WO2021180001A1 - 身份验证 - Google Patents

身份验证 Download PDF

Info

Publication number
WO2021180001A1
WO2021180001A1 PCT/CN2021/079293 CN2021079293W WO2021180001A1 WO 2021180001 A1 WO2021180001 A1 WO 2021180001A1 CN 2021079293 W CN2021079293 W CN 2021079293W WO 2021180001 A1 WO2021180001 A1 WO 2021180001A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
verification
identity
compared
biological
Prior art date
Application number
PCT/CN2021/079293
Other languages
English (en)
French (fr)
Inventor
魏晓林
柴振华
Original Assignee
北京三快在线科技有限公司
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 北京三快在线科技有限公司 filed Critical 北京三快在线科技有限公司
Publication of WO2021180001A1 publication Critical patent/WO2021180001A1/zh

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
    • G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity

Definitions

  • This application relates to the field of computer vision, specifically to identity verification.
  • the mainstream way of identity verification is based on the biometric recognition of human face, fingerprint, palm print, iris, vein, voice print, and gait.
  • face recognition with its natural and non-contact nature, brings some new experiences to the user's identity verification process in many scenarios (such as facial payment).
  • This application provides an identity verification method, device, electronic equipment, and storage medium.
  • an identity verification method including: obtaining a verification image for identity verification; identifying a non-biological feature related to the identity from the verification image; and obtaining a non-biological feature corresponding to the non-biological feature The image to be compared; the identity verification result is determined according to the verification image and the image to be compared.
  • the identifying non-biological features related to the identity from the verification image includes: performing pattern identification code detection on the verification image; when it is detected that the verification image does not contain a specified type of pattern identification code Next, it is determined that the identity verification has failed; in the case of detecting that the verification image contains a specified type of graphic identification code, the detected specified type of graphic identification code is recognized by the graphic identification code, and the recognition result is regarded as an identity-related non-biological feature .
  • the specified type of graphic identification code is a one-dimensional code and/or a two-dimensional code.
  • the acquiring the image to be compared corresponding to the non-biological feature includes: searching in a registered image library according to the non-biological feature, and using the retrieved registered image as the one corresponding to the non-biological feature The image to be compared; if the registered image cannot be retrieved, it is determined that the identity verification has failed.
  • the method further includes: in response to the registration request, obtaining a registered image of the target object; determining the non-biological characteristics of the target object according to the registered image; generating a visualization carrier of the non-biological characteristics for the target object in When performing identity verification, the visual carrier is displayed to form a corresponding verification image.
  • the determining the identity verification result based on the verification image and the image to be compared includes: performing biometric recognition on the verification image and the image to be compared, and determining the identity based on the recognized biometrics. Similarity: If the identity similarity is greater than the preset threshold, the identity verification is passed, otherwise the identity verification fails.
  • the verification image and the image to be compared are both images containing a face, and the biological feature is a local feature of the face and/or an overall feature of the face.
  • an identity verification device which includes: a verification image acquisition unit for acquiring a verification image for identity verification; and a non-biometric identification unit for identifying from the verification image Non-biological characteristics related to identity; to-be-compared image acquisition unit for acquiring the to-be-compared image corresponding to said non-biological characteristics; identity verification unit for determining according to said verification image and said to-be-compared image Authentication result.
  • the non-biometric identification unit is configured to perform pattern identification code detection on the verification image; in the case where it is detected that the verification image does not contain a specified type of pattern identification code, it is determined that the identity verification has failed;
  • the verification image contains a specified type of graphic identification code
  • the detected specified type of graphic identification code is recognized by the graphic identification code, and the recognition result is used as an identity-related non-biological feature.
  • the specified type of graphic identification code is a one-dimensional code and/or a two-dimensional code.
  • the to-be-compared image acquisition unit is configured to search in a registered image library according to the non-biological characteristics, and use the retrieved registered images as the to-be-compared images corresponding to the non-biological characteristics; If the registered image cannot be retrieved, it is determined that the authentication has failed.
  • the device further includes: a registration unit configured to obtain a registered image of the target object in response to a registration request; determine the non-biological characteristics of the target object according to the registered image; generate a visual carrier of the non-biological characteristics, This allows the target object to display the visual carrier when performing identity verification and thereby form a corresponding verification image.
  • a registration unit configured to obtain a registered image of the target object in response to a registration request; determine the non-biological characteristics of the target object according to the registered image; generate a visual carrier of the non-biological characteristics, This allows the target object to display the visual carrier when performing identity verification and thereby form a corresponding verification image.
  • the identity verification unit is configured to perform biometric recognition on the verification image and the image to be compared, and determine identity similarity based on the recognized biometric characteristics; if the identity similarity is greater than a preset threshold, Then the authentication is passed, otherwise the authentication fails.
  • the verification image and the image to be compared are both images containing a face, and the biological feature is a local feature of the face and/or an overall feature of the face.
  • an electronic device including: a processor; and a memory arranged to store computer-executable instructions, which when executed, cause the processor to execute as described above Any of the methods described.
  • a computer-readable storage medium stores one or more programs, and the one or more programs, when executed by a processor, implement any of the foregoing One described method.
  • the embodiment of the present application obtains a verification image used for identity verification, identifies non-biological features related to the identity from the verification image, and obtains the image to be compared corresponding to the non-biological feature. According to the verification image and The image to be compared determines the identity verification result.
  • the beneficial effect is that the use of identity-related non-biological characteristics reduces the scope of identity verification and simplifies the 1:N identification problem to a 1:1 verification problem, which not only improves the efficiency of identity verification, but also reduces computing resources, and is suitable for mobile terminals. It also greatly improves the accuracy of identity verification. It is especially suitable for scenes where biometrics such as masks on the face are disturbed. At the same time, the use of computer vision means does not require human contact. During periods of high epidemics Reduce the user's risk of infection.
  • Fig. 1 shows a schematic flowchart of an identity verification method according to an embodiment of the present application.
  • Fig. 2 shows a schematic structural diagram of an identity verification device according to an embodiment of the present application.
  • Fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.
  • the authentication based on face recognition usually compares the current user’s face image taken with the preset images in the pre-established image library one by one to find the most similar preset image. If the current user If the similarity between the facial image and the preset image reaches the confidence level, the identity corresponding to the preset image is considered to be the identity of the current user.
  • This 1:N method cannot achieve the preset accuracy in scenarios such as when the user’s face is blocked due to wearing a mask during the outbreak of the epidemic, because it is very likely to recognize A as B, which greatly reduces the need for identity verification.
  • Other biometric identification such as fingerprint identification, will have the risk of contact infection; iris identification requires customized equipment that is currently not popular enough. Therefore, it is very meaningful to use the natural and non-contact characteristics of the face to optimize the face recognition system and algorithm for identity verification.
  • the technical idea of this application is to convert the above-mentioned 1:N recognition problem into a 1:1 verification problem, that is, first determine the image to be compared, and then compare with the image to be compared to determine A Is it A?
  • Fig. 1 shows a schematic flowchart of an identity verification method according to an embodiment of the present application. As shown in Fig. 1, the method includes steps S110-S140.
  • Step S110 Obtain a verification image used for identity verification.
  • the embodiments of the present application can be applied to many practical scenarios such as attendance, access control, personnel sampling in logistics and distribution, etc.
  • the source of the verification image can be a mobile phone, attendance equipment, sampling equipment, and so on.
  • the user can be informed in advance of the object to be photographed, for example, the user's face is required to face the camera to take a front face.
  • the verification image may be one or more independently stored images, or each image frame in the verification video, which is not limited in this application.
  • Step S120 identifying non-biological features related to the identity from the verification image.
  • the non-biological characteristics here should be unique, in order to be able to determine a single identity based on the non-biological characteristics. For example, when a new employee enters a job, the administrative department assigns an employee ID. At this time, the employee ID is a non-biological feature that can identify the employee. Non-biological features need to be expressed in the verification image, for example, in the form of a visual carrier. For example, if an employee wears a work card with a work number written on the work card, the work card is a visual carrier of the non-biological characteristics of the work number.
  • step S130 an image to be compared corresponding to a non-biological feature is obtained.
  • the image to be compared can also be one or more independently stored images, or each image frame in the verification video, but they all correspond to the same identity.
  • one verification image and one image to be compared can meet the minimum requirements, and the efficiency of multiple images or videos is slightly lower, but the robustness is stronger.
  • Step S140 Determine the identity verification result based on the verification image and the image to be compared.
  • the method shown in Figure 1 uses non-biological features related to identity to narrow the scope of identity verification and simplifies the 1:N identification problem to a 1:1 verification problem, which not only improves the efficiency of identity verification, but also reduces computing resources. It is suitable for lightweight computing scenarios such as mobile terminals and greatly improves the accuracy of identity verification. It is especially suitable for scenarios where biometric features such as masks on the face are disturbed. At the same time, computer vision is used to eliminate the need for human contact. It reduces the user's risk of infection during periods of high epidemics.
  • identifying non-biological features related to identity from the verification image includes: performing pattern identification code detection on the verification image; In this case, it is determined that the identity verification has failed; in the case of detecting that the verification image contains a specified type of graphic identification code, the detected specified type of graphic identification code is recognized by the graphic identification code, and the recognition result is regarded as a non-biological feature related to the identity.
  • the pattern identification code of the specified type may be a one-dimensional code and/or a two-dimensional code.
  • the designated type of graphic identification code can be preferably a quick response (QR) code, which is a type of two-dimensional code, which has large information capacity, high reliability, can express multiple types of information such as Chinese characters and images, and is confidential. Strong anti-counterfeiting and other advantages.
  • QR codes are closely related to life, users do not need additional training, which reduces user learning costs; QR code detection and recognition technology is also very mature and technically easy to implement.
  • the information contained in the pattern identification code of the specified type may be a unique identifier, including but not limited to work number, key, etc.
  • obtaining the image to be compared corresponding to the non-biological feature includes: searching in the registered image database according to the non-biological feature, and using the retrieved registered image as corresponding to the non-biological feature The image to be compared; if the registered image cannot be retrieved, it is determined that the identity verification has failed.
  • the user needs to provide his own image as a registered image in advance, so that if the corresponding registered image cannot be retrieved based on non-biological characteristics during identity verification, the user may be prompted that the user has not registered yet.
  • the identity verification failure in this application may be caused by the user's unregistered status. For example, if an employee has not yet been registered for attendance by the administrative department, the attendance device cannot be used for attendance and attendance records cannot be generated. It may also provide false non-biological characteristics, such as creating a QR code by yourself in an attempt to impersonate. Since the information contained in the QR code does not have a corresponding registered image, the identity verification will also fail.
  • the above method further includes: in response to the registration request, obtaining a registered image of the target object; determining the non-biological characteristics of the target object according to the registered image; When performing identity verification, the visual carrier is displayed and the corresponding verification image is formed.
  • the visualization carrier here can be a virtual carrier such as an image, or an entity such as a card.
  • the user's QR code can be printed on the outside of the mask.
  • the materialized QR code serves as a non-biological feature visualization carrier, and the information contained in the QR code is non-biological features. Biological characteristics.
  • determining the identity verification result based on the verification image and the image to be compared includes: performing biometric recognition on the verification image and the image to be compared, and determining that the identities are similar based on the recognized biometrics. If the identity similarity is greater than the preset threshold, the identity verification is passed, otherwise the identity verification fails.
  • the authentication failure here may be caused by fraudulent use of other people’s non-biological characteristics, such as borrowing a colleague’s QR code. Taking face recognition as an example, the actual comparison is between your own facial image and the colleague’s face. The image, obviously, finally recognized that the identity similarity is very low, consistent with the real situation, and reflects the reliability of identity verification.
  • the verification image and the image to be compared may both be images containing a face, and the biological feature is a local feature of the face and/or an overall feature of the face.
  • the face recognition technology is relatively mature, and it can be realized by directly selecting the methods in the existing technology, or making fine adjustments based on the existing technology.
  • the basic neural network models that can be used include but are not limited to VGG (named from its developer Visual Geometry Group) model, Inception ( Founding) model, etc.
  • the verification image can include palmprint image areas, fingerprint image areas, and iris image areas, and so on.
  • Fig. 2 shows a schematic structural diagram of an identity verification device according to an embodiment of the present application.
  • the identity verification device 200 includes a verification image acquisition unit 210, a non-biometric identification unit 220, an image acquisition unit 230 to be compared, and an identity verification unit 240.
  • the verification image acquisition unit 210 is configured to acquire a verification image for identity verification.
  • the embodiments of the present application can be applied to many practical scenarios such as attendance, access control, personnel sampling in logistics and distribution, etc.
  • the source of the verification image can be a mobile phone, attendance equipment, sampling equipment, and so on.
  • the user can be informed in advance of the object to be photographed, for example, the user's face is required to face the camera to take a front face.
  • the verification image may be one or more independently stored images, or each image frame in the verification video, which is not limited in this application.
  • the non-biological feature recognition unit 220 is used for recognizing non-biological features related to the identity from the verification image.
  • the non-biological characteristics here should be unique, in order to be able to determine a single identity based on the non-biological characteristics. For example, when a new employee enters a job, the administrative department assigns an employee ID. At this time, the employee ID is a non-biological feature that can identify the employee. Non-biological features need to be expressed in the verification image, for example, in the form of a visual carrier. For example, if an employee wears a work card with a work number written on the work card, the work card is a visual carrier of the non-biological characteristics of the work number.
  • the to-be-compared image acquiring unit 230 is configured to acquire the to-be-compared image corresponding to the non-biological feature.
  • the image to be compared can also be one or more independently stored images, or each image frame in the verification video, but they all correspond to the same identity.
  • one verification image and one image to be compared can meet the minimum requirements, and the efficiency of multiple images or videos is slightly lower, but the robustness is stronger.
  • the identity verification unit 240 is configured to determine the identity verification result according to the verification image and the image to be compared.
  • the device shown in Figure 2 utilizes identity-related non-biological features to narrow the scope of identity verification and simplify the 1:N identification problem to a 1:1 verification problem, which not only improves the efficiency of identity verification, but also reduces computing resources. It is suitable for lightweight computing scenarios such as mobile terminals and greatly improves the accuracy of identity verification. It is especially suitable for scenarios where biometric features such as masks on the face are disturbed. At the same time, computer vision is used to eliminate the need for human contact. It reduces the user's risk of infection during periods of high epidemics.
  • the non-biometric identification unit 220 is used to perform pattern identification code detection on the verification image; if it is detected that the verification image does not contain a specified type of pattern identification code, determine the identity verification Failed; in the case of detecting that the verification image contains a specified type of graphic identification code, perform graphic identification code recognition on the detected specified type of graphic identification code, and use the recognition result as an identity-related non-biological feature.
  • the pattern identification code of the specified type may be a one-dimensional code and/or a two-dimensional code.
  • the designated type of graphic identification code can be preferably a quick response (QR) code, which is a type of two-dimensional code, which has large information capacity, high reliability, can express multiple types of information such as Chinese characters and images, and is confidential. Strong anti-counterfeiting and other advantages.
  • QR codes are closely related to life, users do not need additional training, which reduces user learning costs; QR code detection and recognition technology is also very mature and technically easy to implement.
  • the information contained in the pattern identification code of the specified type may be a unique identifier, including but not limited to work number, key, etc.
  • the to-be-compared image acquisition unit 230 is configured to search in the registered image library based on non-biological characteristics, and use the retrieved registered image as the to-be-compared corresponding to the non-biological characteristics. For images; if the registered image cannot be retrieved, it is determined that the identity verification has failed.
  • the user needs to provide his own image as a registered image in advance, so that if the corresponding registered image cannot be retrieved based on non-biological characteristics during identity verification, the user may be prompted that the user has not registered yet.
  • the identity verification failure in this application may be caused by the user's unregistered status. For example, if an employee has not yet been registered for attendance by the administrative department, the attendance device cannot be used for attendance and attendance records cannot be generated. It may also provide false non-biological characteristics, such as creating a QR code by yourself in an attempt to impersonate. Since the information contained in the QR code does not have a corresponding registered image, the identity verification will also fail.
  • the above-mentioned device further includes: a registration unit for obtaining a registered image of the target object in response to a registration request; determining the non-biological characteristics of the target object according to the registered image; generating a non-biological feature visualization carrier, In order for the target object to display the visual carrier when performing identity verification, and thus form a corresponding verification image.
  • the visualization carrier here can be a virtual carrier such as an image, or an entity such as a card.
  • the user's QR code can be printed on the outside of the mask.
  • the materialized QR code serves as a non-biological feature visualization carrier, and the information contained in the QR code is non-biological features. Biological characteristics.
  • the identity verification unit 240 is configured to perform biometric recognition on the verification image and the image to be compared, and determine the identity similarity according to the recognized biological characteristics; if the identity similarity is greater than If the threshold is preset, the authentication is passed, otherwise the authentication fails.
  • the authentication failure here may be caused by fraudulent use of other people’s non-biological characteristics, such as borrowing a colleague’s QR code. Taking face recognition as an example, the actual comparison is between your own facial image and the colleague’s face. The image, obviously, finally recognized that the identity similarity is very low, consistent with the real situation, and reflects the reliability of identity verification.
  • the verification image and the image to be compared may both be images containing a face, and the biological feature is a local feature of the face and/or an overall feature of the face.
  • the face recognition technology is relatively mature, and it can be realized by directly selecting the methods in the existing technology, or making fine adjustments based on the existing technology.
  • the basic neural network models that can be used include but are not limited to VGG (named from its developer Visual Geometry Group) model, Inception ( Founding) model, etc.
  • the verification image can include palmprint image areas, fingerprint image areas, and iris image areas, and so on.
  • the embodiment of the present application obtains a verification image for identity verification, identifies non-biological features related to the identity from the verification image, and obtains the image to be compared corresponding to the non-biological feature. According to the verification image Confirm the identity verification result with the image to be compared.
  • the beneficial effect is that the use of identity-related non-biological characteristics reduces the scope of identity verification and simplifies the 1:N identification problem to a 1:1 verification problem, which not only improves the efficiency of identity verification, but also reduces computing resources, and is suitable for mobile terminals. It also greatly improves the accuracy of identity verification. It is especially suitable for scenes where biometrics such as masks on the face are disturbed. At the same time, the use of computer vision means does not require human contact. During periods of high epidemics Reduce the user's risk of infection.
  • modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and/or processes or units are mutually exclusive, any combination can be used to compare all the features disclosed in this specification (including the accompanying claims, abstract and drawings) and any method or methods disclosed in this manner or All the processes or units of the equipment are combined. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.
  • the various component embodiments of the present application may be implemented by hardware, or by software modules running on one or more processors, or by a combination of them.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all components in the identity verification device according to the embodiments of the present application.
  • This application can also be implemented as a device or device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein.
  • Such a program for implementing the present application may be stored on a computer-readable medium, or may have the form of one or more signals.
  • Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.
  • FIG. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the electronic device 300 includes a processor 310 and a memory 320 arranged to store computer-executable instructions (computer-readable program code).
  • the memory 320 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM.
  • the memory 320 has a storage space 330 for storing computer-readable program codes 331 for executing any method steps in the above-mentioned methods.
  • the storage space 330 for storing computer-readable program codes may include various computer-readable program codes 331 respectively used to implement various steps in the above method.
  • the computer-readable program code 331 may be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. Such a computer program product is usually, for example, a computer-readable storage medium as shown in FIG. 4.
  • Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.
  • the computer-readable storage medium 400 stores the computer-readable program code 331 for executing the method steps according to the present application, which can be read by the processor 310 of the electronic device 300, when the computer-readable program code 331 is run by the electronic device 300 , Causing the electronic device 300 to execute each step in the method described above.
  • the computer readable program code 331 stored in the computer readable storage medium can execute the method shown in any of the above embodiments.
  • the computer readable program code 331 may be compressed in an appropriate form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本申请公开了一种方法。所述方法包括：获取用于身份验证的验证图像；从所述验证图像中识别出与身份相关的非生物特征；获取与所述非生物特征对应的待比对图像；根据所述验证图像与所述待比对图像确定身份验证结果。

Description

身份验证 技术领域
本申请涉及计算机视觉领域，具体涉及身份验证。
背景技术
目前，身份验证的主流方式是基于人脸、指纹、掌纹、虹膜、静脉、声纹以及步态等生物特征进行生物特征识别来实现的。而其中人脸识别以其自然性和非接触性在许多场景(如刷脸支付)给用户的身份验证过程带来了一些新的体验。
发明内容
本申请提供一种身份验证方法、装置、电子设备和存储介质。
依据本申请的一个方面，提供了一种身份验证方法，包括：获取用于身份验证的验证图像；从所述验证图像中识别出与身份相关的非生物特征；获取与所述非生物特征对应的待比对图像；根据所述验证图像与所述待比对图像确定身份验证结果。
可选地，所述从所述验证图像中识别出与身份相关的非生物特征包括：对所述验证图像进行图形识别码检测；在检测到所述验证图像不包含指定类型图形识别码的情况下，判定身份验证失败；在检测到所述验证图像包含指定类型图形识别码的情况下，对检测到的指定类型图形识别码进行图形识别码识别，将识别结果作为与身份相关的非生物特征。
可选地，所述指定类型图形识别码为一维码和/或二维码。
可选地，所述获取与所述非生物特征对应的待比对图像包括：根据所述非生物特征在注册图像库中进行检索，将检索到的注册图像作为与所述非生物特征对应的待比对图像；在检索不到注册图像的情况下，判定身份验证失败。
可选地，所述方法还包括：响应于注册请求，获取目标对象的注册图像；根据所述注册图像确定目标对象的非生物特征；生成所述非生物特征的可视化载体，以供目标对象在进行身份验证时展示所述可视化载体并从而形成相应的验证图像。
可选地，所述根据所述验证图像与所述待比对图像确定身份验证结果包括：对所述验证图像和所述待比对图像分别进行生物特征识别，根据识别出的生物特征确定身份相 似性；若身份相似性大于预设阈值，则身份验证通过，否则身份验证失败。
可选地，所述验证图像和所述待比对图像均为包含脸部的图像，所述生物特征为脸部局部特征和/或脸部整体特征。
依据本申请的另一方面，提供了一种身份验证装置，包括：验证图像获取单元，用于获取用于身份验证的验证图像；非生物特征识别单元，用于从所述验证图像中识别出与身份相关的非生物特征；待比对图像获取单元，用于获取与所述非生物特征对应的待比对图像；身份验证单元，用于根据所述验证图像与所述待比对图像确定身份验证结果。
可选地，所述非生物特征识别单元，用于对所述验证图像进行图形识别码检测；在检测到所述验证图像不包含指定类型图形识别码的情况下，判定身份验证失败；在检测到所述验证图像包含指定类型图形识别码的情况下，对检测到的指定类型图形识别码进行图形识别码识别，将识别结果作为与身份相关的非生物特征。
可选地，所述指定类型图形识别码为一维码和/或二维码。
可选地，所述待比对图像获取单元，用于根据所述非生物特征在注册图像库中进行检索，将检索到的注册图像作为与所述非生物特征对应的待比对图像；在检索不到注册图像的情况下，判定身份验证失败。
可选地，所述装置还包括：注册单元，用于响应于注册请求，获取目标对象的注册图像；根据所述注册图像确定目标对象的非生物特征；生成所述非生物特征的可视化载体，以供目标对象在进行身份验证时展示所述可视化载体并从而形成相应的验证图像。
可选地，所述身份验证单元，用于对所述验证图像和所述待比对图像分别进行生物特征识别，根据识别出的生物特征确定身份相似性；若身份相似性大于预设阈值，则身份验证通过，否则身份验证失败。
可选地，所述验证图像和所述待比对图像均为包含脸部的图像，所述生物特征为脸部局部特征和/或脸部整体特征。
依据本申请的又一方面，提供了一种电子设备，包括：处理器；以及被安排成存储计算机可执行指令的存储器，所述计算机可执行指令在被执行时使所述处理器执行如上述任一所述的方法。
依据本申请的再一方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，所述一个或多个程序当被处理器执行时，实现如上述任一所述 的方法。
由上述可知，本申请的实施例，通过获取用于身份验证的验证图像，从验证图像中识别出与身份相关的非生物特征，获取与非生物特征对应的待比对图像，根据验证图像与待比对图像确定身份验证结果。有益效果在于，利用与身份相关的非生物特征缩小了身份验证范围，将1：N的识别问题简化为1：1的验证问题，不仅提高了身份验证效率，减少了计算资源，适用于移动端等轻量化计算场景，而且也大大提升了身份验证的准确率，特别适合脸部戴有口罩等生物特征受到干扰的场景，同时利用计算机视觉的手段，不需要进行人体接触，在流行病高发时段降低了用户感染风险。
上述说明仅是本申请实施例的概述，为了能够更清楚了解本申请的技术手段，而可依照说明书的内容予以实施，并且为了让本申请的上述和其它目的、特征和优点能够更明显易懂，以下特举本申请的具体实施方式。
附图说明
通过阅读下文一些实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出一些实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。在附图中：
图1示出了根据本申请一个实施例的一种身份验证方法的流程示意图。
图2示出了根据本申请一个实施例的一种身份验证装置的结构示意图。
图3示出了根据本申请一个实施例的电子设备的结构示意图。
图4示出了根据本申请一个实施例的计算机可读存储介质的结构示意图。
具体实施方式
目前，基于人脸识别的身份验证通常是将当前拍摄的当前用户的脸部图像与预先建立的图像库中的预设图像进行一一比对，找出最相似的预设图像，如果当前用户的脸部图像与预设图像之间的相似度达到置信度，则认为预设图像对应的身份就是当前用户的身份。这种1：N的方式在流行病爆发期，用户的脸部因为戴口罩而被遮挡等场景下就无法达到预设精度，因为很可能将A识别成B，这就大大降低了身份验证的准确率。其他生物特征识别，如指纹识别会有接触感染风险；虹膜识别需要定制的设备目前还不够普及。因此，利用人脸的自然性和非接触式特点，优化人脸识别系统和算法以进行身份 验证是非常有意义的。
本申请的技术构思在于，将上面提到的1：N的识别问题转换为1：1的验证问题，即先确定要比对的图像，再通过与要比对的图像进行比对，确定A是否是A。
下面将参照附图更详细地描述本申请的示例性实施例。虽然附图中显示了本申请的示例性实施例，然而应当理解，可以以各种形式实现本申请而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本申请，并且能够将本申请的范围完整的传达给本领域的技术人员。
图1示出了根据本申请一个实施例的一种身份验证方法的流程示意图。如图1所示，该方法包括步骤S110-S140。
步骤S110，获取用于身份验证的验证图像。
本申请的实施例可以应用于考勤、门禁、物流配送中的人员抽检等诸多实际场景，相应地，验证图像的来源可以是手机、考勤设备、抽检设备等等。可以预先告知用户拍摄的对象，例如要求用户脸部正对摄像头以拍摄正脸。
例如，验证图像可以是一张或多张独立存储的图像，也可以是验证视频中的各图像帧，本申请对此不做限制。
步骤S120，从验证图像中识别出与身份相关的非生物特征。
这里的非生物特征应当是具有唯一性的，以期能够根据非生物特征确定单一身份。例如，当新员工入职后，行政部门为其分配工号，此时工号就是可以标识员工身份的非生物特征。非生物特征需要在验证图像中有所表达，例如以可视化载体的方式展示。例如，员工佩戴工卡，工卡上写有工号，则工卡就是工号这一非生物特征的可视化载体。
步骤S130，获取与非生物特征对应的待比对图像。
与验证图像类似地，待比对图像同样可以是一张或多张独立存储的图像，也可以是验证视频中的各图像帧，但均对应于同一身份。一般来说，一张验证图像与一张待比对图像即可满足最低需求，多张图像或者视频的效率稍低，但鲁棒性更强。
步骤S140，根据验证图像与待比对图像确定身份验证结果。
例如，判断验证图像与待比对图像表征的身份是否一致，若一致则身份验证通过，否则身份验证失败。
可见，图1所示的方法，利用与身份相关的非生物特征缩小了身份验证范围，将1： N的识别问题简化为1：1的验证问题，不仅提高了身份验证效率，减少了计算资源，适用于移动端等轻量化计算场景，而且也大大提升了身份验证的准确率，特别适合脸部戴有口罩等生物特征受到干扰的场景，同时利用计算机视觉的手段，不需要进行人体接触，在流行病高发时段降低了用户感染风险。
在本申请的一个实施例中，上述方法中，从验证图像中识别出与身份相关的非生物特征包括：对验证图像进行图形识别码检测；在检测到验证图像不包含指定类型图形识别码的情况下，判定身份验证失败；在检测到验证图像包含指定类型图形识别码的情况下，对检测到的指定类型图形识别码进行图形识别码识别，将识别结果作为与身份相关的非生物特征。
例如，在本申请的一个实施例中，上述方法中，指定类型图形识别码可以为一维码和/或二维码。结合目前的技术发展，指定类型图形识别码可以优选为快速响应(QR)码，其为二维码的一种，具有信息容量大、可靠性高、可表示汉字及图像等多类型信息、保密防伪性强等优点。
并且，由于QR码已与生活息息相关，用户不需要进行额外的培训，降低了用户学习成本；QR码检测和识别的技术也已非常成熟，在技术上也易于实现。
指定类型图形识别码所包含的信息可以是具有唯一性的标识，包括但不限于工号、密钥等。
在本申请的一个实施例中，上述方法中，获取与非生物特征对应的待比对图像包括：根据非生物特征在注册图像库中进行检索，将检索到的注册图像作为与非生物特征对应的待比对图像；在检索不到注册图像的情况下，判定身份验证失败。
例如，用户需要预先提供自己的图像作为注册图像，这样如果在身份验证时，无法根据非生物特征检索到对应的注册图像，可以提示用户尚未注册。
也就是说，本申请中的身份验证失败可能由用户尚未注册导致，比如员工尚未由行政部门进行考勤注册，则不能通过考勤设备进行考勤，也无法产生考勤记录。也可能是提供了虚假的非生物特征，比如自己制作了一个二维码企图冒充，由于该二维码包含的信息是没有对应的注册图像的，也会导致身份验证失败。
关于注册的具体流程可以参照下面的实施例。在本申请的一个实施例中，上述方法还包括：响应于注册请求，获取目标对象的注册图像；根据注册图像确定目标对象的非生物特征；生成非生物特征的可视化载体，以供目标对象在进行身份验证时展示可视化 载体并从而形成相应的验证图像。
这里的可视化载体可以是虚拟载体如图像，也可以是实体如卡片。例如，在一个具体场景中，用户需要佩戴口罩，则可以在口罩外侧打印好用户二维码，此时实体化的二维码就作为非生物特征的可视化载体，二维码包含的信息就是非生物特征。
在本申请的一个实施例中，上述方法中，根据验证图像与待比对图像确定身份验证结果包括：对验证图像和待比对图像分别进行生物特征识别，根据识别出的生物特征确定身份相似性；若身份相似性大于预设阈值，则身份验证通过，否则身份验证失败。
这里的身份验证失败，可能是因为冒用了他人的非生物特征，例如借用了同事的二维码导致，以人脸识别为例，实际比对的就是自己的脸部图像与同事的脸部图像，显然最终识别出身份相似性很低，与真实情况一致，体现了身份验证的可靠性。
例如，在本申请的一个实施例中，上述方法中，验证图像和待比对图像可以均为包含脸部的图像，生物特征为脸部局部特征和/或脸部整体特征。
人脸识别技术已经较为成熟，可以直接选用现有技术中的方式来实现，或者以现有技术为基础进行细微调整。例如通过搭建、训练神经网络模型，进行特征提取和身份相似性比对，可选用的基础神经网络模型包括但不限于VGG(名称源自其开发者Visual Geometry Group，视觉几何组)模型、Inception(创始)模型等。
除了脸部特征外，掌纹特征、指纹特征以及虹膜特征等也可以作为生物特征，例如，验证图像中可以包含掌纹图像区、指纹图像区和虹膜图像区，等等。
图2示出了根据本申请一个实施例的一种身份验证装置的结构示意图。如图2所示，身份验证装置200包括验证图像获取单元210、非生物特征识别单元220、待比对图像获取单元230和身份验证单元240。
验证图像获取单元210，用于获取用于身份验证的验证图像。
本申请的实施例可以应用于考勤、门禁、物流配送中的人员抽检等诸多实际场景，相应地，验证图像的来源可以是手机、考勤设备、抽检设备等等。可以预先告知用户拍摄的对象，例如要求用户脸部正对摄像头以拍摄正脸。
例如，验证图像可以是一张或多张独立存储的图像，也可以是验证视频中的各图像帧，本申请对此不做限制。
非生物特征识别单元220，用于从验证图像中识别出与身份相关的非生物特征。
这里的非生物特征应当是具有唯一性的，以期能够根据非生物特征确定单一身份。例如，当新员工入职后，行政部门为其分配工号，此时工号就是可以标识员工身份的非生物特征。非生物特征需要在验证图像中有所表达，例如以可视化载体的方式展示。例如，员工佩戴工卡，工卡上写有工号，则工卡就是工号这一非生物特征的可视化载体。
待比对图像获取单元230，用于获取与非生物特征对应的待比对图像。
与验证图像类似地，待比对图像同样可以是一张或多张独立存储的图像，也可以是验证视频中的各图像帧，但均对应于同一身份。一般来说，一张验证图像与一张待比对图像即可满足最低需求，多张图像或者视频的效率稍低，但鲁棒性更强。
身份验证单元240，用于根据验证图像与待比对图像确定身份验证结果。
例如，判断验证图像与待比对图像表征的身份是否一致，若一致则身份验证通过，否则身份验证失败。
可见，图2所示的装置，利用与身份相关的非生物特征缩小了身份验证范围，将1：N的识别问题简化为1：1的验证问题，不仅提高了身份验证效率，减少了计算资源，适用于移动端等轻量化计算场景，而且也大大提升了身份验证的准确率，特别适合脸部戴有口罩等生物特征受到干扰的场景，同时利用计算机视觉的手段，不需要进行人体接触，在流行病高发时段降低了用户感染风险。
在本申请的一个实施例中，上述装置中，非生物特征识别单元220，用于对验证图像进行图形识别码检测；在检测到验证图像不包含指定类型图形识别码的情况下，判定身份验证失败；在检测到验证图像包含指定类型图形识别码的情况下，对检测到的指定类型图形识别码进行图形识别码识别，将识别结果作为与身份相关的非生物特征。
例如，在本申请的一个实施例中，上述装置中，指定类型图形识别码可以为一维码和/或二维码。结合目前的技术发展，指定类型图形识别码可以优选为快速响应(QR)码，其为二维码的一种，具有信息容量大、可靠性高、可表示汉字及图像等多类型信息、保密防伪性强等优点。
并且，由于QR码已与生活息息相关，用户不需要进行额外的培训，降低了用户学习成本；QR码检测和识别的技术也已非常成熟，在技术上也易于实现。
指定类型图形识别码所包含的信息可以是具有唯一性的标识，包括但不限于工号、密钥等。
在本申请的一个实施例中，上述装置中，待比对图像获取单元230，用于根据非生物特征在注册图像库中进行检索，将检索到的注册图像作为与非生物特征对应的待比对图像；在检索不到注册图像的情况下，判定身份验证失败。
例如，用户需要预先提供自己的图像作为注册图像，这样如果在身份验证时，无法根据非生物特征检索到对应的注册图像，可以提示用户尚未注册。
也就是说，本申请中的身份验证失败可能由用户尚未注册导致，比如员工尚未由行政部门进行考勤注册，则不能通过考勤设备进行考勤，也无法产生考勤记录。也可能是提供了虚假的非生物特征，比如自己制作了一个二维码企图冒充，由于该二维码包含的信息是没有对应的注册图像的，也会导致身份验证失败。
关于注册的具体流程可以参照下面的实施例。在本申请的一个实施例中，上述装置还包括：注册单元，用于响应于注册请求，获取目标对象的注册图像；根据注册图像确定目标对象的非生物特征；生成非生物特征的可视化载体，以供目标对象在进行身份验证时展示可视化载体并从而形成相应的验证图像。
这里的可视化载体可以是虚拟载体如图像，也可以是实体如卡片。例如，在一个具体场景中，用户需要佩戴口罩，则可以在口罩外侧打印好用户二维码，此时实体化的二维码就作为非生物特征的可视化载体，二维码包含的信息就是非生物特征。
在本申请的一个实施例中，上述装置中，身份验证单元240，用于对验证图像和待比对图像分别进行生物特征识别，根据识别出的生物特征确定身份相似性；若身份相似性大于预设阈值，则身份验证通过，否则身份验证失败。
这里的身份验证失败，可能是因为冒用了他人的非生物特征，例如借用了同事的二维码导致，以人脸识别为例，实际比对的就是自己的脸部图像与同事的脸部图像，显然最终识别出身份相似性很低，与真实情况一致，体现了身份验证的可靠性。
例如，在本申请的一个实施例中，上述装置中，验证图像和待比对图像可以均为包含脸部的图像，生物特征为脸部局部特征和/或脸部整体特征。
人脸识别技术已经较为成熟，可以直接选用现有技术中的方式来实现，或者以现有技术为基础进行细微调整。例如通过搭建、训练神经网络模型，进行特征提取和身份相似性比对，可选用的基础神经网络模型包括但不限于VGG(名称源自其开发者Visual Geometry Group，视觉几何组)模型、Inception(创始)模型等。
除了脸部特征外，掌纹特征、指纹特征以及虹膜特征等也可以作为生物特征，例如， 验证图像中可以包含掌纹图像区、指纹图像区和虹膜图像区，等等。
综上所述，本申请的实施例，通过获取用于身份验证的验证图像，从验证图像中识别出与身份相关的非生物特征，获取与非生物特征对应的待比对图像，根据验证图像与待比对图像确定身份验证结果。有益效果在于，利用与身份相关的非生物特征缩小了身份验证范围，将1：N的识别问题简化为1：1的验证问题，不仅提高了身份验证效率，减少了计算资源，适用于移动端等轻量化计算场景，而且也大大提升了身份验证的准确率，特别适合脸部戴有口罩等生物特征受到干扰的场景，同时利用计算机视觉的手段，不需要进行人体接触，在流行病高发时段降低了用户感染风险。
需要说明的是：
在此提供的算法和显示不与任何特定计算机、虚拟装置或者其它设备固有相关。各种通用装置也可以与基于在此的示教一起使用。根据上面的描述，构造这类装置所要求的结构是显而易见的。此外，本申请也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本申请的内容，并且上面对特定语言所做的描述是为了披露本申请的最佳实施方式。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实施例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在上面对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如下面的权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此 公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的身份验证装置中的一些或者全部部件的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的设备或者装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
例如，图3示出了根据本申请一个实施例的电子设备的结构示意图。该电子设备300包括处理器310和被安排成存储计算机可执行指令(计算机可读程序代码)的存储器320。存储器320可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。存储器320具有存储用于执行上述方法中的任何方法步骤的计算机可读程序代码331的存储空间330。例如，用于存储计算机可读程序代码的存储空间330可以包括分别用于实现上面的方法中的各种步骤的各个计算机可读程序代码331。计算机可读程序代码331可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。这些计算机程序产品包括诸如硬盘、紧致盘(CD)、存储卡或者软盘之类的程序代码载体。这样的计算机程序产品通常为例如图4所示的计算机可读存储介质。图4示出了根据本申请一个实施例的一种计算机可读存储介质的结构示意图。该计算机可读存储介质400存储有用于执行根据本申请的方法步骤的计算机可读程序代码331，可以被电子设备300的处理器310读取，当计算机可读程序代码331由电子设备300运行时，导致该电子设备300执行上面所描述的方法中的各个步骤，具体来说，该计算机可读存储介质存储的计算机可读程序代码331可以执行上述任一实施例中示出的方法。计算机可读程序代码331可以以适当形式进行压缩。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。单词“包含”不排除存在未列在权利要求中的元件或步骤。位于元件之前的单词“一”或“一个”不排除存在多个这样的元件。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (10)

  1. 一种身份验证方法，包括：
    获取用于身份验证的验证图像；
    从所述验证图像中识别出与身份相关的非生物特征；
    获取与所述非生物特征对应的待比对图像；
    根据所述验证图像与所述待比对图像确定身份验证结果。
  2. 如权利要求1所述的方法，其中，所述从所述验证图像中识别出与身份相关的非生物特征包括：
    对所述验证图像进行图形识别码检测；
    在检测到所述验证图像不包含指定类型图形识别码的情况下，判定身份验证失败；
    在检测到所述验证图像包含指定类型图形识别码的情况下，对检测到的指定类型图形识别码进行图形识别码识别，将识别结果作为与身份相关的非生物特征。
  3. 如权利要求2所述的方法，其中，所述指定类型图形识别码为一维码和/或二维码。
  4. 如权利要求1所述的方法，其中，所述获取与所述非生物特征对应的待比对图像包括：
    根据所述非生物特征在注册图像库中进行检索，将检索到的注册图像作为与所述非生物特征对应的待比对图像；
    在检索不到注册图像的情况下，判定身份验证失败。
  5. 如权利要求4所述的方法，所述方法还包括：
    响应于注册请求，获取目标对象的注册图像；
    根据所述注册图像确定目标对象的非生物特征；
    生成所述非生物特征的可视化载体，以供目标对象在进行身份验证时展示所述可视化载体并从而形成相应的验证图像。
  6. 如权利要求1-5中任一项所述的方法，其中，所述根据所述验证图像与所述待比对图像确定身份验证结果包括：
    对所述验证图像和所述待比对图像分别进行生物特征识别，根据识别出的生物特征确定身份相似性；
    若身份相似性大于预设阈值，则身份验证通过，否则身份验证失败。
  7. 如权利要求6所述的方法，其中，所述验证图像和所述待比对图像均为包含脸 部的图像，所述生物特征为脸部局部特征和/或脸部整体特征。
  8. 一种身份验证装置，包括：
    验证图像获取单元，用于获取用于身份验证的验证图像；
    非生物特征识别单元，用于从所述验证图像中识别出与身份相关的非生物特征；
    待比对图像获取单元，用于获取与所述非生物特征对应的待比对图像；
    身份验证单元，用于根据所述验证图像与所述待比对图像确定身份验证结果。
  9. 一种电子设备，该电子设备包括：处理器；以及被安排成存储计算机可执行指令的存储器，其中，所述计算机可执行指令在被执行时使所述处理器执行如权利要求1-7中任一项所述的方法。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储一个或多个程序，其中，所述一个或多个程序当被处理器执行时，实现如权利要求1-7中任一项所述的方法。
PCT/CN2021/079293 2020-03-13 2021-03-05 身份验证 WO2021180001A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010175937.8 2020-03-13
CN202010175937.8A CN111428594A (zh) 2020-03-13 2020-03-13 身份验证方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2021180001A1 true WO2021180001A1 (zh) 2021-09-16

Family

ID=71547810

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/079293 WO2021180001A1 (zh) 2020-03-13 2021-03-05 身份验证

Country Status (2)

Country Link
CN (1) CN111428594A (zh)
WO (1) WO2021180001A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114647826A (zh) * 2022-01-30 2022-06-21 北京旷视科技有限公司 身份核验方法、电子设备、存储介质及计算机程序产品

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111428594A (zh) * 2020-03-13 2020-07-17 北京三快在线科技有限公司 身份验证方法、装置、电子设备和存储介质
CN111986369A (zh) * 2020-08-27 2020-11-24 四川卫宁软件有限公司 一种医疗行为管理方法及其管理系统、计算机终端

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104598795A (zh) * 2015-01-30 2015-05-06 科大讯飞股份有限公司 身份验证方法及系统
CN104734852A (zh) * 2013-12-24 2015-06-24 中国移动通信集团湖南有限公司 一种身份认证方法及装置
CN105681316A (zh) * 2016-02-02 2016-06-15 腾讯科技（深圳）有限公司 身份验证方法和装置
CN107294730A (zh) * 2017-08-24 2017-10-24 北京无线电计量测试研究所 一种多模态生物特征身份认证方法、装置及系统
CN107679457A (zh) * 2017-09-06 2018-02-09 阿里巴巴集团控股有限公司 用户身份校验方法及装置
CN109274683A (zh) * 2018-10-30 2019-01-25 国网安徽省电力有限公司信息通信分公司 一种交叉组合认证系统及其认证方法
CN109344722A (zh) * 2018-09-04 2019-02-15 阿里巴巴集团控股有限公司 一种用户身份确定方法、装置及电子设备
CN109871722A (zh) * 2019-01-10 2019-06-11 深圳市雄帝科技股份有限公司 基于光学图形码的身份验证方法、系统、终端及存储介质
EP3594850A1 (fr) * 2018-07-13 2020-01-15 Idemia Identity & Security France Procédé de reconnaissance biométrique
CN111428594A (zh) * 2020-03-13 2020-07-17 北京三快在线科技有限公司 身份验证方法、装置、电子设备和存储介质

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103065148A (zh) * 2012-12-03 2013-04-24 黄敏 获取视频中服装二维码的方法和装置
CN104573597B (zh) * 2013-10-10 2018-12-11 腾讯科技（深圳）有限公司 一种二维码识别方法，及装置
CN103745188A (zh) * 2014-01-23 2014-04-23 惠州Tcl移动通信有限公司 通过图像识别提醒过期商品的方法和电子终端
CN105760867A (zh) * 2016-02-19 2016-07-13 深圳市润农科技有限公司 一种图像中二维码和/或文字的提取方法及装置
CN108335099A (zh) * 2018-03-25 2018-07-27 湛江正信科技服务有限公司 移动支付的方法、装置、移动终端及存储介质
CN110363047B (zh) * 2018-03-26 2021-10-26 普天信息技术有限公司 人脸识别的方法、装置、电子设备和存储介质
CN108833359A (zh) * 2018-05-22 2018-11-16 深圳市商汤科技有限公司 身份验证方法、装置、设备、存储介质及程序
CN110647955A (zh) * 2018-06-26 2020-01-03 义隆电子股份有限公司 身份验证方法
CN109063604A (zh) * 2018-07-16 2018-12-21 阿里巴巴集团控股有限公司 一种人脸识别方法及终端设备
CN109191112B (zh) * 2018-07-16 2021-09-28 创新先进技术有限公司 身份验证方法及装置
CN110516426A (zh) * 2019-08-21 2019-11-29 广州国音智能科技有限公司 身份认证方法、认证终端、装置及可读存储介质
CN110570185B (zh) * 2019-09-03 2024-03-26 腾讯科技（深圳）有限公司 资源转移方法、装置、存储介质及电子设备

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104734852A (zh) * 2013-12-24 2015-06-24 中国移动通信集团湖南有限公司 一种身份认证方法及装置
CN104598795A (zh) * 2015-01-30 2015-05-06 科大讯飞股份有限公司 身份验证方法及系统
CN105681316A (zh) * 2016-02-02 2016-06-15 腾讯科技（深圳）有限公司 身份验证方法和装置
CN107294730A (zh) * 2017-08-24 2017-10-24 北京无线电计量测试研究所 一种多模态生物特征身份认证方法、装置及系统
CN107679457A (zh) * 2017-09-06 2018-02-09 阿里巴巴集团控股有限公司 用户身份校验方法及装置
EP3594850A1 (fr) * 2018-07-13 2020-01-15 Idemia Identity & Security France Procédé de reconnaissance biométrique
CN109344722A (zh) * 2018-09-04 2019-02-15 阿里巴巴集团控股有限公司 一种用户身份确定方法、装置及电子设备
CN109274683A (zh) * 2018-10-30 2019-01-25 国网安徽省电力有限公司信息通信分公司 一种交叉组合认证系统及其认证方法
CN109871722A (zh) * 2019-01-10 2019-06-11 深圳市雄帝科技股份有限公司 基于光学图形码的身份验证方法、系统、终端及存储介质
CN111428594A (zh) * 2020-03-13 2020-07-17 北京三快在线科技有限公司 身份验证方法、装置、电子设备和存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114647826A (zh) * 2022-01-30 2022-06-21 北京旷视科技有限公司 身份核验方法、电子设备、存储介质及计算机程序产品

Also Published As

Publication number Publication date
CN111428594A (zh) 2020-07-17

Similar Documents

Publication Publication Date Title
CN109948408B (zh) 活性测试方法和设备
WO2021180001A1 (zh) 身份验证
KR100571826B1 (ko) 대용량 얼굴 인식 장치 및 방법
JP6155306B2 (ja) 顔認識方法、装置、プログラム、およびコンピュータ可読記録媒体
JP6650946B2 (ja) モバイル・デバイスを用いてキャプチャしたイメージを使用する指紋ベースのユーザ認証を実行するためのシステムおよび方法
de Luis-Garcı́a et al. Biometric identification systems
Dahia et al. Continuous authentication using biometrics: An advanced review
AU2022203880B2 (en) Methods and systems for determining user liveness and verifying user identities
WO2019130670A1 (ja) 生体認証システム
KR20170002892A (ko) 위조 지문 검출 방법 및 장치, 지문 인식 방법 및 장치
EP4057237A1 (en) Reference image enrollment and evolution for security systems
KR102321917B1 (ko) 온라인 시험 화상 원격 관리 및 감독 시스템
Haji et al. Real time face recognition system (RTFRS)
Kumar et al. Face recognition attendance system using local binary pattern algorithm
JP2021103538A (ja) 情報処理装置、情報処理方法、および、情報処理プログラム
Alsellami et al. The recent trends in biometric traits authentication based on internet of things (IoT)
Chaudhari et al. Real Time Face Recognition Based Attendance System using Multi Task Cascaded Convolutional Neural Network
Gupta et al. Unsupervised biometric anti-spoofing using generative adversarial networks
CN116226817A (zh) 身份识别方法、装置、计算机设备和存储介质
El-Bashir et al. Face Recognition Model Based on Covariance Intersection Fusion for Interactive devices
Zolotarev et al. Liveness detection methods implementation to face identification reinforcement in gaming services
Marutotamtama et al. Face Recognition and Face Spoofing Detector for Attendance System
Ramalingam et al. Fundamentals and advances in 3D face recognition
Sehgal Palm recognition using LBP and SVM
Liashenko et al. Investigation of the influence of image quality on the work of biometric authentication methods

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: 21767697

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: 21767697

Country of ref document: EP

Kind code of ref document: A1