
  • Step S3 Match the target portrait image to be recognized with the face image sample in the feature database to obtain a matching face image sample, and then proceed to step S5.
  • step S4 Calling the posture correction model library, correcting the target portrait image to be recognized, and obtaining a target portrait image similar to the standard posture, and proceeding to step S6.
  • Step S5 Search a feature database to obtain user information corresponding to the matched face image sample.
  • Step S6 Match the face image of the target to be recognized in the approximate standard posture with the face image sample in the feature database to obtain a matching face image sample, and then enter the step S5.
  • Step S7 Display user information.
  • the user information includes age information.
  • the feature database stores several face image samples and user information corresponding to each of the face image samples.
  • the method further includes: step S5.1, adopting an age estimation method according to the target portrait image to be recognized Estimate the age of the user and proceed to the step S7.
  • one embodiment of the present application also provides a face recognition method to obtain a target portrait image to be recognized; recognize and display the display information of the target portrait; when the terminal receives a display information error signal; capture new input information , Import the new input information into the feature database to update.
  • the new input information is imported into the feature database for updating, it further includes the step of displaying new display information, the display information including user age information, hobby information, facial features information, skin color information, and skin status information.
  • the display information including user age information, hobby information, facial features information, skin color information, and skin status information.
  • the manner in which the terminal captures the new input information includes one or any combination of voice input, file import, and text input.
  • the step of the terminal receiving the display information error signal specifically includes: the user actively touches the display information to remind the display information error or the terminal captures and judges the user's emotional information to obtain the display information error signal.
  • the specific steps of the terminal capturing and judging the user's emotional information to obtain the display information error signal include:
  • the terminal After the terminal displays the display information of the target portrait, it calls the terminal shooting component, voice input component or infrared sensor to obtain the user's expression and sound after seeing the display information, and judge the user's emotional information.
  • an embodiment of the present application also provides a face recognition method
  • the display information of the object to be identified is generated according to the identification information.
  • the method further includes a step of classifying the object to be identified according to the pixel set, and the object to be identified is a portrait image of the target to be identified.
  • the feature database provided by an embodiment of the present application has learning capabilities. It can be an adaptive feature database that can be continuously updated.
  • face recognition method is used to recognize faces, it can improve Face recognition accuracy improves user experience.
  • an embodiment of the present application also discloses an electronic terminal device, including: a processor 100, a memory 101, and a computer program stored in the memory and capable of running on the processor.
  • a processor 100 executes the program, the face recognition method described above is implemented.
  • the electronic terminal device further includes: a power supply module 102, an interactive component 103, a communication module 104, a sensor module 105, and an interface 106.
  • the processor 100 generally performs overall operations of an electronic terminal device, such as operations associated with display, telephone call, data communication, camera operations, and recording operations.
  • the processor 100 may include one or more modules to facilitate interaction between the processor 100 and other modules.
  • the processor 100 may include a multimedia module to facilitate the interaction between the interactive component 103 and the processor 100.
  • the memory 101 is configured to store various types of data to support operations in the electronic terminal device. Examples of these data include instructions for any application or method operated on the electronic terminal device, contact data, phone book data, messages, pictures, videos, etc.
  • the power supply module 102 provides power for various modules of the electronic terminal device.
  • the power supply module 102 may include a power management system, one or more power supplies, and other modules associated with generating, managing, and distributing power for electronic terminal devices.
  • the interaction component 103 includes a screen that provides an output interface between the electronic terminal device and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of the touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the sensor module 105 includes one or more sensors for providing various aspects of state evaluation for the electronic terminal device.
  • the sensor module 105 can detect the on/off status of the electronic terminal device and the relative positioning of the modules, such as the display and keypad of the electronic terminal device.
  • the sensor module 105 can also detect the electronic terminal device or a component of the electronic terminal device. The position changes, the presence or absence of contact between the user and the electronic terminal device, the orientation or acceleration/deceleration of the electronic terminal device and its temperature change.
  • the sensor module 105 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor module 105 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • an embodiment of the present application further provides a computer-readable storage medium, including: a face recognition program is stored on the computer-readable storage medium, and when the face recognition program is executed by a processor Implement the steps of the face recognition method as described above.
  • computer-readable storage media include: electrical connections with one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect via the Internet) ).
  • LAN local area network
  • WAN wide area network
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be used in a dedicated hardware-based system that performs the specified functions or actions. It can be realized, or it can be realized by a combination of dedicated hardware and computer instructions.
  • each module may exist alone, or two or more modules may be integrated to form an independent part.
  • the target portrait image to be recognized is matched with the facial image samples in the updated feature database, so as to improve the accuracy of age recognition.
  • the present application also provides a face recognition method through another embodiment, including: acquiring a target portrait image to be recognized; identifying and displaying display information of the target portrait; when the terminal receives a display information error signal; Capture new input information and import the new input information into the feature database to update.
  • the feature database of the present application has learning capabilities, and it can be an adaptive feature database that can be continuously updated.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Image Analysis (AREA)

Abstract

A face recognition method and an electronic terminal device can improve the recognition precision. The method comprises: obtaining a target portrait image to be recognized (S1); determining whether a portrait posture in the target portrait image to be recognized is a standard posture (S2); and extracting recognition information of the target portrait image, and generating display information of the target portrait according to the recognition information.

Description

人脸识别方法和电子终端设备Face recognition method and electronic terminal equipment
本专利申请要求2019年9月11日提交的中国专利申请号为201910858770.2，申请人为深圳传音控股股份有限公司，发明名称为“人脸识别方法和电子终端设备”的优先权，该申请的全文以引用的方式并入本申请中。This patent application claims the priority of the Chinese patent application number 201910858770.2 filed on September 11, 2019, the applicant is Shenzhen Transsion Holdings Co., Ltd., and the invention title is "Face Recognition Method and Electronic Terminal Equipment". The full text of the application Incorporated into this application by reference.
技术领域Technical field
本申请涉及终端技术领域，具体涉及一种人脸识别方法和电子终端设备。This application relates to the field of terminal technology, and in particular to a face recognition method and electronic terminal equipment.
背景技术Background technique
近些年来，人脸识别技术由于其具有的优点被广泛应用于企业、住宅安全和管理，如人脸识别门禁考勤***，人脸识别防盗门等，以及公安、司法和刑侦(例如，利用人脸识别***和网络在全国范围内追捕逃犯)；自助服务(例如，银行的自动提款机，如果同时应用人脸识别就会很大程度上避免被他人盗取现金现象的发生、信息安全(例如，计算机登录、电子政务和电子商务)以及增强相机拍照趣味性等方面。In recent years, face recognition technology has been widely used in enterprise and residential security and management due to its advantages, such as face recognition access control and attendance systems, face recognition anti-theft doors, etc., as well as public security, judicial and criminal investigations (for example, the use of human Facial recognition systems and networks hunt down fugitives across the country); self-service (for example, bank ATMs. If facial recognition is applied at the same time, it will largely avoid the occurrence of cash stolen by others, and information security ( For example, computer login, e-government and e-commerce) and enhancing the fun of taking pictures with cameras.
人脸识别技术至少包括以下优点，非接触的，即用户不需要和设备直接接触；非强制性，即被识别的人脸图像信息可以主动获取；并发性，即实际应用场景下可以进行多个人脸的分拣、判断和识别。Face recognition technology includes at least the following advantages: non-contact, that is, the user does not need to directly contact the device; non-mandatory, that is, the recognized face image information can be actively obtained; concurrency, that is, multiple people can be used in actual application scenarios. Sorting, judgment and recognition of faces.
对于增强相机拍照趣味性的应用，具体的，在相机拍照过程中，为了实现增加拍照的用户体验和趣味性，会对拍照中出现的人脸进行年龄估计，并在人脸检测框上显示年龄信息。For applications that enhance the fun of taking pictures with the camera, specifically, in the process of taking pictures with the camera, in order to increase the user experience and fun of taking pictures, the age of the faces appearing in the pictures will be estimated, and the age will be displayed on the face detection frame information.
但是现有技术中对于用户年龄的识别一方面其局限于人脸模板数据库与自身年龄估计算法之间的修正，缺少自适应性的特征库学习更新能力，对于用户的年龄识别不精准；另一方面，现有技术中所采用的人脸模板数据库定位算法的定位精确度受到相机所处于的拍照环境的影响，即拍照环境的明亮度，所采集到的人脸图像的姿态，人脸图像的表情变化等外界拍照条件变化会降低人脸模板数据库定位算法的定位精确度，进而导致对用户年龄识别的精度降低。However, the recognition of the user's age in the prior art is limited to the correction between the face template database and its own age estimation algorithm, lacks the ability to learn and update the adaptive feature database, and is inaccurate for the user's age recognition; On the other hand, the positioning accuracy of the face template database positioning algorithm used in the prior art is affected by the photographing environment in which the camera is located, that is, the brightness of the photographing environment, the posture of the collected face image, and the difference of the face image. Changes in external photographing conditions such as facial expression changes will reduce the positioning accuracy of the face template database positioning algorithm, which in turn will reduce the accuracy of user age recognition.
发明概述Summary of the invention
技术问题technical problem
问题的解决方案The solution to the problem
技术解决方案Technical solutions
本申请的目的在于，提供一种人脸识别方法和电子终端设备，用以解决现有技术中的人脸模板数据库缺少自适应性的特征库学习更新能力，以及人脸模板数据库定位算法的定位精确度受到相机所处于的拍照环境的影响导致对用户年龄识别的精度降低的问题。The purpose of this application is to provide a face recognition method and electronic terminal equipment to solve the lack of adaptive feature database learning and updating capabilities of the face template database in the prior art, and the positioning of the face template database positioning algorithm. The accuracy is affected by the photographing environment in which the camera is located, which leads to a problem that the accuracy of the user's age identification is reduced.
为解决上述技术问题，本申请提供一种人脸识别方法，作为其中一种实施方式，所述人脸识别方法包括步骤：To solve the above technical problems, this application provides a face recognition method. As one of the implementation manners, the face recognition method includes the steps:
获取待识别目标人像图像；判断所述待识别目标人像图像中的人像姿态是否为标准姿态；提取所述目标人像图像的识别信息，根据识别信息生成所述目标人像的显示信息。Obtain the target portrait image to be recognized; determine whether the portrait posture in the target portrait image to be recognized is a standard posture; extract the recognition information of the target portrait image, and generate the display information of the target portrait according to the recognition information.
作为其中一种实施方式，所述判断所述待识别目标人像图像中的人像姿态是否为标准姿态；若是，则将所述待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述识别信息，As one of the implementation manners, the judging whether the portrait pose in the target portrait image to be recognized is a standard pose; if so, matching the target portrait image to be recognized with the face image samples in the feature database to obtain The identification information,
若否，则调用姿态矫正模型库，对所述待识别目标人像图像进行矫正，得到近似标准姿态的待识别目标人像图像，并将所述近似标准姿态的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述识别信息；If not, call the posture correction model library to correct the target portrait image to be recognized to obtain a target portrait image similar to the standard posture, and compare the target portrait image similar to the standard posture with the information in the feature database. Matching the face image samples to obtain the identification information;
查找特征数据库，得到所述匹配的人脸图像样本对应的用户信息。The feature database is searched to obtain the user information corresponding to the matched face image sample.
作为其中一种实施方式，所述识别信息为匹配的人脸图像样本。As one of the implementation manners, the identification information is a matching face image sample.
作为其中一种实施方式，当所述待识别目标人像图像和与其相匹配的人脸图像样本的相似度未超过设定阈值时，还包括：采用年龄估算法根据所述待识别目标人像图像估计用户年龄。As one of the implementation manners, when the similarity between the portrait image of the target to be recognized and the matching face image sample does not exceed a set threshold, the method further includes: using an age estimation method to estimate the portrait image of the target to be recognized User age.
作为其中一种实施方式，所述显示信息为用户信息，包括该用户的年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。As one of the implementation manners, the display information is user information, including one or any combination of age information, hobby information, facial features information, skin color information, and skin state information of the user.
作为其中一种实施方式，当所述显示信息错误时，纠正所述显示信息，更新所述特征数据库。As one of the implementation manners, when the displayed information is wrong, the displayed information is corrected and the characteristic database is updated.
作为其中一种实施方式，所述纠正所述显示信息的步骤包括：当所述年龄信息误差不处于预设范围时，手动修改所述显示信息。As one of the implementation manners, the step of correcting the display information includes: manually modifying the display information when the error of the age information is not within a preset range.
为解决上述技术问题，本申请还提供一种人脸识别方法，作为其中一种实施方式，包含：获取待识别目标人像图像；识别并显示所述目标人像的显示信息；当终端收到显示信息错误信号；捕获新输入信息，将新输入信息导入特征数据库更新。In order to solve the above technical problems, this application also provides a face recognition method. As one of the implementation manners, it includes: acquiring a target portrait image to be recognized; identifying and displaying the display information of the target portrait; when the terminal receives the display information Error signal; capture new input information, import the new input information into the feature database to update.
作为其中一种实施方式，在将所述新输入信息导入所述特征数据库更新后，还包括显示新显示信息的步骤，所述显示信息包括用户年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。As one of the implementation manners, after the new input information is imported into the feature database to update, it further includes the step of displaying new display information, the display information including user age information, hobby information, facial features information, skin color information, One or any combination of skin status information.
作为其中一种实施方式，所述终端捕获新输入信息的方式包括语音输入、文件导入和文字键入中的一种或其任意一组合。As one of the implementation manners, the manner in which the terminal captures the new input information includes one or any combination of voice input, file import, and text input.
作为其中一种实施方式，所述终端收到显示信息错误信号的步骤具体包括：用户主动触控显示信息以提醒显示信息错误或终端捕获并判断用户情绪信息获得显示信息错误信号。As one of the implementation manners, the step of the terminal receiving the display information error signal specifically includes: the user actively touches the display information to remind the display information error or the terminal captures and judges the user's emotional information to obtain the display information error signal.
作为其中一种实施方式，所述终端捕获并判断用户情绪信息获得显示信息错误信号具体步骤包括：As one of the implementation manners, the specific steps of the terminal capturing and judging the user's emotional information to obtain the display information error signal include:
终端显示所述目标人像的显示信息后，调用终端拍摄组件、语音输入组件或红外传感器，获取用户看到所述显示信息后的表情、声音，判断用户的情绪信息。After the terminal displays the display information of the target portrait, it calls the terminal shooting component, voice input component or infrared sensor to obtain the user's expression and sound after seeing the display information, and judge the user's emotional information.
为解决上述技术问题，本申请还提供一种人脸识别方法，作为其中一种实施方式，包含：In order to solve the above technical problems, this application also provides a face recognition method. As one of the implementation manners, it includes:
获取预览界面中的待识别对象；Obtain the object to be recognized in the preview interface;
采集所述待识别对象的像素集合；Collecting the pixel set of the object to be identified;
根据所述像素集合判断待识别对象的识别信息；Judging the identification information of the object to be identified according to the pixel set;
根据所述识别信息生成所述待识别对象的显示信息。The display information of the object to be identified is generated according to the identification information.
作为其中一种实施方式，在采集所述待识别对象的像素集合后，还包括根据所述像素集合对待识别对象进行分类的步骤，所述待识别对象为待识别目标人像图像。As one of the embodiments, after collecting the pixel set of the object to be identified, the method further includes a step of classifying the object to be identified according to the pixel set, and the object to be identified is a portrait image of the object to be identified.
为解决上述技术问题，本申请还提供一种电子终端设备，包含：处理器，存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现如上文所述的人脸识别方法。In order to solve the above technical problems, the present application also provides an electronic terminal device, including: a processor, a memory, and a computer program stored on the memory and running on the processor, and the processor executes the program When realizing the face recognition method as described above.
为解决上述技术问题，本申请还提供一种计算机可读存储介质，作为其中一种实施方式，包含：所述计算机可读存储介质上存储有人脸识别程序，所述人脸识别程序被处理器执行时实现如上文所述的人脸识别方法的步骤。In order to solve the above technical problems, this application also provides a computer-readable storage medium. As one of the implementation manners, it includes: the computer-readable storage medium stores a face recognition program, and the face recognition program is processed by a processor. When executed, the steps of the face recognition method as described above are realized.
发明的有益效果The beneficial effects of the invention
有益效果Beneficial effect
本申请提供的人脸识别方法，包含：终端收到显示信息错误信号，捕获新输入信息，将新输入信息导入所述特征数据库更新。由此可知，本申请的人脸识别方法具有学习能力，其可以是为自适应性的可不断更新的特征数据库，采用如上所述的人脸识别方法来识别人脸时，可以提高人脸识别精度，提高用户体验。The face recognition method provided by the present application includes: a terminal receives a display information error signal, captures new input information, and imports the new input information into the feature database to update. It can be seen that the face recognition method of the present application has learning capabilities, which can be an adaptive feature database that can be continuously updated. When the face recognition method described above is used to recognize a face, it can improve face recognition. Accuracy, improve user experience.
另外，本申请还提供了一种人脸识别方法，包含：获取待识别目标人像图像；根据判断规则提取所述目标人像图像的识别信息，根据识别信息生成所述目标人像的显示信息。即具体的通过将待识别目标人像图像进行姿态判断，当判断结果为自由姿态时，可以通过矫正该待识别目标人像图像的姿态，并利用经矫正过的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配使得人脸识别不受相机拍照环境的影响，提高了人脸识别精度。同时，还可根据用户自愿的信息共享，即当用户认为当前识别出的年龄信息不符合实际年龄时，上传信息，上传信息后，所述特征数据库当中的至少一个样品信息进行了更新，之后，再以将待识别目标人像图像与更新后的特征数据库中的人脸图像样本进行匹配，以此提高年龄识别的准确率。In addition, the present application also provides a face recognition method, including: acquiring a target portrait image to be recognized; extracting identification information of the target portrait image according to a judgment rule, and generating display information of the target portrait based on the identification information. That is to say, the posture of the target portrait image to be recognized is specifically judged. When the judgment result is a free posture, the posture of the target portrait image to be recognized can be corrected, and the corrected target portrait image to be recognized and the feature database are used. The matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition. At the same time, it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
对附图的简要说明Brief description of the drawings
附图说明Description of the drawings
图1为本申请一实施例提供的一种人脸识别方法的流程示意图。FIG. 1 is a schematic flowchart of a face recognition method provided by an embodiment of this application.
图2为本申请一实施例提供的一种电子终端设备的结构示意图。FIG. 2 is a schematic structural diagram of an electronic terminal device provided by an embodiment of this application.
发明实施例Invention embodiment
本发明的实施方式Embodiments of the present invention
为更进一步阐述本申请为达成预定申请目的所采取的技术手段及功效，以下结合附图及较佳实施例，对本申请详细说明如下。In order to further illustrate the technical means and effects adopted by this application to achieve the intended application purpose, the application will be described in detail below with reference to the accompanying drawings and preferred embodiments.
通过具体实施方式的说明，当可对本申请为达成预定目的所采取的技术手段及效果得以更加深入且具体的了解，然而所附图式仅是提供参考与说明之用，并非用来对本申请加以限制。Through the description of the specific implementation manners, it is possible to gain a deeper and specific understanding of the technical means and effects adopted by this application to achieve the intended purpose. However, the accompanying drawings are only for reference and explanation purposes, and are not used to describe the application. limit.
诚如背景技术所述，现有技术中对于用户年龄的识别一方面其局限于人脸模板数据库与自身年龄估计算法之间的修正，缺少自适应性的特征库学***、地理环境、病症等因素的不同，使得相同年龄的人脸具有明显的差异性，或特征相近的人脸其年龄差距却较大，因而导致根据人脸面貌特征无论视觉直观去断定一个人的年龄，还是利用计算机去估计一幅脸像的年龄，都存在着较大的不确定性。在一个人从小孩长成青年人的过程中，人脸部骨骼不断生长，从而脸型不断变长变大，相貌也随之变化，而由青年人不断衰老变成老年人的过程中，皮肤的肤色、皱纹也会随之变化，因此年龄识别率会随着人的年龄变化而急剧下降。相关技术中，拍照时的年龄估计方案都是基于图像视觉的算法，提取人脸外观特征，建立特征与年龄值之间的回归或者分类关系模型，再通过这个关系模型预测新拍人脸的年龄，由于图像受光线、发型、遮挡、图像分辨率、化妆等因素的影响很大，导致纯粹基于图像视觉的年龄估计算法的在年龄显示上有较大偏差，同一个人采用不同姿势的拍照，或者在不同光线下的拍照，都会显示出不同的年龄，会让用户感觉相机的年龄算法不靠谱，影响用户的使用体验。As mentioned in the background art, the recognition of the user’s age in the prior art is limited to the correction between the face template database and its own age estimation algorithm, and lacks the ability to learn and update the self-adaptive feature database. Recognition is not accurate; on the other hand, the positioning accuracy of the face template database positioning algorithm used in the prior art is affected by the photographing environment in which the camera is located, that is, the brightness of the photographing environment and the difference between the collected face images Changes in external photographing conditions, such as postures and facial expression changes in facial images, will reduce the positioning accuracy of the facial template database positioning algorithm, which in turn will reduce the accuracy of user age recognition. Research has found that in reality, due to differences in living standards, geographical environment, diseases, and other factors, faces of the same age have obvious differences, or faces with similar characteristics have a large age gap, which leads to Features Whether visually determining the age of a person or using a computer to estimate the age of a face, there are large uncertainties. When a person grows from a child to a young person, the bones of the face continue to grow, so that the face continues to grow and grow, and the appearance also changes. In the process of aging from young people to old people, the skin’s Skin color and wrinkles will also change, so the age recognition rate will drop sharply with people's age. In related technologies, the age estimation schemes when taking pictures are based on image vision algorithms, which extract facial appearance features, establish a regression or classification relationship model between features and age values, and then use this relationship model to predict the age of the newly photographed face Because the image is greatly affected by factors such as light, hairstyle, occlusion, image resolution, makeup, etc., the age estimation algorithm based purely on image vision has a large deviation in age display, and the same person takes pictures in different poses, or Taking pictures under different light will show different ages, which will make users feel that the age algorithm of the camera is not reliable, and affect the user experience.
基于上述研究，本申请一方面通过一实施例提供了一种人脸识别方法，包含以下过程：获取待识别目标人像图像；根据判断规则提取所述目标人像图像的识 别信息，根据识别信息生成所述目标人像的显示信息。即具体的是通过将待识别目标人像图像进行姿态判断，当判断结果为自由姿态时，可以通过矫正该待识别目标人像图像的姿态，并利用经矫正过的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配使得人脸识别不受相机拍照环境的影响，提高了人脸识别精度。同时，还可根据用户自愿的信息共享，即当用户认为当前识别出的年龄信息不符合实际年龄时，上传信息，上传信息后，所述特征数据库当中的至少一个样品信息进行了更新，之后，再以将待识别目标人像图像与更新后的特征数据库中的人脸图像样本进行匹配，以此提高年龄识别的准确率。Based on the above research, on the one hand, the present application provides a face recognition method through an embodiment, which includes the following processes: obtain a target portrait image to be recognized; extract the recognition information of the target portrait image according to the judgment rule, and generate a face recognition method based on the recognition information. Describes the display information of the target portrait. Specifically, the posture of the target image to be recognized is judged. When the result of the judgment is a free posture, the posture of the target image to be recognized can be corrected, and the corrected image of the target person to be recognized and the feature database can be used. Matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition. At the same time, it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
另一方面，本申请还通过另一实施例提供了一种人脸识别方法，包含：获取待识别目标人像图像；识别并显示所述目标人像的显示信息；当终端收到显示信息错误信号；捕获新输入信息，将新输入信息导入特征数据库更新。由此可知，本申请的人脸识别方法具有学习能力，其可以是为自适应性的可不断更新的特征数据库，采用如上所述的人脸识别方法来识别人脸时，可以提高人脸识别精度，提高用户体验。On the other hand, the present application also provides a face recognition method through another embodiment, including: acquiring a target portrait image to be recognized; identifying and displaying display information of the target portrait; when the terminal receives a display information error signal; Capture new input information and import the new input information into the feature database to update. It can be seen that the face recognition method of the present application has learning capabilities, which can be an adaptive feature database that can be continuously updated. When the face recognition method described above is used to recognize a face, it can improve face recognition. Accuracy, improve user experience.
下面将结合示意图对本发明的具体实施方式进行更详细的描述。根据下列描述和权利要求书，本发明的优点和特征将更清楚。需说明的是，附图均采用非常简化的形式且均使用非精准的比例，仅用以方便、明晰地辅助说明本发明实施例的目的。The specific embodiments of the present invention will be described in more detail below in conjunction with the schematic diagrams. According to the following description and claims, the advantages and features of the present invention will be clearer. It should be noted that the drawings all adopt a very simplified form and all use imprecise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention.
为了清楚，不描述实际一实施例的全部特征。在下列描述中，不详细描述公知的功能和结构，因为它们会使本发明由于不必要的细节而混乱。应当认为在任何实际一实施例的开发中，必须作出大量实施细节以实现开发者的特定目标，例如按照有关***或有关商业的限制，由一个一实施例改变为另一个一实施例。另外，应当认为这种开发工作可能是复杂和耗费时间的，但是对于本领域技术人员来说仅仅是常规工作。For the sake of clarity, not all features of an actual embodiment are described. In the following description, well-known functions and structures are not described in detail because they may confuse the present invention due to unnecessary details. It should be considered that in the development of any actual embodiment, a large number of implementation details must be made to achieve the developer's specific goals, for example, according to system or business restrictions, one embodiment is changed to another embodiment. In addition, it should be considered that this kind of development work may be complicated and time-consuming, but it is only routine work for those skilled in the art.
需说明的是，附图均采用非常简化的形式且均使用非精准的比率，仅用以方便、明晰地辅助说明本申请一实施例的目的。It should be noted that the drawings are in a very simplified form and all use imprecise ratios, which are only used to conveniently and clearly assist in explaining the purpose of an embodiment of the present application.
本实施例一种人脸识别方法，包括以下过程：获取待识别目标人像图像；根据判断规则提取所述目标人像图像的识别信息，根据识别信息生成所述目标人像 的显示信息。A face recognition method of this embodiment includes the following processes: acquiring a target portrait image to be recognized; extracting recognition information of the target portrait image according to a judgment rule, and generating display information of the target portrait according to the recognition information.
在本实施例中，所述判断规则为判断所述待识别目标人像图像中的人像姿态是否为标准姿态；若是，则将所述待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述识别信息，In this embodiment, the judgment rule is to judge whether the portrait pose in the target portrait image to be recognized is a standard pose; if so, match the target portrait image to be recognized with the face image sample in the feature database , To obtain the identification information,
若否，则调用姿态矫正模型库，对所述待识别目标人像图像进行矫正，得到近似标准姿态的待识别目标人像图像，并将所述近似标准姿态的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述识别信息；If not, call the posture correction model library to correct the target portrait image to be recognized to obtain a target portrait image similar to the standard posture, and compare the target portrait image similar to the standard posture with the information in the feature database. Matching the face image samples to obtain the identification information;
查找特征数据库，得到所述匹配的人脸图像样本对应的用户信息。The feature database is searched to obtain the user information corresponding to the matched face image sample.
所述识别信息为匹配的人脸图像样本。当所述待识别目标人像图像和与其相匹配的人脸图像样本的相似度未超过设定阈值时，还包括：采用年龄估算法根据所述待识别目标人像图像估计用户年龄。所述显示信息为用户信息，包括该用户的年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。当所述显示信息错误时，纠正所述显示信息，更新所述特征数据库。所述纠正所述显示信息的步骤包括：当所述年龄信息误差不处于预设范围时，手动修改所述显示信息。The identification information is a matching face image sample. When the similarity between the to-be-recognized target portrait image and the matching face image sample does not exceed a set threshold, the method further includes: using an age estimation method to estimate the age of the user based on the to-be-recognized target portrait image. The display information is user information, including one or any combination of the user's age information, hobby information, facial features information, skin color information, and skin state information. When the display information is wrong, the display information is corrected and the characteristic database is updated. The step of correcting the display information includes: manually modifying the display information when the error of the age information is not within a preset range.
由此可知，通过将待识别目标人像图像进行姿态判断，当判断结果为自由姿态时，可以通过矫正该待识别目标人像图像的姿态，并利用经矫正过的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配使得人脸识别不受相机拍照环境的影响，提高了人脸识别精度。同时，还可根据用户自愿的信息共享，即当用户认为当前识别出的年龄信息不符合实际年龄时，上传信息，上传信息后，所述特征数据库当中的至少一个样品信息进行了更新，之后，再以将待识别目标人像图像与更新后的特征数据库中的人脸图像样本进行匹配，以此提高年龄识别的准确率。It can be seen that by judging the posture of the target portrait image to be recognized, when the result of the determination is a free posture, the posture of the target portrait image to be recognized can be corrected, and the corrected target portrait image to be recognized and the feature database can be used Matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition. At the same time, it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database to improve the accuracy of age recognition.
具体的，本实施例所提供的人脸识别方法，如图1所示，步骤S1、获取待识别目标人像图像。步骤S2、判断所述待识别目标人像图像中的人像姿态是否为标准姿态；若是，则进入步骤S3，若否，则进入步骤S4。步骤S3、将所述待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到匹配的人脸图像样本，进入步骤S5。步骤S4、调用姿态矫正模型库，对所述待识别目标人像图 像进行矫正，得到近似标准姿态的待识别目标人像图像，进入步骤S6。步骤S5、查找特征数据库，得到所述匹配的人脸图像样本对应的用户信息。步骤S6、将所述近似标准姿态的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到匹配的人脸图像样本，进入所述步骤S5。步骤S7、显示用户信息。Specifically, in the face recognition method provided by this embodiment, as shown in FIG. 1, step S1 is to obtain a portrait image of a target to be recognized. Step S2: It is judged whether the portrait posture in the target portrait image to be recognized is a standard posture; if yes, go to step S3, if not, go to step S4. Step S3: Match the target portrait image to be recognized with the face image sample in the feature database to obtain a matching face image sample, and then proceed to step S5. Step S4: Calling the posture correction model library, correcting the target portrait image to be recognized, and obtaining a target portrait image similar to the standard posture, and proceeding to step S6. Step S5: Search a feature database to obtain user information corresponding to the matched face image sample. Step S6: Match the face image of the target to be recognized in the approximate standard posture with the face image sample in the feature database to obtain a matching face image sample, and then enter the step S5. Step S7: Display user information.
在本实施例中，所述用户信息包含年龄信息。所述特征数据库存储若干个人脸图像样本，以及与各个所述人脸图像样本相对应的用户信息。In this embodiment, the user information includes age information. The feature database stores several face image samples and user information corresponding to each of the face image samples.
所述姿态矫正模型库包括标准姿态和自由姿态，所述步骤S4进一步包括：提取自由姿态的所述待识别目标人像图像的特征点，并对提取到的所述特征点进行定位，之后对经定位处理的所述特征点进行归一化建模处理，得到所述近似标准姿态的待识别目标人像图像。The posture correction model library includes a standard posture and a free posture, and the step S4 further includes: extracting the feature points of the target portrait image to be recognized in the free posture, and positioning the extracted feature points, and then the warp The characteristic points of the positioning processing are subjected to normalization modeling processing to obtain the target portrait image to be recognized in the approximate standard posture.
进一步的，当所述待识别目标人像图像和与其相匹配的人脸图像样本的相似度未超过设定阈值时，还包括：步骤S5.1、采用年龄估算法根据所述待识别目标人像图像估计用户年龄，进入所述步骤S7。Further, when the similarity between the target portrait image to be recognized and the matching face image sample does not exceed the set threshold, the method further includes: step S5.1, adopting an age estimation method according to the target portrait image to be recognized Estimate the age of the user and proceed to the step S7.
当所述年龄信息误差不处于预设范围时，本实施例所述的人脸识别方法还包括：步骤S8、修改用户信息；步骤S9、更新所述特征数据库，并重复步骤S1～步骤S7。When the age information error is not within the preset range, the face recognition method of this embodiment further includes: step S8, modifying user information; step S9, updating the feature database, and repeating steps S1 to S7.
基于同一发明构思，本申请一实施例还提供一种人脸识别方法，获取待识别目标人像图像；识别并显示所述目标人像的显示信息；当终端收到显示信息错误信号；捕获新输入信息，将新输入信息导入特征数据库更新。Based on the same inventive concept, one embodiment of the present application also provides a face recognition method to obtain a target portrait image to be recognized; recognize and display the display information of the target portrait; when the terminal receives a display information error signal; capture new input information , Import the new input information into the feature database to update.
优选地，在将所述新输入信息导入所述特征数据库更新后，还包括显示新显示信息的步骤，所述显示信息包括用户年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。Preferably, after the new input information is imported into the feature database for updating, it further includes the step of displaying new display information, the display information including user age information, hobby information, facial features information, skin color information, and skin status information. One or any combination of them.
优选地，所述终端捕获新输入信息的方式包括语音输入、文件导入和文字键入中的一种或其任意一组合。Preferably, the manner in which the terminal captures the new input information includes one or any combination of voice input, file import, and text input.
优选地，所述终端收到显示信息错误信号的步骤具体包括：用户主动触控显示信息以提醒显示信息错误或终端捕获并判断用户情绪信息获得显示信息错误信号。Preferably, the step of the terminal receiving the display information error signal specifically includes: the user actively touches the display information to remind the display information error or the terminal captures and judges the user's emotional information to obtain the display information error signal.
优选地，所述终端捕获并判断用户情绪信息获得显示信息错误信号具体步骤包括：Preferably, the specific steps of the terminal capturing and judging the user's emotional information to obtain the display information error signal include:
终端显示所述目标人像的显示信息后，调用终端拍摄组件、语音输入组件或红外传感器，获取用户看到所述显示信息后的表情、声音，判断用户的情绪信息。After the terminal displays the display information of the target portrait, it calls the terminal shooting component, voice input component or infrared sensor to obtain the user's expression and sound after seeing the display information, and judge the user's emotional information.
再一方面，本申请一实施例还提供一种人脸识别方法，In another aspect, an embodiment of the present application also provides a face recognition method,
获取预览界面中的待识别对象；Obtain the object to be recognized in the preview interface;
采集所述待识别对象的像素集合；Collecting the pixel set of the object to be identified;
根据所述像素集合判断待识别对象的识别信息；Judging the identification information of the object to be identified according to the pixel set;
根据所述识别信息生成所述待识别对象的显示信息。The display information of the object to be identified is generated according to the identification information.
优选地，在采集所述待识别对象的像素集合后，还包括根据所述像素集合对待识别对象进行分类的步骤，所述待识别对象为待识别目标人像图像。Preferably, after collecting the pixel set of the object to be identified, the method further includes a step of classifying the object to be identified according to the pixel set, and the object to be identified is a portrait image of the target to be identified.
由此可知，本申请一实施例所提供的特征数据库具有学习能力，其可以是为自适应性的可不断更新的特征数据库，采用如上所述的人脸识别方法来识别人脸时，可以提高人脸识别精度，提高用户体验。It can be seen that the feature database provided by an embodiment of the present application has learning capabilities. It can be an adaptive feature database that can be continuously updated. When the above-mentioned face recognition method is used to recognize faces, it can improve Face recognition accuracy improves user experience.
基于同一发明构思，本申请一实施例还公开了一种电子终端设备，包含：处理器100，存储器101以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器100执行所述程序时实现上文所述的人脸识别方法。Based on the same inventive concept, an embodiment of the present application also discloses an electronic terminal device, including: a processor 100, a memory 101, and a computer program stored in the memory and capable of running on the processor. When the device 100 executes the program, the face recognition method described above is implemented.
所述电子终端设备可以是移动电话，游戏控制台，电脑、平板设备，个人数字助理等。The electronic terminal device may be a mobile phone, a game console, a computer, a tablet device, a personal digital assistant, etc.
所述电子终端设备还包括：电源模块102，交互组件103，通信模块104，传感器模块105以及接口106。处理器100通常电子终端设备的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理器100可以包括一个或多个模块，便于处理器100和其他模块之间的交互。例如，处理器100可以包括多媒体模块，以方便交互组件103和处理器100之间的交互。存储器101被配置为存储各种类型的数据以支持在电子终端设备的操作。这些数据的示例包括用于在电子终端设备上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器101可以由任何类型的易失性或非易 失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。The electronic terminal device further includes: a power supply module 102, an interactive component 103, a communication module 104, a sensor module 105, and an interface 106. The processor 100 generally performs overall operations of an electronic terminal device, such as operations associated with display, telephone call, data communication, camera operations, and recording operations. The processor 100 may include one or more modules to facilitate interaction between the processor 100 and other modules. For example, the processor 100 may include a multimedia module to facilitate the interaction between the interactive component 103 and the processor 100. The memory 101 is configured to store various types of data to support operations in the electronic terminal device. Examples of these data include instructions for any application or method operated on the electronic terminal device, contact data, phone book data, messages, pictures, videos, etc. The memory 101 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable and Programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
电源模块102为电子终端设备的各种模块提供电力。电源模块102可以包括电源管理***，一个或多个电源，及其他与为电子终端设备生成、管理和分配电力相关联的模块。交互组件103包括在电子终端设备和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与触摸或滑动操作相关的持续时间和压力。在一些实施例中，交互组件103包括一个前置摄像头和/或后置摄像头。当电子终端设备处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜***或具有焦距和光学变焦能力。The power supply module 102 provides power for various modules of the electronic terminal device. The power supply module 102 may include a power management system, one or more power supplies, and other modules associated with generating, managing, and distributing power for electronic terminal devices. The interaction component 103 includes a screen that provides an output interface between the electronic terminal device and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of the touch or slide action, but also detect the duration and pressure related to the touch or slide operation. In some embodiments, the interactive component 103 includes a front camera and/or a rear camera. When the electronic terminal device is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
交互组件103还包括音频模块被配置为输出和/或输入音频信号。例如，音频模块包括一个麦克风(MIC)，当电子终端设备处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器101或经由通信模块104发送。在一些实施例中，音频模块还包括一个扬声器，用于输出音频信号。接口106为I/O的接口为处理器100和***接口模块之间提供接口，上述***接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。The interactive component 103 also includes an audio module configured to output and/or input audio signals. For example, the audio module includes a microphone (MIC). When the electronic terminal device is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal may be further stored in the memory 101 or transmitted via the communication module 104. In some embodiments, the audio module further includes a speaker for outputting audio signals. The interface 106 is an I/O interface that provides an interface between the processor 100 and a peripheral interface module. The above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
传感器模块105包括一个或多个传感器，用于为电子终端设备提供各个方面的状态评估。例如，传感器模块105可以检测到电子终端设备的打开/关闭状态，模块的相对定位，例如组件为电子终端设备的显示器和小键盘，传感器模块105还可以检测电子终端设备或电子终端设备一个组件的位置改变，用户与电子终端设备接触的存在或不存在，电子终端设备方位或加速/减速和其温度变化。传感器模块105可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器模块105还可以包括光传感器，如CMOS或CCD图像传感器 ，用于在成像应用中使用。在一些实施例中，该传感器模块105还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。通信模块104被配置为便于电子终端设备和其他设备之间有线或无线方式的通信。电子终端设备可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信模块104经由广播信道接收来自外部广播管理***的广播信号或广播相关信息。在一个示例性实施例中，通信模块104还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。The sensor module 105 includes one or more sensors for providing various aspects of state evaluation for the electronic terminal device. For example, the sensor module 105 can detect the on/off status of the electronic terminal device and the relative positioning of the modules, such as the display and keypad of the electronic terminal device. The sensor module 105 can also detect the electronic terminal device or a component of the electronic terminal device. The position changes, the presence or absence of contact between the user and the electronic terminal device, the orientation or acceleration/deceleration of the electronic terminal device and its temperature change. The sensor module 105 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact. The sensor module 105 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor module 105 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor. The communication module 104 is configured to facilitate wired or wireless communication between the electronic terminal device and other devices. Electronic terminal devices can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination of them. In an exemplary embodiment, the communication module 104 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication module 104 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
其他方面，基于同一发明构思，本申请一实施例还提供一种计算机可读存储介质，包含：所述计算机可读存储介质上存储有人脸识别程序，所述人脸识别程序被处理器执行时实现如上文所述的人脸识别方法的步骤。In other aspects, based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, including: a face recognition program is stored on the computer-readable storage medium, and when the face recognition program is executed by a processor Implement the steps of the face recognition method as described above.
本申请实施方式的计算机可读存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于电、磁、光、电磁、红外线或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机硬盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其组合使用。The computer-readable storage medium of the embodiment of the present application may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言-诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言-诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。The computer program code used to perform the operations of this application can be written in one or more programming languages or a combination thereof. The programming languages include object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect via the Internet) ).
应当注意的是，在本文的实施方式中所揭露的装置和方法，也可以通过其他的方式实现。以上所描述的装置实施方式仅仅是示意性的，例如，附图中的流程图和框图显示了根据本文的多个实施方式的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用于执行规定的功能或动作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。It should be noted that the devices and methods disclosed in the embodiments herein can also be implemented in other ways. The device implementations described above are merely illustrative. For example, the flowcharts and block diagrams in the drawings show the possible implementation architecture, functions, and operations of the devices, methods, and computer program products according to the multiple implementations herein. . In this regard, each block in the flowchart or block diagram may represent a module, program or part of the code, and the module, program segment or part of the code contains one or more options for realizing the specified logical function. Executing instructions, the module, program segment, or part of the code includes one or more executable instructions for realizing specified logic functions. It should also be noted that in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be used in a dedicated hardware-based system that performs the specified functions or actions. It can be realized, or it can be realized by a combination of dedicated hardware and computer instructions.
另外，在本文各个实施方式中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。In addition, the functional modules in the various embodiments herein may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
综上所述，本申请一方面通过一实施例提供了一种人脸识别方法，包含以下过程：获取待识别目标人像图像；根据判断规则提取所述目标人像图像的识别信息，根据识别信息生成所述目标人像的显示信息。即具体的是通过将待识别目 标人像图像进行姿态判断，当判断结果为自由姿态时，可以通过矫正该待识别目标人像图像的姿态，并利用经矫正过的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配使得人脸识别不受相机拍照环境的影响，提高了人脸识别精度。同时，还可根据用户自愿的信息共享，即当用户认为当前识别出的年龄信息不符合实际年龄时，上传信息，上传信息后，所述特征数据库当中的至少一个样品信息进行了更新，之后，再以将待识别目标人像图像与更新后的特征数据库中的人脸图像样本进行匹配，以此提高年龄识别的准确率。In summary, on the one hand, the present application provides a face recognition method through an embodiment, which includes the following processes: acquiring a target portrait image to be recognized; extracting the recognition information of the target portrait image according to the judgment rule, and generating according to the recognition information The display information of the target person. Specifically, the posture of the target image to be recognized is judged. When the result of the judgment is a free posture, the posture of the target image to be recognized can be corrected, and the corrected image of the target person to be recognized and the feature database can be used Matching of face image samples makes face recognition not affected by the camera's photographing environment, and improves the accuracy of face recognition. At the same time, it can also be based on the user's voluntary information sharing, that is, when the user believes that the currently identified age information does not meet the actual age, upload the information. After uploading the information, at least one sample information in the characteristic database is updated, and then, Then, the target portrait image to be recognized is matched with the facial image samples in the updated feature database, so as to improve the accuracy of age recognition.
另一方面，本申请还通过另一实施例提供了一种人脸识别方法，包含：获取待识别目标人像图像；识别并显示所述目标人像的显示信息；当终端收到显示信息错误信号；捕获新输入信息，将新输入信息导入特征数据库更新。由此可知，本申请的特征数据库具有学习能力，其可以是为自适应性的可不断更新的特征数据库，采用如上所述的人脸识别方法来识别人脸时，可以提高人脸识别精度，提高用户体验。On the other hand, the present application also provides a face recognition method through another embodiment, including: acquiring a target portrait image to be recognized; identifying and displaying display information of the target portrait; when the terminal receives a display information error signal; Capture new input information and import the new input information into the feature database to update. It can be seen from this that the feature database of the present application has learning capabilities, and it can be an adaptive feature database that can be continuously updated. When the above-mentioned face recognition method is used to recognize faces, the accuracy of face recognition can be improved. Improve user experience.
以上所述，仅是本申请的较佳实施例而已，并非对本申请作任何形式上的限制，虽然本申请已以较佳实施例揭露如上，然而并非用以限定本申请，任何熟悉本专业的技术人员，在不脱离本申请技术方案范围内，当可利用上述揭示的技术内容作出些许更动或修饰为等同变化的等效实施例，但凡是未脱离本申请技术方案内容，依据本申请的技术实质对以上实施例所作的任何简单修改、等同变化与修饰，均仍属于本申请技术方案的范围内。The above are only the preferred embodiments of the application, and do not limit the application in any form. Although the application has been disclosed as the preferred embodiments, it is not intended to limit the application. Anyone familiar with the profession Technical personnel, without departing from the scope of the technical solution of the present application, can use the technical content disclosed above to make slight changes or modifications to equivalent embodiments with equivalent changes, provided that the content of the technical solution of the present application is not deviated from the technical solution of the present application. Any simple modifications, equivalent changes, and modifications made to the above embodiments by technical essence still fall within the scope of the technical solutions of the present application.

Claims (16)

  1. 一种人脸识别方法，其中，所述人脸识别方法包含以下过程：A face recognition method, wherein the face recognition method includes the following processes:
    获取待识别目标人像图像；Obtain a portrait image of the target to be recognized;
    判断所述待识别目标人像图像中的人像姿态；Judging the portrait posture in the portrait image of the target to be recognized;
    根据所述人像姿态判断结果提取所述目标人像图像的识别信息，根据识别信息生成所述目标人像的显示信息。The identification information of the target portrait image is extracted according to the judgment result of the portrait posture, and the display information of the target portrait is generated according to the identification information.
  2. 如权利要求1所述的人脸识别方法，其中，所述判断所述待识别目标人像图像中的人像姿态是否为标准姿态；若是，则将所述待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述显示信息，The face recognition method according to claim 1, wherein said judging whether the portrait posture in the target portrait image to be recognized is a standard posture; if so, comparing the target portrait image to be recognized with the person in the feature database Face image samples are matched to obtain the display information,
    若否，则调用姿态矫正模型库，对所述待识别目标人像图像进行矫正，得到近似标准姿态的待识别目标人像图像，并将所述近似标准姿态的待识别目标人像图像与特征数据库中的人脸图像样本进行匹配，得到所述识别信息；If not, call the posture correction model library to correct the target portrait image to be recognized to obtain a target portrait image similar to the standard posture, and compare the target portrait image similar to the standard posture with the information in the feature database. Matching the face image samples to obtain the identification information;
    查找特征数据库，得到所述匹配的人脸图像样本对应的显示信息。The feature database is searched to obtain the display information corresponding to the matched face image sample.
  3. 如权利要求1所述的人脸识别方法，其中，所述识别信息为匹配的人脸图像样本。The face recognition method according to claim 1, wherein the identification information is a matching face image sample.
  4. 如权利要求1所述的人脸识别方法，其中，当所述待识别目标人像图像和与其相匹配的人脸图像样本的相似度未超过设定阈值时，还包括：采用年龄估算法根据所述待识别目标人像图像估计用户年龄。The face recognition method according to claim 1, wherein, when the similarity between the human face image sample to be recognized and the face image sample matching it does not exceed a set threshold, the method further comprises: adopting an age estimation method according to all The portrait image of the target to be recognized estimates the age of the user.
  5. 如权利要求1或4所述的人脸识别方法，其中，所述显示信息为用户信息，包括该用户的年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。The face recognition method according to claim 1 or 4, wherein the display information is user information, including one of the user’s age information, hobby information, facial features information, skin color information, skin state information, or Any combination.
  6. 如权利要求5所述的人脸识别方法，其中，The face recognition method according to claim 5, wherein:
    当所述显示信息错误时，纠正所述显示信息，更新所述特征数据库。When the display information is wrong, the display information is corrected and the characteristic database is updated.
  7. 如权利要求6所述的人脸识别方法，其中，所述纠正所述显示信息的步骤包括：当所述年龄信息误差不处于预设范围时，手动修改所述显示信息。8. The face recognition method of claim 6, wherein the step of correcting the displayed information comprises: manually modifying the displayed information when the error of the age information is not within a preset range.
  8. 一种人脸识别方法，其中，包含：A face recognition method, which includes:
    获取待识别目标人像图像；Obtain a portrait image of the target to be recognized;
    识别并显示所述目标人像的显示信息；Identify and display the display information of the target person;
    当终端收到显示信息错误信号；When the terminal receives a display information error signal;
    捕获新输入信息，将新输入信息导入特征数据库更新。Capture new input information and import the new input information into the feature database to update.
  9. 如权利要求8所述的人脸识别方法，其中，在将所述新输入信息导入所述特征数据库更新后，还包括显示新显示信息的步骤，所述显示信息包括用户年龄信息、爱好信息、五官特征信息、肤色信息、皮肤状态信息中的一种或其任意一组合。The face recognition method according to claim 8, wherein after the new input information is imported into the feature database to update, it further comprises the step of displaying the new display information, the display information including the user’s age information, hobby information, One or any combination of facial features information, skin color information, and skin state information.
  10. 如权利要求8所述的人脸识别方法，其中，所述终端捕获新输入信息的方式包括语音输入、文件导入和文字键入中的一种或其任意一组合。8. The face recognition method according to claim 8, wherein the method for the terminal to capture new input information includes one or any combination of voice input, file import, and text input.
  11. 如权利要求8所述的人脸识别方法，其中，所述终端收到显示信息错误信号的步骤具体包括：用户主动触控显示信息以提醒显示信息错误或终端捕获并判断用户情绪信息获得显示信息错误信号。The face recognition method according to claim 8, wherein the step of the terminal receiving a display information error signal specifically includes: the user actively touches the display information to remind the display information error or the terminal captures and judges the user’s emotional information to obtain the display information Error signal.
  12. 如权利要求11所述的人脸识别方法，其中，所述终端捕获并判断用户情绪信息获得显示信息错误信号具体步骤包括：The face recognition method according to claim 11, wherein the specific steps of the terminal capturing and judging the user's emotion information to obtain the display information error signal include:
    终端显示所述目标人像的显示信息后，调用终端拍摄组件、语音输入组件或红外传感器，获取用户看到所述显示信息后的表情、声音，判断用户的情绪信息。After the terminal displays the display information of the target portrait, it calls the terminal shooting component, voice input component or infrared sensor to obtain the user's expression and sound after seeing the display information, and judge the user's emotional information.
  13. 一种人脸识别方法，其中，包含：A face recognition method, which includes:
    获取预览界面中的待识别对象；Obtain the object to be recognized in the preview interface;
    采集所述待识别对象的像素集合；Collecting the pixel set of the object to be identified;
    根据所述像素集合判断待识别对象的识别信息；Judging the identification information of the object to be identified according to the pixel set;
    根据所述识别信息生成所述待识别对象的显示信息。The display information of the object to be identified is generated according to the identification information.
  14. 如权利要求13所述的人脸识别方法，其中，在采集所述待识别对象的像素集合后，还包括根据所述像素集合对待识别对象进行分类的步骤，所述待识别对象为待识别目标人像图像。The face recognition method according to claim 13, wherein after collecting the pixel set of the object to be recognized, it further comprises a step of classifying the object to be recognized according to the pixel set, and the object to be recognized is the object to be recognized Portrait image.
  15. 一种电子终端设备，其中，包括：处理器，存储器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现如权利要求1～14中任意一项所述的人脸识别方法。An electronic terminal device, comprising: a processor, a memory, and a computer program stored on the memory and running on the processor, and the processor executes the program as claimed in claims 1-14 The face recognition method described in any one of.
  16. 一种计算机可读存储介质，其中，包含：所述计算机可读存储介质上存储有人脸识别程序，所述人脸识别程序被处理器执行时实现如权利要求1～14中任意一项所述的人脸识别方法的步骤。A computer-readable storage medium, comprising: storing a face recognition program on the computer-readable storage medium, and when the face recognition program is executed by a processor, the face recognition program is implemented as described in any one of claims 1 to 14 The steps of the face recognition method.
PCT/CN2019/122508 2019-09-11 2019-12-02 Face recognition method and electronic terminal device WO2021047069A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910858770.2A CN110717399A (en) 2019-09-11 2019-09-11 Face recognition method and electronic terminal equipment
CN201910858770.2 2019-09-11

Publications (1)

Publication Number Publication Date
WO2021047069A1 true WO2021047069A1 (en) 2021-03-18

Family

ID=69209847

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/122508 WO2021047069A1 (en) 2019-09-11 2019-12-02 Face recognition method and electronic terminal device

Country Status (2)

Country Link
CN (1) CN110717399A (en)
WO (1) WO2021047069A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420666A (en) * 2021-06-23 2021-09-21 上海应用技术大学 Memory assisting method and device based on face recognition technology
CN114049658A (en) * 2021-09-18 2022-02-15 特斯联科技集团有限公司 Floating population management method and device based on face recognition, computer equipment and storage medium
CN114140856A (en) * 2021-12-07 2022-03-04 广联达科技股份有限公司 Face recognition method, device, system, computer equipment and readable storage medium
CN114283464A (en) * 2021-11-26 2022-04-05 珠海格力电器股份有限公司 Method and system for improving face recognition and intelligent terminal
CN114821513A (en) * 2022-06-29 2022-07-29 威海凯思信息科技有限公司 Image processing method and device based on multilayer network and electronic equipment
CN115471893A (en) * 2022-09-16 2022-12-13 北京百度网讯科技有限公司 Method and device for training face recognition model and face recognition

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428576B (en) * 2020-03-02 2024-04-26 广州微盾科技股份有限公司 Feature information learning method, electronic device and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989331A (en) * 2015-02-11 2016-10-05 佳能株式会社 Facial feature extraction apparatus, facial feature extraction method, image processing equipment and image processing method
US20170140210A1 (en) * 2015-11-16 2017-05-18 Canon Kabushiki Kaisha Image processing apparatus and image processing method
CN107622261A (en) * 2017-11-03 2018-01-23 北方工业大学 Face age estimation method and device based on deep learning
CN109977781A (en) * 2019-02-26 2019-07-05 上海上湖信息技术有限公司 Method for detecting human face and device, readable storage medium storing program for executing

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102917120A (en) * 2012-09-20 2013-02-06 北京百纳威尔科技有限公司 Mobile terminal and method for refreshing information displayed by mobile terminal
CN107133576A (en) * 2017-04-17 2017-09-05 北京小米移动软件有限公司 Age of user recognition methods and device
CN108229420B (en) * 2018-01-22 2020-10-16 维沃移动通信有限公司 Face recognition method and mobile terminal
CN109583972A (en) * 2018-12-19 2019-04-05 中新智擎科技有限公司 A kind of advertisement demonstration method, device, advertisement robot and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989331A (en) * 2015-02-11 2016-10-05 佳能株式会社 Facial feature extraction apparatus, facial feature extraction method, image processing equipment and image processing method
US20170140210A1 (en) * 2015-11-16 2017-05-18 Canon Kabushiki Kaisha Image processing apparatus and image processing method
CN107622261A (en) * 2017-11-03 2018-01-23 北方工业大学 Face age estimation method and device based on deep learning
CN109977781A (en) * 2019-02-26 2019-07-05 上海上湖信息技术有限公司 Method for detecting human face and device, readable storage medium storing program for executing

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420666A (en) * 2021-06-23 2021-09-21 上海应用技术大学 Memory assisting method and device based on face recognition technology
CN114049658A (en) * 2021-09-18 2022-02-15 特斯联科技集团有限公司 Floating population management method and device based on face recognition, computer equipment and storage medium
CN114283464A (en) * 2021-11-26 2022-04-05 珠海格力电器股份有限公司 Method and system for improving face recognition and intelligent terminal
CN114140856A (en) * 2021-12-07 2022-03-04 广联达科技股份有限公司 Face recognition method, device, system, computer equipment and readable storage medium
CN114821513A (en) * 2022-06-29 2022-07-29 威海凯思信息科技有限公司 Image processing method and device based on multilayer network and electronic equipment
CN115471893A (en) * 2022-09-16 2022-12-13 北京百度网讯科技有限公司 Method and device for training face recognition model and face recognition
CN115471893B (en) * 2022-09-16 2023-11-21 北京百度网讯科技有限公司 Face recognition model training, face recognition method and device

Also Published As

Publication number Publication date
CN110717399A (en) 2020-01-21

Similar Documents

Publication Publication Date Title
WO2021047069A1 (en) Face recognition method and electronic terminal device
TW202105199A (en) Data update method, electronic device and storage medium thereof
WO2020000961A1 (en) Method, device, and server for image tag identification
EP3179408A2 (en) Picture processing method and apparatus, computer program and recording medium
US10115019B2 (en) Video categorization method and apparatus, and storage medium
CN106572299A (en) Camera switching-on method and device
CN105357425B (en) Image capturing method and device
CN109934275B (en) Image processing method and device, electronic equipment and storage medium
CN108712603B (en) Image processing method and mobile terminal
CN110287671B (en) Verification method and device, electronic equipment and storage medium
CN109360197B (en) Image processing method and device, electronic equipment and storage medium
TWI757668B (en) Network optimization method and device, image processing method and device, storage medium
WO2022227393A1 (en) Image photographing method and apparatus, electronic device, and computer readable storage medium
CN108833262B (en) Session processing method, device, terminal and storage medium
WO2019153925A1 (en) Searching method and related device
WO2018098860A1 (en) Photograph synthesis method and apparatus
EP3975046A1 (en) Method and apparatus for detecting occluded image and medium
TW202009761A (en) Identification method and apparatus and computer-readable storage medium
TWI752105B (en) Feature image acquisition method, acquisition device, and user authentication method
CN107038428A (en) Vivo identification method and device
WO2016188065A1 (en) Cloud business card recommendation method and apparatus
CN110399934A (en) A kind of video classification methods, device and electronic equipment
CN111144266A (en) Facial expression recognition method and device
CN107169429A (en) Vivo identification method and device
US20220270352A1 (en) Methods, apparatuses, devices, storage media and program products for determining performance parameters

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: 19945051

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19945051

Country of ref document: EP

Kind code of ref document: A1