WO2020215250A1 - 人脸注册方法、人脸识别装置、识别设备和可存储介质 - Google Patents

人脸注册方法、人脸识别装置、识别设备和可存储介质 Download PDF

Info

Publication number
WO2020215250A1
WO2020215250A1 PCT/CN2019/084083 CN2019084083W WO2020215250A1 WO 2020215250 A1 WO2020215250 A1 WO 2020215250A1 CN 2019084083 W CN2019084083 W CN 2019084083W WO 2020215250 A1 WO2020215250 A1 WO 2020215250A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
mobile terminal
registration
recognition device
collected
Prior art date
Application number
PCT/CN2019/084083
Other languages
English (en)
French (fr)
Inventor
李明采
王波
Original Assignee
深圳市汇顶科技股份有限公司
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 深圳市汇顶科技股份有限公司 filed Critical 深圳市汇顶科技股份有限公司
Priority to CN201980000570.1A priority Critical patent/CN110249340A/zh
Priority to PCT/CN2019/084083 priority patent/WO2020215250A1/zh
Publication of WO2020215250A1 publication Critical patent/WO2020215250A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • 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

Definitions

  • This application relates to the field of face recognition technology, and in particular to a face registration method, face recognition device, recognition device and storage medium.
  • Face recognition is a kind of biometric recognition technology based on human facial feature information.
  • a series of related technologies that use a video camera or camera to collect images or video streams containing faces, and automatically detect and track faces in the images, and then perform facial recognition on the detected faces, usually also called face recognition and facial recognition .
  • 3D face recognition is the basis for using 3D face recognition to unlock mobile phones/door locks. It is mainly to build a private database (face photos, 3D facial data or features extracted from photos ⁇ 3D information) inside the module. When using a similar unlocking function, the real-time collected data is compared with the established private database to determine whether the data is the same person's data in the database, so as to determine whether to authorize.
  • 3D face recognition builds a 3D face model by acquiring depth information and 2D face images. Compared with 2D face recognition, 3D face recognition has a high recognition rate, high security, more accuracy and efficiency.
  • the inventor of the present application found that the application of 3D face recognition to the door lock solution needs to address the way of interacting with the user, especially the solution of interacting with the user when registering the face information.
  • the application scenario of the door lock needs to be considered.
  • the face door lock system is equipped with a display screen. During the process of user registration, the face image collected by the user is displayed in real time and the relevant registration information is prompted. For the door lock system, the display screen increases the door lock The hardware cost and the higher power consumption during use make the standby period of the door lock shorter, which brings a bad experience to the user.
  • the purpose of some embodiments of this application is to provide a face registration method, face recognition device, recognition device, and storage medium, so as to reduce the hardware of the face recognition device and reduce the hardware cost while ensuring user experience as much as possible.
  • the embodiment of the present application provides a face registration method, including: collecting a face picture; transmitting the collected face picture to a mobile terminal independent of the face recognition device for real-time display by the mobile terminal Integrate the collected face pictures to obtain 3D face registration data; send information indicating the completion of registration to the mobile terminal.
  • the embodiment of the present application also provides a face recognition device, including: a collection module, including: a 2D image collection unit and a depth information collection unit, used to collect face pictures; a communication module, used to collect the collected face pictures Transmitted to a mobile terminal independent of the face recognition device for real-time display by the mobile terminal, and also used to send information indicating the completion of registration to the mobile terminal after registration is completed; first processing The module is used to fuse the collected face pictures to obtain 3D face registration data.
  • a collection module including: a 2D image collection unit and a depth information collection unit, used to collect face pictures
  • a communication module used to collect the collected face pictures Transmitted to a mobile terminal independent of the face recognition device for real-time display by the mobile terminal, and also used to send information indicating the completion of registration to the mobile terminal after registration is completed
  • first processing is used to fuse the collected face pictures to obtain 3D face registration data.
  • An embodiment of the present application also provides a face recognition device, including: at least one processor; and, a memory communicatively connected with the at least one processor; wherein the memory stores the memory that can be used by the at least one processor.
  • the executed instruction is executed by the at least one processor, so that the at least one processor can execute the aforementioned face registration method.
  • the embodiment of the present application also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the above-mentioned face registration method is implemented.
  • the embodiment of the application now transmits the collected face picture to the mobile terminal during the face registration process, so that the user can see his preview screen in real time through the mobile terminal during the registration process.
  • No need to view through the face recognition device so that the display device of the face recognition device can be removed, so as to reduce the hardware volume of the face recognition device, reduce the cost of the face recognition device, and ensure that the user has a better experience .
  • the communication of data is one-way, which will not cause excessive interaction and binding between the device and the mobile terminal, which reduces the complexity of the entire system and facilitates the independent design and design of the device and the mobile phone. Production is conducive to large-scale commercial use of products.
  • the transferring the collected face pictures to the mobile terminal specifically includes: transferring part of the pictures in the collected face pictures to the mobile terminal.
  • transferring part of the pictures in the collected face pictures to the mobile terminal only part of the picture is transmitted, not all pictures, which reduces the amount of transmitted data.
  • part of the pictures transmitted is at least 20 per second. Since the frame rate of the mobile terminal exceeds 20 to ensure the dynamic effect when displaying, this embodiment reduces the amount of transmitted data while ensuring the preview experience of the user.
  • the processing of the collected face picture specifically includes: when the prompt information needs to be sent, the prompt information is transmitted to the mobile terminal for the mobile terminal to prompt in real time. Since 3D face registration has higher requirements for the collected image data and needs to prompt the user in real time, this embodiment also sends the information to be prompted to the mobile terminal to ensure the smooth display of the prompt information to the user during the registration process. Ensure registration accuracy.
  • a reminder message needs to be issued in the following situations: the collected face pictures do not meet the registration requirements.
  • the prompt information includes: information prompting the user to adjust the posture and/or adjust the position.
  • This embodiment clearly prompts when the face image does not meet the registration requirements, and tries to ensure the accuracy of the registration process.
  • the collected face picture before transferring the collected face picture to the mobile terminal, it further includes: determining whether the face picture meets the registration requirements; when it is determined that the face picture meets the registration requirements, executing the collection Steps of transferring the received face picture to the mobile terminal.
  • the face picture is transmitted when it meets the registration requirements, so as to avoid transmitting the wrong picture, thereby preventing the user from viewing the wrong picture.
  • the face picture is collected, it is determined whether it is in communication with a mobile terminal; if it is in communication with a mobile terminal, the step of collecting the face picture is executed. In this embodiment, as much as possible to ensure that the face image can be successfully transmitted during registration.
  • the step of determining whether to communicate with a mobile terminal is executed.
  • This embodiment clearly detects the timing of the communication connection.
  • the registration data After the registration data is obtained, it includes: recognizing the collected face picture and obtaining the recognition result.
  • Fig. 1 is a flowchart of a face registration method according to the first embodiment of the present application
  • FIG. 2 is a schematic diagram of an example in which a face recognition device is applied to a door lock in the face registration method in the first embodiment of the present application;
  • Fig. 3 is a flowchart of a face registration method according to a second embodiment of the present application.
  • Fig. 4 is a flowchart of a face registration method according to a third embodiment of the present application.
  • Fig. 5 is a schematic structural diagram of a face recognition device in a fourth embodiment of the present application.
  • Fig. 6 is a schematic structural diagram of a face recognition device according to a fifth embodiment of the present application.
  • the first embodiment of the present application relates to a face registration method.
  • This embodiment can be applied to a face recognition device.
  • a smart door lock when a new user is added (that is, a new user is registered), the smart door lock needs to enter new user information, specifically the face of the new user Data is collected, processed, and stored in the user database, so that when the new user needs to open or close the smart door lock, he stands in front of the smart door lock, and the camera device of the smart door lock collects facial information and recognizes it.
  • FIG. 1 The specific process of the face registration method in this embodiment is shown in FIG. 1.
  • Step 101 Collect a face picture.
  • the camera device that comes with the smart door lock is used to collect face pictures.
  • the camera device starts shooting, and after collecting a picture, it first performs 2D face detection to determine whether there is a person. Face, if there is a human face, proceed to the following steps. If there is no human face, the shooting may be wrong. If an incomplete human face is captured or a human face that is not clear enough is captured, then return to recapture the picture.
  • the deep learning method can be used for 2D face detection.
  • the deep learning method is used to obtain the facial features required for a complete 2D face, and the facial features obtained by the deep learning method are used for comparison during detection. Detection, if the collected picture meets these facial features, it is considered that there is a human face in the collected picture, otherwise, it is considered that there is no human face.
  • the facial features can be whether there are eyes, whether the number of eyes is two, whether there is a nose, whether the number of noses is one, the contour shape can be the possible shape of the eyes, the possible shape of the nose, and it can also include eyes and nose. The relative positions of, etc. will not be listed here.
  • Step 102 Transmit the collected face picture to the mobile terminal.
  • the face image is specifically transmitted via wifi.
  • the mobile terminal can be a mobile user terminal with a display such as a mobile phone, a tablet PC, etc., such as a mobile phone.
  • the face recognition device can be a smart door lock fixed on the anti-theft door.
  • the face recognition device and the mobile terminal are two independent devices. In an example, take a mobile phone as an example. After the mobile phone and the face recognition device are connected through wifi, the face recognition device collects the face picture, and then transmits the face picture to the wireless module (wireless communication module). The mobile phone, the mobile phone directly displays the face picture after receiving it, so as to minimize the picture that the user sees and the actual time delay. In this way, the operating convenience of fixed installation equipment can be improved with the convenience of the mobile terminal, and the hardware cost of the fixed installation equipment does not need to be increased.
  • part of the collected face pictures are transferred to a mobile terminal independent of the face recognition device. There is no need to transfer all the collected pictures to the mobile terminal.
  • the collection frequency is relatively high.
  • the frame rate of playing pictures is 20 frames per second. , You can ensure that the dynamic effects you see are relatively smooth and not stuck.
  • part of the pictures to be transmitted can be selected from the face pictures collected every second, at least 20 pictures per second, such as 30 pictures per second, that is, one picture is transmitted every 2 seconds, other facial pictures are not transmitted To the mobile terminal, photos that are not transmitted will still participate in the subsequent processing of the face recognition device. In this way, the amount of transmitted pictures can be significantly reduced, which reduces the transmission pressure and ensures the user's viewing experience.
  • a dedicated APP can be installed on the mobile phone, and the wireless module performs data transmission with the mobile phone APP when the face recognition module collects face pictures.
  • the face picture can be subjected to simple picture processing before transmission, such as blurring the background, sharpening the face, etc., to make the displayed face picture clearer.
  • Step 103 Fuse the collected face pictures to obtain 3D registration data of the face.
  • the face images collected multiple times are merged, which includes superimposing, combining, and deduplicating face feature data to form a fused face model, and obtain the face data in the registration data according to the fused data .
  • the registration data can include account name, password and other information, which will not be repeated here.
  • the number of acquisitions can be judged after fusion. During the registration of the 3D face, a certain number of acquisitions can be preset to ensure that a sufficient amount of data is collected. If it is determined after one fusion that the number of collections has not reached the predetermined value, return to step 101 to continue collection until the number of collections is reached, and the data obtained after the last fusion is the face data in the registration data.
  • Step 104 Send information indicating the completion of registration to the mobile terminal.
  • the registration process After the integration is completed, if the registration process is completed, then information indicating that the registration is complete can be generated.
  • the above information is also sent to the mobile terminal, which is displayed in real time by the mobile terminal, which can prompt the user that the registration has been completed and does not need to be maintained Standing position.
  • the information used to indicate the completion of the registration may include text prompts, voice prompts, etc., in another example, it may also include a preview of the registered information, such as a merged face, account information, and so on.
  • a recognition step may also be included, specifically: recognizing the collected face picture to obtain the recognition result. It can be seen that during recognition, the newly collected face image is compared with the face data in the pre-stored registration information, and the feature parameters of the face are specifically compared. In the example of applying the face recognition device to the door lock, after the comparison is passed, the passed result is sent to the door lock control module to control the opening or closing of the door lock.
  • the 3D face recognition door lock system includes: a door lock control module, a face Recognition control module and 3D face acquisition module.
  • the 3D face acquisition module transmits the collected face pictures to the face recognition control module, and the face recognition control module processes, detects and compares the received face pictures Peer steps, and transmit the processing results to the door lock control module, and the door lock control module controls the opening or closing of the door lock.
  • the user side can use the APP on the mobile terminal to interact with the 3D face recognition door lock system.
  • this embodiment transmits the collected face picture to the mobile terminal during the face registration process, so that the user can see his own preview screen in real time through the mobile terminal during the registration process, without View through the face recognition device, so that the display device of the face recognition device can be removed, so that the hardware volume of the face recognition device is reduced, the cost of the face recognition device is reduced, and the user has a better user experience.
  • the communication of data is one-way, which will not cause excessive interaction and binding between the device and the mobile terminal, which reduces the complexity of the entire system and facilitates the independent design and design of the device and the mobile phone. Production is conducive to large-scale commercial use of products.
  • the face registration method is applied to a face recognition device as an example.
  • the face registration method in this embodiment can also be applied to a server.
  • the specific process may include: the server uses the face recognition device Collect face pictures, obtain a single picture and then perform face recognition, and judge whether the pictures containing faces collected multiple times in one registration are the same person, and it will be judged as multiple face pictures of the same person Perform data fusion, and finally obtain registration data.
  • the face image is transmitted through wifi when transmitting, but Bluetooth can also be used for transmission in practical applications, which will not be repeated here.
  • the second embodiment of the present application relates to a face registration method.
  • This embodiment is a further improvement on the basis of the first embodiment.
  • the main improvement is that in addition to displaying the collected face pictures, this embodiment can also be used in the process of processing the face pictures by the face recognition device. , Provide real-time prompts to users to further ensure the accuracy of data collection during registration.
  • Steps 301 to 302 are similar to steps 101 to 102 in the first embodiment, and will not be repeated here.
  • Step 303 Determine whether the collected face image meets the registration requirements; if yes, proceed to step 304; if not, proceed to step 306.
  • a complete face needs to be collected.
  • the way to determine whether the specific face is complete or whether the face is clear and recognizable can be the feature recognition method. If the predetermined facial feature can be recognized, the face in the face picture can be considered complete and recognizable.
  • other identification methods can also be used in practical applications, which will not be listed here.
  • the face image that meets the registration requirements can be limited to: the face in the face image needs to be from a real face. If the face image is collected from a photo or an avatar model, it will affect the subsequent data processing results Accuracy. Therefore, the qualified registration requirements include real human faces, which helps to improve the accuracy of subsequent processing results. Furthermore, as to how to judge that the face image is collected from the photo, it can be judged in the following ways:
  • the structured light image can be used for detection, which specifically includes: performing 3D reconstruction on the structured light image of the human face to obtain a reconstructed image; and detecting whether the human face in the face image is a living body according to the reconstructed image.
  • a structured light image is collected by a camera device, it can be judged whether the collected face is a real human face or a photo according to the converted 3D image. Since the photo is a two-dimensional object, if the photo is used as the collection object, It is impossible to obtain a 3D image with a normal stereoscopic effect, so in one example, it can be determined whether the object of collection is a real person or a photo according to whether the reconstructed image is a 3D image.
  • other methods can be used to determine whether the human face is from a real human face, which will not be repeated here.
  • Step 304 to step 305 are similar to step 103 to step 104 in the first embodiment, and will not be repeated here.
  • Step 306 Transmit the prompt information to the aforementioned mobile terminal.
  • a prompt message may be issued.
  • the prompt message may include information that prompts the user to adjust posture or position, and may also include the above two types. The combination of prompt information.
  • the face picture is on the left side of the entire picture, and the left side exceeds the picture area and cannot be collected, the user can be prompted to move some positions to the right, and the judgment will continue during the next collection. If the face picture collected next time meets the registration requirements, it will be explained The user has moved the location according to the instructions. If the face image collected next time still does not meet the registration requirements, the user will continue to be prompted.
  • the mobile terminal sends out prompts in real time after receiving the prompt information.
  • the prompts can be broadcast by voice, superimposed text display on the interface that displays the face picture, etc., which will not be listed here.
  • the face recognition device may have a built-in audio announcer, and when a prompt message needs to be sent out, a voice prompt can be played through the audio announcer to prompt the user.
  • step 306 After the above step 306 is executed, return to step 301 to collect the face picture again. It can be seen that when it is determined that the collected face image does not meet the registration requirements, subsequent image fusion is not performed.
  • this embodiment needs to send a prompt message when it is determined that the collected face picture does not meet the registration requirements.
  • a prompt message can also be sent under other circumstances, such as too many errors, image transmission failure, etc. I will not list them all here.
  • the step of determining whether the picture meets the requirements in this embodiment is after the step of transmitting the face picture.
  • the step of determining whether the picture meets the requirements can be set before the step of transmitting the face picture, so that Pictures that do not meet the registration requirements are no longer transmitted to the mobile terminal, so that the pictures viewed by the user are face pictures that meet the requirements, and a better viewing experience is obtained.
  • the above-mentioned feature data can be saved as a template, and then during the fusion, the templates can be fused.
  • multiple face pictures correspond to different angles of a face.
  • the templates are deeply fused according to the change of the face angle, and the data obtained after the last fusion is the face data in the registration data. .
  • the data volume in the template data is streamlined, it is also beneficial to reduce the data volume during processing.
  • the third embodiment of the present application relates to a face registration method.
  • This embodiment is a further improvement on the basis of the first embodiment.
  • the main improvement lies in: the detection of the new communication connection in this embodiment can make the face picture successfully transmitted during the registration process as much as possible, so that the user’s The experience remains unchanged.
  • Step 401 Detect whether it is in communication with a mobile terminal; if yes, continue to execute step 403; if not, execute step 402.
  • the user can connect to the wireless module of the face recognition device through the wifi module of the mobile phone, so first check whether there is a wifi connection between the user’s mobile phone and the face recognition device. If it is connected, it can be considered that the user is ready to start Register, continue to step 403, if not connected, it can be considered that the user has not yet arrived in the registration area, or is not yet ready, continue to step 402.
  • this step can trigger detection when the face recognition device is turned on, or when the registration starts.
  • the registration function can be activated through a predetermined function button, or through voice control, such as user dictation. Register, the face recognition device will start registration after receiving the voice command of "start registration".
  • the user can connect the Bluetooth module of the face recognition device through the Bluetooth module, and correspondingly, specifically detect whether there is a Bluetooth connection between the user's mobile phone and the face recognition device.
  • Step 402 Send a prompt message.
  • the voice prompt can be performed through the built-in voice announcer of the face recognition device. In practical applications, it can also be accompanied by simultaneous prompts such as the flashing of the LED indicator light.
  • the communication module of the face recognition device continues to send out a connection request broadcast for the mobile terminal to connect.
  • the prompt message may not be sent out, and only the broadcast of the connection request may continue to be sent for the mobile terminal to connect. If the connection is successful, the broadcast of the connection request may be stopped to prevent other devices from connecting by mistake.
  • step 402 After step 402, return to step 401.
  • Steps 403 to 406 in this embodiment are similar to steps 101 to 104 in the first embodiment, and will not be repeated here.
  • this embodiment pre-detects whether it is in communication with the mobile terminal, and starts the registration after the connection is determined, as far as possible to ensure that the face image can be successfully transmitted during registration, so as to avoid the situation that the user cannot see the image during registration.
  • the fourth embodiment of the present application relates to a face recognition device.
  • FIG. 5 The schematic diagram of the device in this embodiment is shown in FIG. 5, and specifically includes:
  • the collection module includes: a 2D image collection unit and a depth information collection unit, which are used to collect face pictures.
  • the communication module is used to transmit the collected face pictures to a mobile terminal independent of the face recognition equipment for real-time display of the mobile terminal. It is also used to send information indicating the completion of registration to Mobile terminal.
  • the first processing module is used to fuse the collected face pictures to obtain 3D face registration data.
  • this embodiment is a device example corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment.
  • the related technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they will not be repeated here.
  • the related technical details mentioned in this embodiment can also be applied in the first embodiment.
  • modules involved in this embodiment are all logical modules.
  • a logical unit can be a physical unit, a part of a physical unit, or multiple physical units. The combination of units is realized.
  • this embodiment does not introduce a unit that is not closely related to solving the technical problem proposed by the present invention, but this does not indicate that there are no other units in this embodiment.
  • the first processing module specifically includes: a prompt sub-module for determining whether prompt information needs to be sent; a trigger sub-module for sending prompt information to the communication module when prompt information needs to be sent; communication The module is also used to transmit the prompt information to the mobile terminal when the prompt information is received for real-time display by the mobile terminal.
  • the communication module is also used to determine whether to communicate with a mobile terminal; the collection module is specifically used to collect face pictures when the communication module determines to communicate with a mobile terminal.
  • the face recognition device further includes: a second processing module for determining whether the face image meets the registration requirements; when it is determined that the face image meets the registration requirements, triggering the communication module to execute the transfer of the collected face image To the mobile terminal.
  • the face recognition device is a face recognition device without a display function.
  • the face recognition device further includes: a third processing module for recognizing the collected face picture and obtaining the recognition result.
  • the fifth embodiment of the present invention relates to a face recognition device, as shown in FIG. 6, including:
  • At least one processor and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute as described above Any one of the face registration methods in the first embodiment to the fourth embodiment.
  • the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors and various circuits of the memory together.
  • the bus can also connect various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., which are all well-known in the art, and therefore, no further description will be given herein.
  • the bus interface provides an interface between the bus and the transceiver.
  • the transceiver may be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on the transmission medium.
  • the data processed by the processor is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor.
  • the processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions.
  • the memory can be used to store data used by the processor when performing operations.
  • the sixth embodiment of the present invention relates to a computer-readable storage medium storing a computer program.
  • the computer program is executed by the processor, the above method embodiment is realized.
  • the program is stored in a storage medium and includes several instructions to enable a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods in the embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Telephone Function (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种人脸注册方法、人脸识别装置、识别设备和可存储介质。其中，人脸注册方法应用于人脸识别设备，包括：采集人脸图片(101)；将采集到的人脸图片传送至独立于所述人脸识别设备之外的移动终端 (102)；融合采集到的人脸图片，获得人脸3D注册数据(103)；将用于指示注册完成的信息发送至所述移动终端(104)。还提供了人脸识别装置、人脸识别设备和计算机可读存储介质。采用上述方案，减少人脸识别设备的硬件体积，降低人脸识别设备的成本，同时又能保证用户有较好的使用体验。

Description

人脸注册方法、人脸识别装置、识别设备和可存储介质 技术领域
本申请涉及人脸识别技术领域，特别涉及一种人脸注册方法、人脸识别装置、识别设备和可存储介质。
背景技术
人脸识别，是基于人的脸部特征信息进行身份识别的一种生物识别技术。用摄像机或摄像头采集含有人脸的图像或视频流，并自动在图像中检测和跟踪人脸，进而对检测到的人脸进行脸部识别的一系列相关技术，通常也叫做人像识别、面部识别。
基于人脸识别技术的实际应用，需要先进行人脸注册，获取人脸图片数据，为增加人脸识别的准确性，现采用3D人脸识别技术，注册时对应地采用3D人脸注册。实际应用中，3D人脸注册是使用3D人脸识别进行手机/门锁解锁的基础，主要是在模块内部建立私有数据库(面部照片、面部三维数据或根据照片\三维信息提取的特征)，在使用类似解锁功能时，实时采集数据与所建立的私有数据库进行比对，判定该数据是否与数据库内是同一人的数据，从而决定是否授权通过。3D人脸识别通过获取深度信息以及2D人脸图像构建3D人脸模型，相比2D人脸识别，3D人脸识别具有识别率高、安全性高、更加精准、高效。
本申请发明人发现，3D人脸识别应用到门锁方案中需要解决与用户交互方式，特别是注册人脸信息时与用户交互的方案，同时还需要考虑门锁的应用场景，这样需要在人脸门锁系统中配置显示屏，在用户注册人脸的过程中，实时显示用户采集的人脸图像，并提示相关的注册信息，而显示屏对于门锁系统来讲，加大了门锁的硬件成本，在使用的过程中带来的功耗较高，使得门锁的待机周期变短，给用户带来了不良的体验。
发明内容
本申请部分实施例的目的在于提供一种人脸注册方法、人脸识别装置、识别设备和可存储介质，使得在尽量保证用户体验的前提下，减少人脸识别设备的硬件，降低硬件成本。
本申请实施例提供了一种人脸注册方法，包括：采集人脸图片；将采集到的人脸图片传送至独立于所述人脸识别设备之外的移动终端，供所述移动终端实时显示；融合采集到的人脸图片，获得人脸3D注册数据；将用于指示注册完成的信息发送至所述移动终端。
本申请实施例还提供了一种人脸识别装置，包括：采集模块，包括：2D图像采集单元和深度信息采集单元，用于采集人脸图片；通信模块，用于将采集到的人脸图片传送至独立于所述人脸识别设备之外的移动终端，供所述移动终端实时显示，还用于在注册完成后，将用于指示注册完成的信息发送至所述移动终端；第一处理模块，用于融合采集到的人脸图片，获得人脸3D注册数据。
本申请实施例还提供了一种人脸识别设备，包括：至少一个处理器；以 及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上述的人脸注册方法。
本申请实施例还提供了一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现如上述的人脸注册方法。
本申请实施例现对于现有技术而言，在人脸注册的过程中，将采集到的人脸图片传送至移动终端，使得用户在注册过程中可以通过移动终端实时看到自己的预览画面，无需通过人脸识别设备查看，从而使得人脸识别设备的显示设备得以去除，以至于减少人脸识别设备的硬件体积，降低人脸识别设备的成本，同时又能保证用户有较好的使用体验。另一方面，数据的沟通是单向的，不会在设备和手机终端之间产生过多的交互和绑定，降低了整个系统的复杂度，方便设备商和手机商各自独立的进行设计和生产，有利于产品规模化商用。
例如，所述将采集到的人脸图片传送至移动终端，具体为：将采集到的人脸图片中的部分图片传送至所述移动终端。本实施例在传送图片中仅传送部分，并非所有图片，减少传输数据量。
例如，传送的部分图片至少为每秒20张。由于移动终端在显示时，帧率超过20才能保证动态效果，本实施例在减少传输数据量的同时保证用户的预览体验。
例如，所述处理采集到的人脸图片，具体包括：在需发出提示信息时，将所述提示信息传送至所述移动终端，供所述移动终端实时提示。由于3D人脸注册时，对采集图像数据有较高的要求，需要对用户进行实时提示，本实施例将需提示的信息也发送至移动终端，保证注册过程中提示信息的顺利展示给 用户，保证注册准确性。
例如，在以下情况需发出提示信息：采集到的人脸图片不符合注册要求。
例如，所述提示信息包括：提示用户调整姿势和/或调整位置的信息。本实施例明确在人脸图片不符合注册要求时进行提示，尽量保证注册过程准确。
例如，所述将采集到的人脸图片传送至移动终端之前，还包括：判断所述人脸图片是否符合注册要求；在判定所述人脸图片符合所述注册要求时，执行所述将采集到的人脸图片传送至移动终端的步骤。本实施例明确在人脸图片符合注册要求时再传送，避免传送错误照片，从而避免用户查看到错误图片。
例如，所述采集人脸图片之前，判断是否与一移动终端通信连接；若与一移动终端通信连接，则执行所述采集人脸图片的步骤。本实施例尽可能保证注册时人脸图片可以成功传送出去。
例如，在所述人脸识别设备开机时，或者在注册功能键被触发时，执行所述判断是否与一移动终端通信连接的步骤。本实施例明确检测通信连接的时机。
例如，所述获得注册数据之后，包括：识别采集到的人脸图片，获得识别结果。
附图说明
一个或多张实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是根据本申请第一实施例中的人脸注册方法的流程图；
图2是根据本申请第一实施例中的人脸注册方法中以人脸识别设备应用于门锁为例的示意图；
图3是根据本申请第二实施例中的人脸注册方法的流程图；
图4是根据本申请第三实施例中的人脸注册方法的流程图；
图5是根据本申请第四实施例中的人脸识别装置的结构示意图；
图6是根据本申请第五实施例中的人脸识别设备的结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请部分实施例进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
本申请第一实施例涉及一种人脸注册方法。
本实施方式可以应用于一种人脸识别装置，以智能门锁为例，智能门锁在新增用户(即新用户注册)时，需要录入新用户信息，具体为将新增用户的人脸数据收集、处理、存储入用户数据库，从而在该新用户需要开启或关闭智能门锁时，站立于智能门锁前方，由智能门锁的摄像设备采集人脸信息并识别。
本实施例中人脸注册方法的具体流程如图1所示。
步骤101，采集人脸图片。
具体的说，本实施方式中通过智能门锁自带的摄像设备采集人脸图片，在一个例子中，摄像设备启动拍摄，采集到一张图片后，先进行2D人脸检测，判断是否存在人脸，如果存在人脸，则进行后续步骤，如果不存在人脸，可能拍摄出错，拍摄到不完全的人脸或拍摄到不够清晰的人脸，则返回重新采集图 片。
在一个例子中，可以采用深度学习法进行2D人脸检测，通过深度学习法获得一个完整的2D人脸所需包含的人脸特征，在检测时利用深度学习法得到的人脸特征进行比对检测，如果采集到的图片中符合这些人脸特征，就认为采集到的图片中存在人脸，否则，就认为不存在人脸。其中，人脸特征可以是是否有眼睛、眼睛的数量是否为两个、是否有鼻子、鼻子的数量是否为一个，轮廓形状可以是眼睛可能的形状，鼻子可能的形状，还可以包含眼睛和鼻子的相对位置等，在此不再一一列举。
步骤102，将采集到的人脸图片传送至移动终端。
具体的说，人脸图片具体通过wifi传送，移动终端可以是手机、平板电脑PAD等带显示屏的可移动用户终端，如手机，人脸识别设备可以是固定设置在防盗门上的智能门锁，人脸识别设备和移动终端是相互独立的两个设备。在一个例子中，以手机为例，手机和人脸识别设备通过wifi连接后，人脸识别设备在采集到人脸图片后，再通过内置的wireless模块(无线通信模块)将人脸图片传送至手机，手机收到人脸图片后直接进行显示，尽量减少用户看到的图片和实际的时延。如此，可以借助移动终端的便利性完善固定安装类设备的操作便利性，并且不需要增加固定安装类设备的硬件成本。
在一个例子中，将采集到的人脸图片中的部分图片传送至独立于人脸识别设备之外的移动终端，无需将所有采集到的图片都传送至移动终端，由于在采集时，采集模组为了保证人脸图片处理需要，采集频率较高，而移动终端显示照片时，只需保证动态的播放效果，所以并不需要这么高的图片帧率，一般播放图片的帧率在20帧/秒，即可保证看到的动态效果较为流畅不卡顿。对应 的，传送的部分图片可以从每秒采集到的人脸图片中选取，至少为每秒20张，如每秒选取30张，也就是每2秒传送一张，其他的人脸图片不传送至移动终端，不传送的照片仍会参与人脸识别设备后续的处理过程。这样，传送的图片量可以明显减少，即降低了传输压力，又能保证用户的观看体验。
在一个例子中，手机上可以装有专用APP，人脸识别模块在采集人脸图片的过程中，wireless模块与手机APP进行数据传输。
在一个例子中，人脸图片在传送前可以进行简单的图片处理，如虚化背景、锐化人脸等，使得显示的人脸图片更为清晰。
步骤103，融合采集到的人脸图片，获得人脸3D注册数据。
具体的说，将多次采集到的人脸图片融合，其中包括将人脸特征数据叠加、组合、去重，形成融合后的人脸模型，根据融合后的数据获得注册数据中的人脸数据。此外，注册数据可以包含账户名、密码等信息，在此不再赘述。
在一个例子中，融合后可以进行采集次数的判断，在3D人脸的注册过程中，可以预设一定量的采集次数，以保证采集到足够的数据量。如果在一次融合后判定出采集数未达到预定值，则返回步骤101继续采集，直到采集次数达到，获得的最后一次融合后的数据即为注册数据中的人脸数据。
步骤104，将用于指示注册完成的信息发送至移动终端。
在融合完成后，如注册过程完成，那么可以生成用于指示注册完成的信息，本实施方式中将上述信息同样发送至移动终端，由移动终端实时显示，可以提示用户注册已完成，无需继续保持站立姿势。在一个例子中，用于指示注册完成的信息可以包括文字提示、语音提示等，在另一个例子中，还可以包括注册信息的预览，如融合后的人脸、账号信息等等。
此外，本实施方式中，在注册完成后，还可以包括识别步骤，具体为：识别采集到的人脸图片，获得识别结果。可以看出，在识别时将新采集到的人脸影像和预存的注册信息中的人脸数据比对，具体比对人脸的特征参数。在将人脸识别设备应用于门锁的例子中，在比对通过后，将通过的结果发送给门锁控制模块，控制门锁开启或关闭。
以人脸识别设备应用于门锁为例，本实施方式可以采用如图2所示的硬件结构实现上述步骤101至步骤104，3D人脸识别门锁系统中包含：门锁控制模块、人脸识别控制模块、3D人脸采集模块，其中，3D人脸采集模块将采集到的人脸图片传输给人脸识别控制模块，人脸识别控制模块对收到的人脸图片进行处理、检测、比对等步骤，并将处理结果传输给门锁控制模块，由门锁控制模块控制门锁开或闭。用户侧可以使用移动终端上的APP和3D人脸识别门锁系统进行交互。
本实施例相对于现有技术而言，在人脸注册的过程中，将采集到的人脸图片传送至移动终端，使得用户在注册过程中可以通过移动终端实时看到自己的预览画面，无需通过人脸识别设备查看，从而使得人脸识别设备的显示设备得以去除，以至于减少人脸识别设备的硬件体积，降低人脸识别设备的成本，同时又能保证用户有较好的使用体验。另一方面，数据的沟通是单向的，不会在设备和手机终端之间产生过多的交互和绑定，降低了整个系统的复杂度，方便设备商和手机商各自独立的进行设计和生产，有利于产品规模化商用。
本实施例中以人脸注册方法应用于人脸识别装置为例，在另一个例子中，本实施例中的人脸注册方法还可以应用于服务器，具体过程可以包括：服务器通过人脸识别装置采集人脸图片，获得采集到的单个图片后进行人脸识别，对 一次注册中多次采集到的包含人脸的图片进行是否为同一人的判断，将判定为同一人的多张人脸图片进行数据融合，最终获得注册数据。
此外，本实施方式中在传输人脸图片时通过wifi进行传输，而实际应用中还可以采用蓝牙进行传输，在此不再赘述。
本申请第二实施例涉及一种人脸注册方法。本实施方式是在第一实施方式的基础上做了进一步改进，主要改进之处在于：本实施方式除了展示采集到的人脸图片外，还能在人脸识别设备处理人脸图片的过程中，对用户的进行实时提示，进一步保证注册时数据采集的准确性。
本实施方式中人脸注册方法如图3所示，具体如下：
步骤301至步骤302与第一实施方式中的步骤101至步骤102相类似，在此不再赘述。
步骤303，判断采集到的人脸图片是否符合注册要求；若是，则继续执行步骤304；若否，则执行步骤306。
具体的说，3D人脸注册时，对获取的人脸图片有较高要求，在一个例子中，需要采集到完整的人脸，如采集时由于用户没有对准摄像设备，或用户移动，造成拍摄出来的照片中人脸不完全或者人脸模糊无法辨识，都无法应用于后续的3D图片处理，属于不符合注册要求的人脸图片。具体人脸是否完全，或人脸是否清晰可辨的方式可以采用特征识别的方式，如果可以识别到预定的人脸特征，就可以认为人脸图片中的人脸完全且可辨。此外，实际应用中还可以采用其他识别方法，在此不再一一列举。
在另一个例子中，符合注册要求的人脸图片可以限定为：人脸图片中的 人脸需来自真实的人脸，如果人脸图片采集自照片，或头像模型，都将影响后续数据处理结果的准确性。所以，符合的注册要求中包括来自真实人脸，有利于提升后续处理结果的准确性。进一步说，关于如何判断人脸图片采集自照片，具体可以通过以下方式判断：
在一个例子中，可以通过结构光图像进行检测，具体包括：对人脸的结构光图像进行3D重建，获得重建图；根据重建图检测人脸图片中的人脸是否为活体。具体的说，通过摄像设备采集结构光图像时，可以根据转换生成的3D图像来判断被采集的人脸是真人人脸还是照片，由于照片是二维物体，所以如果用照片作为采集对象，就无法获得有正常立体效果的3D图像，所以在一个例子中，可以根据重建图是否为3D图像就可以确定采集对象是真人还是照片。此外，在实际应用中，还可以采用其他方式判断人脸是否来自真实的人脸，在此不再一一赘述。
步骤304至步骤305与第一实施方式中的步骤103至步骤104相类似，在此不再赘述。
步骤306，将提示信息传送至上述移动终端。
具体的说，在步骤303判定采集到的人脸图片不符合注册要求时，可以发出提示信息，在一个例子中，提示信息可以包括提示用户调整姿势或调整位置的信息，还可以包括上述两种提示信息的组合。
如人脸图片位于整个图片左侧，且左侧超过图片区域，无法采集到，可以提示用户向右移动一些位置，下次采集时继续判断，如果下次采集的人脸图片符合注册要求，说明用户已经根据指示移动了位置，如果下次采集的人脸图片仍然不符合注册要求，则继续提示用户。
继续说明，移动终端在收到提示信息后，实时发出提示，提示可以通过语音播报、在显示人脸图片的界面上叠加文字显示等方式，在此不再一一列举。
在一个例子中，人脸识别设备可以内置音频播报器，可以在需要发出提示信息的时候，同时通过音频播报器播放语音提示，以提示用户。
在上述步骤306执行之后，返回执行步骤301，再次采集人脸图片。可见，在判定采集到的人脸图片不符合注册要求时，则不进行后续的图片融合。
继续说明，本实施方式在判定采集到的人脸图片不符合注册要求时需要发出提示信息，在其他例子中，还可以在其他情况下发出提示信息，如错误次数过多，图片传送失败等，在此不再一一列举。
需要说明的是，本实施方式中判断图片是否符合要求的步骤在传送人脸图片的步骤之后，在其他例子中还可以将判断图片是否符合要求的步骤设置在传送人脸图片的步骤之前，使得不符合注册要求的图片不再传送至移动终端，使得用户查看到的图片为符合要求的人脸图片，获得较好的阅览体验。
具体的说，在融合人脸图片数据前，可以将上述特征数据存为模板，之后在融合时，可以融合各模板。具体的说，多张人脸图片对应一个人脸的不同角度，在融合时，根据人脸角度变化，将各模板深度融合，获得的最后一次融合后的数据即为注册数据中的人脸数据。由于模板数据中数据量精简，也有利于减少处理过程中的数据量。
可见，由于3D人脸注册时，对采集图像数据有较高的要求，需要对用户进行实时提示，本实施例将需提示的信息也发送至移动终端，由移动终端实时提示，保证注册过程中提示信息的顺利展示给用户，保证注册准确性。另外，本实施例明确还可以在人脸图片符合注册要求时再传送，避免传送错误照片， 从而避免用户查看到错误图片。
本申请第三实施例涉及一种人脸注册方法。本实施方式是在第一实施方式的基础上做了进一步改进，主要改进之处在于：本实施方式新增通信连接的检测，可以尽可能使得注册过程中人脸图片可以成功传送，使用户的使用体验不变。
本实施方式中人脸注册方法的流程图如图4所示，具体如下：
步骤401，检测是否与一移动终端通信连接；若是，则继续执行步骤403；若否，则执行步骤402。
具体的说，本实施例中用户可以通过手机的wifi模块连接人脸识别设备的wireless模块，所以首先检测是否有用户手机和人脸识别设备wifi连接，如果已连接，可以认为用户已准备好开始注册，继续执行步骤403，如果未连接，则可以认为用户还未到注册区域，或者还未准备好，继续执行步骤402。
更具体的说，本步骤可以在人脸识别设备开机的时候触发检测，也可以在开始注册时触发检测，其中，注册功能可以通过预定的功能按键启动，还可以通过语音控制，如用户口述启动注册，人脸识别设备接收到“开始注册”的语音指令后启动注册。
在一个例子中，用户可以通过蓝牙模块连接人脸识别设备的蓝牙模块，对应地，具体检测是否有用户手机和人脸识别设备蓝牙连接。
步骤402，发出提示信息。
具体的说，当确定人脸识别设备未与移动终端通信连接，可以通过人脸识别设备内置的语音播报器进行语音提示，实际应用中，还可以配合LED指示 灯闪烁等同时提示。
继续说明，在发出提示信息的同时，人脸识别设备的通信模块继续发出连接请求的广播，供移动终端连接。在一个例子中，在检测到未通信连接时，可以不发出提示信息，仅继续发出连接请求的广播，供移动终端连接，如果连接成功，则停止发出连接请求的广播，避免其他设备误连。
步骤402之后返回执行步骤401。
本实施方式中步骤403至步骤406与第一实施方式中的步骤101至步骤104相类似，在此不再赘述。
可见，本实施例预先检测是否和移动终端通信连接，在确定连接后开始注册，尽可能保证注册时人脸图片可以成功传送出去，避免用户在注册时无法看到影像的情况。
本申请第四实施例涉及一种人脸识别装置。
本实施方式中的装置示意图如图5所示，具体包括：
采集模块，包括：2D图像采集单元和深度信息采集单元，用于采集人脸图片。
通信模块，用于将采集到的人脸图片传送至独立于人脸识别设备之外的移动终端，供移动终端实时显示，还用于在注册完成后，将用于指示注册完成的信息发送至移动终端。
第一处理模块，用于融合采集到的人脸图片，获得人脸3D注册数据。
不难发现，本实施方式为与第一实施方式相对应的装置实施例，本实施方式可与第一实施方式互相配合实施。第一实施方式中提到的相关技术细节在 本实施方式中依然有效，为了减少重复，这里不再赘述。相应地，本实施方式中提到的相关技术细节也可应用在第一实施方式中。
值得一提的是，本实施方式中所涉及到的各模块均为逻辑模块，在实际应用中，一个逻辑单元可以是一个物理单元，也可以是一个物理单元的一部分，还可以以多个物理单元的组合实现。此外，为了突出本发明的创新部分，本实施方式中并没有将与解决本发明所提出的技术问题关系不太密切的单元引入，但这并不表明本实施方式中不存在其它的单元。
此外，在一个例子中，第一处理模块，具体包括：提示子模块，用于确定是否需要发出提示信息；触发子模块，用于在需发出提示信息时，将提示信息发送至通信模块；通信模块，还用于在接收到提示信息时，将提示信息传送至移动终端，供移动终端实时显示。
在一个例子中，通信模块，还用于确定是否与一移动终端通信连接；采集模块，具体用于在通信模块确定与一移动终端通信连接时，采集人脸图片。
在一个例子中，人脸识别装置还包括：第二处理模块，用于确定人脸图片是否符合注册要求；在确定人脸图片符合注册要求时，触发通信模块执行将采集到的人脸图片传送至移动终端。
在一个例子中，人脸识别装置为不具有显示功能的人脸识别装置。
在一个例子中，人脸识别装置还包括：第三处理模块，用于识别采集到的人脸图片，获得识别结果。
本发明第五实施方式涉及一种人脸识别设备，如图6所示，包括：
至少一个处理器；以及，与至少一个处理器通信连接的存储器；其中， 存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行如上述第一实施方式至第四实施方式中任意一个人脸注册方法。
其中，存储器和处理器采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器和存储器的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器。
其中，处理器负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器可以被用于存储处理器在执行操作时所使用的数据。
本发明第六实施方式涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现上述方法实施例。
即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域的普通技术人员可以理解，上述各实施例是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (18)

  1. 一种人脸注册方法，其特征在于，应用于人脸识别设备，包括：
    采集人脸图片；
    将采集到的人脸图片传送至独立于所述人脸识别设备之外的移动终端，供所述移动终端实时显示；
    融合采集到的人脸图片，获得人脸3D注册数据；
    将用于指示注册完成的信息发送至所述移动终端。
  2. 如权利要求1所述的方法，其特征在于，所述将采集到的人脸图片传送至移动终端，具体为：
    将采集到的人脸图片中的部分图片传送至所述移动终端。
  3. 如权利要求2所述的方法，其特征在于，传送的部分图片至少为每秒20张。
  4. 如权利要求1所述的方法，其特征在于，所述采集人脸图片之后，以及所述将用于指示注册完成的信息发送至所述移动终端之前，还包括：在需发出提示信息时，将所述提示信息传送至所述移动终端，供所述移动终端实时提示。
  5. 如权利要求4所述的方法，其特征在于，在以下情况需发出提示信息：
    采集到的人脸图片不符合注册要求。
  6. 如权利要求4所述的方法，其特征在于，所述提示信息包括：提示用户调整姿势和/或调整位置的信息。
  7. 如权利要求1所述的方法，其特征在于，所述将采集到的人脸图片传送至移动终端之前，还包括：判断所述人脸图片是否符合注册要求；
    在判定所述人脸图片符合所述注册要求时，执行所述将采集到的人脸图片传送至移动终端的步骤。
  8. 如权利要求1所述的方法，其特征在于，所述采集人脸图片之前，判断是否与一移动终端通信连接；
    若与一移动终端通信连接，则执行所述采集人脸图片的步骤。
  9. 如权利要求8所述的方法，其特征在于，在所述人脸识别设备开机时，或者在注册功能键被触发时，执行所述判断是否与一移动终端通信连接的步骤。
  10. 如权利要求1至9中任意一项所述的方法，所述获得注册数据之后，包括：
    识别采集到的人脸图片，获得识别结果。
  11. 一种人脸识别装置，其特征在于，包括：
    采集模块，包括：2D图像采集单元和深度信息采集单元，用于采集人脸图片；
    通信模块，用于将采集到的人脸图片传送至独立于所述人脸识别装置之外的移动终端，供所述移动终端实时显示，还用于在注册完成后，将用于指示注册完成的信息发送至所述移动终端；
    第一处理模块，用于融合采集到的人脸图片，获得人脸3D注册数据。
  12. 如权利要求11所述的装置，其特征在于，所述第一处理模块，具体包括：
    提示子模块，用于确定是否需要发出提示信息；
    触发子模块，用于在需发出提示信息时，将所述提示信息发送至所述通信模块；
    所述通信模块，还用于在接收到所述提示信息时，将所述提示信息传送至所述移动终端，供所述移动终端实时显示。
  13. 如权利要求11所述的装置，其特征在于，所述通信模块，还用于确定是否与一移动终端通信连接；
    所述采集模块，具体用于在所述通信模块确定与一移动终端通信连接时，采集人脸图片。
  14. 如权利要求11所述的装置，其特征在于，还包括：第二处理模块，用于确定所述人脸图片是否符合注册要求；在确定所述人脸图片符合所述注册要求时，触发所述通信模块执行将采集到的人脸图片传送至移动终端。
  15. 如权利要求11所述的装置，其特征在于，所述人脸识别装置为不具有显示功能的人脸识别装置。
  16. 如权利要求11至15中任意一项所述的装置，其特征在于，所述人脸识别装置，还包括：
    第三处理模块，用于识别采集到的人脸图片，获得识别结果。
  17. 一种人脸识别设备，其特征在于，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至10中任一项所述的人脸注册方法。
  18. 一种计算机可读存储介质，存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至10中任一项所述的人脸注册方法。
PCT/CN2019/084083 2019-04-24 2019-04-24 人脸注册方法、人脸识别装置、识别设备和可存储介质 WO2020215250A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980000570.1A CN110249340A (zh) 2019-04-24 2019-04-24 人脸注册方法、人脸识别装置、识别设备和可存储介质
PCT/CN2019/084083 WO2020215250A1 (zh) 2019-04-24 2019-04-24 人脸注册方法、人脸识别装置、识别设备和可存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/084083 WO2020215250A1 (zh) 2019-04-24 2019-04-24 人脸注册方法、人脸识别装置、识别设备和可存储介质

Publications (1)

Publication Number Publication Date
WO2020215250A1 true WO2020215250A1 (zh) 2020-10-29

Family

ID=67893864

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/084083 WO2020215250A1 (zh) 2019-04-24 2019-04-24 人脸注册方法、人脸识别装置、识别设备和可存储介质

Country Status (2)

Country Link
CN (1) CN110249340A (zh)
WO (1) WO2020215250A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112766086A (zh) * 2021-01-04 2021-05-07 深圳阜时科技有限公司 一种识别模板注册方法及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105023005A (zh) * 2015-08-05 2015-11-04 王丽婷 人脸识别装置及其识别方法
CN105117691A (zh) * 2015-08-04 2015-12-02 福州瑞芯微电子股份有限公司 一种用于人体特征采集的方法及装置
CN106295554A (zh) * 2016-08-08 2017-01-04 北京文安智能技术股份有限公司 一种人脸识别方法、系统及移动终端和人脸识别辅助装置
JP2017220624A (ja) * 2016-06-10 2017-12-14 パナソニックＩｐマネジメント株式会社 部品実装装置における操作管理方法
CN109214352A (zh) * 2018-09-26 2019-01-15 珠海横琴现联盛科技发展有限公司 基于2d摄像头三维成像技术的动态人脸检索识别方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5024067B2 (ja) * 2007-01-19 2012-09-12 コニカミノルタホールディングス株式会社 顔認証システム、方法及びプログラム
WO2010026983A1 (ja) * 2008-09-03 2010-03-11 日本電気株式会社 画像処理装置、画像処理方法、及び画像処理プログラム
CN105869235B (zh) * 2015-01-20 2019-08-30 阿里巴巴集团控股有限公司 一种安全门禁方法及系统
CN105809415B (zh) * 2016-03-04 2020-04-21 腾讯科技（深圳）有限公司 基于人脸识别的签到系统、方法和装置
CN107563168A (zh) * 2017-09-05 2018-01-09 广东欧珀移动通信有限公司 移动终端的解锁方法、装置及移动终端
CN108764024B (zh) * 2018-04-09 2020-03-24 平安科技（深圳）有限公司 人脸识别模型的生成装置、方法及计算机可读存储介质
CN108764180A (zh) * 2018-05-31 2018-11-06 Oppo广东移动通信有限公司 人脸识别方法、装置、电子设备及可读存储介质
CN109118569B (zh) * 2018-08-16 2023-03-10 Oppo广东移动通信有限公司 基于三维模型的渲染方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105117691A (zh) * 2015-08-04 2015-12-02 福州瑞芯微电子股份有限公司 一种用于人体特征采集的方法及装置
CN105023005A (zh) * 2015-08-05 2015-11-04 王丽婷 人脸识别装置及其识别方法
JP2017220624A (ja) * 2016-06-10 2017-12-14 パナソニックＩｐマネジメント株式会社 部品実装装置における操作管理方法
CN106295554A (zh) * 2016-08-08 2017-01-04 北京文安智能技术股份有限公司 一种人脸识别方法、系统及移动终端和人脸识别辅助装置
CN109214352A (zh) * 2018-09-26 2019-01-15 珠海横琴现联盛科技发展有限公司 基于2d摄像头三维成像技术的动态人脸检索识别方法

Also Published As

Publication number Publication date
CN110249340A (zh) 2019-09-17

Similar Documents

Publication Publication Date Title
US9576189B2 (en) Method and apparatus for controlling vehicle using motion recognition with face recognition
WO2019227774A1 (zh) 车辆及车门解锁控制方法、装置和车门解锁系统
CN105243740B (zh) 基于生物特征识别技术的卡安全身份认证系统及实现方法
KR101172227B1 (ko) 차량내 운전자 얼굴 인증을 통한 출입 통제 시스템 및 그 방법
WO2019232973A1 (zh) 车辆控制方法和系统、车载智能系统、电子设备、介质
WO2020223937A1 (zh) 一种人脸识别方法、人脸识别装置和计算机可读存储介质
WO2016107075A1 (zh) 身份验证方法、装置和智能门锁
EP3886058A1 (en) Hotel room door check-in
WO2017193826A1 (zh) 一种云桌面登陆验证方法、云桌面控制系统及客户端
JP2017503276A (ja) 顔構成要素距離を用いた虹彩認識用イメージの取得装置及び方法
TW201629851A (zh) 一種影像識別系統及方法
CN106599660A (zh) 终端安全验证方法及装置
WO2019126908A1 (zh) 图像数据处理方法、装置及设备
CN105224924A (zh) 活体人脸识别方法和装置
CN106251682A (zh) 停车位识别车辆的方法及装置
CN108897423A (zh) 一种vr眼镜及其在线考试防作弊方法
WO2021000415A1 (zh) 活体用户检测方法、装置、计算机设备和存储介质
CN212160784U (zh) 一种身份识别装置及门禁设备
WO2016115786A1 (zh) 终端解锁方法、装置、终端及计算机存储介质
JP2023033412A (ja) 情報処理装置、及び情報処理プログラム
CN106829662B (zh) 一种多功能智能电梯系统及控制方法
WO2020215250A1 (zh) 人脸注册方法、人脸识别装置、识别设备和可存储介质
CN111223219A (zh) 一种身份识别方法及存储介质
WO2019218905A1 (zh) 验证对象的方法、装置和系统
CN213904428U (zh) 一种门禁机和考勤门禁系统

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: 19925945

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: 19925945

Country of ref document: EP

Kind code of ref document: A1