WO2020220453A1 - 一种校验证件与持证人的方法及装置 - Google Patents

一种校验证件与持证人的方法及装置 Download PDF

Info

Publication number
WO2020220453A1
WO2020220453A1 PCT/CN2019/092928 CN2019092928W WO2020220453A1 WO 2020220453 A1 WO2020220453 A1 WO 2020220453A1 CN 2019092928 W CN2019092928 W CN 2019092928W WO 2020220453 A1 WO2020220453 A1 WO 2020220453A1
Authority
WO
WIPO (PCT)
Prior art keywords
certificate
video
face
verifying
image
Prior art date
Application number
PCT/CN2019/092928
Other languages
English (en)
French (fr)
Inventor
钱浩然
谢畅
彭宇翔
王恒
孙谷飞
袁皓
Original Assignee
众安信息技术服务有限公司
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 众安信息技术服务有限公司 filed Critical 众安信息技术服务有限公司
Priority to SG11202011107PA priority Critical patent/SG11202011107PA/en
Priority to JP2019547640A priority patent/JP7071991B2/ja
Publication of WO2020220453A1 publication Critical patent/WO2020220453A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172Classification, e.g. identification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40Spoof detection, e.g. liveness detection
    • G06V40/45Detection of the body part being alive

Definitions

  • the present invention relates to the field of computer technology, in particular to a method and device for verifying a document and a certificate holder.
  • Anti-counterfeiting technology refers to a certain method that can deter forgery. It can greatly increase the difficulty and cost of forgery, or reduce the degree of simulation of forgery.
  • Formal anti-counterfeiting refers to anti-counterfeiting technologies other than products, which generally have strong adaptability and a long anti-counterfeiting life cycle. Because it relies on anti-counterfeiting methods other than the product, the anti-counterfeiting mark must be closely integrated with the product or its packaging to form an inseparable whole. For example, tamper-evident stickers, hot stamping labels, direct printing or molding techniques. At present, most anti-counterfeiting technologies and methods belong to formal anti-counterfeiting, such as packaging anti-counterfeiting, password anti-counterfeiting, various anti-counterfeiting signs or trademarks.
  • Image processing refers to the analysis, processing, and processing of images to meet visual, psychological or other requirements.
  • Image processing is an application of signal processing in the image field. At present, most images are stored in digital form, so image processing refers to digital image processing in many cases. In addition, processing methods based on optical theory still occupy an important position. Image processing is a subcategory of signal processing, and it is also closely related to computer science, artificial intelligence and other fields.
  • Online business requires users to upload personal ID images, such as ID cards, passports, driving licenses, etc.
  • ID cards such as ID cards, passports, driving licenses, etc.
  • the school verifies the authenticity of the documents.
  • a method for verifying a document and a certificate holder includes the following steps:
  • a device for verifying a certificate and a certificate holder comprising:
  • the first video acquisition module for real-time acquisition of the video of the certificate with the specified sequence projection angle
  • the first extraction module used to extract the image features of the credential under different projection angles in the video;
  • the first verification module used to verify the authenticity of the certificate according to the image characteristics of the certificate
  • the second video acquisition module used to acquire face video in real time
  • the second verification module used to verify whether the face video is a real person
  • the second extraction module used to extract the image features of the face in the face video
  • Comparison module when verifying that the credential is true and the face video is a real person, compare the image features of the credential with the image features of the face in the face video to determine Whether the holder is the owner of the certificate.
  • an apparatus for verifying a certificate and a certificate holder including:
  • One or more processors are One or more processors;
  • a computer-readable storage medium having a computer program stored thereon, and when the program is run by a processor, the processor executes the following processing:
  • Fig. 1 is an exemplary flowchart of a method for verifying a document and a certificate holder according to an embodiment of the present disclosure
  • FIG. 2 is an exemplary configuration block diagram of an apparatus for verifying a certificate and a certificate holder according to an embodiment of the present disclosure
  • FIG. 3 is an exemplary configuration of a computing device that can implement an embodiment of the present disclosure.
  • the present disclosure provides a method and device for verifying a document and a certificate holder, which verify the authenticity of the document through different projection angles, verify whether the document is a real person, and combine the characteristics of the real face image with the face image characteristics on the document. Compare to verify whether you hold a certificate. According to one or more embodiments of the present disclosure, while validly verifying the authenticity of the certificate, it is possible to further verify whether the current certificate holder status is.
  • Fig. 1 shows an exemplary flowchart of a method for verifying a document and a certificate holder according to an embodiment of the present disclosure.
  • step S1 a video of a certificate with a prescribed sequence of projection angles is acquired in real time.
  • the video may be collected in real time through a camera installed on a terminal device (for example, a mobile terminal such as a special device for verifying documents and a certificate holder, a smart computer, a tablet computer, etc.).
  • a terminal device for example, a mobile terminal such as a special device for verifying documents and a certificate holder, a smart computer, a tablet computer, etc.
  • step S1 in order to obtain a video with a prescribed sequence of projection angles, in some embodiments, a video in which the certificate holder completes a prescribed sequence of actions while holding the document, and the prescribed sequence of actions makes the document have a prescribed sequence of projection angles.
  • the certificate holder himself completes the prescribed sequence of actions without the need to configure additional manpower and hardware equipment, which can reduce manpower and physical costs.
  • the collection auxiliary device may be a program-controlled manipulator, for example.
  • the prescribed sequence of projection angles in the obtained video are more standardized, which can make the subsequent certificate verification process more accurate.
  • the following uses the video of the holder of the certificate to complete the prescribed sequence of actions as an example for writing.
  • step S1 may further include the following steps: randomly call a number of standardized document action images, generate a video with sequence actions and display it on the front end, prompting the holder to complete the prescribed sequence actions according to the instructions.
  • the certificate holder completes the sequence of actions, the certificate can be placed in different positions and have different projection angles.
  • the projection angle in this embodiment may be, for example, the angle formed between the document and the projection surface of the camera. Specifically, it may be the angle defined by the connection line between the center point of the document and the center point of the projection surface of the camera and the projection surface of the camera.
  • the number of projection angles in the prescribed sequence can be one or more. In some embodiments, by setting multiple projection angles in different directions and/or different angle ranges, it is possible to obtain document image features in different directions and/or different projection angles, thereby improving the reliability of verification.
  • a set of document sequence projection angles may include: upper 45°, left 45°, lower 45°, right 45°, and middle 90°. Hold the certificate so that the certificate is located at 45° above the center of the camera projection surface, 45° on the left, 45° below, 45° on the right, and directly in front of the center of the camera projection surface.
  • the front-end display can be used to show the above-mentioned projection angles to the holder, thereby prompting the holder to complete the prescribed sequence of actions according to the instructions.
  • step S2 the image features of the document under different projection angles in the video are extracted.
  • step S2 may include the following sub-steps:
  • the image characteristics of the certificate in step S22 may include the visual anti-counterfeiting characteristics of the certificate and the image characteristics of the face in the certificate.
  • Computer vision related technologies can be used to extract the image features of the document.
  • algorithms such as SIFT, SURF, BRIEF, ORB, etc. may be used for extraction.
  • step S22 may include step S221: extracting the visual anti-counterfeiting features of the certificate in the picture.
  • the visual anti-counterfeiting features of the certificate may include static visual anti-counterfeiting features.
  • the static visual anti-counterfeiting features such as texture, color, text, etc., will not change with the projection angle of the document and the camera projection surface.
  • the static visual anti-counterfeiting features can be verified by computer vision algorithms.
  • the visual anti-counterfeiting features of the document may include dynamic visual anti-counterfeiting features. Dynamic visual anti-counterfeiting features can include color, shape, etc., which will change with the projection angle.
  • the dynamic visual anti-counterfeiting feature may be, for example, a laser anti-counterfeiting code, and the changes of the laser anti-counterfeiting code at different angles can be recorded by a computer vision method to verify the dynamic visual anti-counterfeiting feature.
  • step S22 may include step S222: extracting facial image features of the credential in the picture.
  • step S222 may specifically include the following sub-steps:
  • the feature points of a human face may include features such as eyes and nose.
  • step S23 may include the following sub-steps:
  • S231 Obtain the position of the certificate in each picture by using a feature matching algorithm, specifically, after calculating a homograph (homography matrix) by searching, and calculating the specific position of the certificate by radiation transformation.
  • step S232 Calculate the angle between the position of the certificate in each picture and the projection surface of the camera according to step S231 to calculate the projection angle of the certificate.
  • step S3 the authenticity of the certificate is verified according to the image characteristics of the certificate.
  • step S3 may include the following sub-steps:
  • the visual anti-counterfeiting feature when the visual anti-counterfeiting feature includes a static visual anti-counterfeiting feature and a dynamic visual anti-counterfeiting feature, the static visual anti-counterfeiting feature and the dynamic visual anti-counterfeiting feature are respectively combined with the static visual anti-counterfeiting feature specification data range and the dynamic visual anti-counterfeiting feature specification data range. Compare to confirm the authenticity of the documents.
  • step S8 may be further included: according to the image characteristics of the certificate under different projection angles, it is verified whether the video capture of the certificate under the prescribed sequence of projection angles is completed. If yes, perform step S3; if no, obtain the video for the certificate again.
  • step S4 a face video is obtained in real time.
  • the video of the certificate is obtained first, and on the premise that the certificate verification is passed, the face video is further obtained to perform the certificate holder verification. In this way, if the certificate verification fails, there is no need to continue the certificate holder verification, which can speed up the verification process and save system overhead.
  • the face video and the ID video can be obtained in the same video.
  • the same video acquisition module can be used to acquire the face video and the ID video.
  • the certificate and the certificate holder are verified separately. This not only simplifies the process and improves user satisfaction, but also further ensures that the real person holds the true certificate and the person holds the certificate, which further improves the school Test reliability.
  • step S5 it is verified whether there is a real person in the face video.
  • the verification process in step S5 may be performed by biopsy.
  • Living body detection is a method to determine the true physiological characteristics of an object in some identity verification scenarios, and can be used in scenarios such as face payment and remote identity verification.
  • living body detection can use combined actions such as blinking, opening mouth, shaking head, and nodding, using technologies such as facial key point positioning and face tracking, to verify whether the user is a real living person. It can effectively resist common attacks such as photos, face changes, masks, occlusions, and screen remakes, so as to help identify fraudulent behaviors and protect the interests of users.
  • the detection method of living body detection may be stereoscopic living body detection, sub-planar detection or infrared FMP detection. In this embodiment, the method of stereoscopic living body detection is preferred.
  • the human face video may be subjected to live detection on a frame-by-frame basis.
  • the verification process when verifying that the face video is not a real person, the verification process can be directly stopped, without the need to continue the extraction of face image features and the comparison of image features in the face video described later.
  • step S6 the image features of the face in the face video are extracted.
  • facial image features can be extracted from the facial video frame by frame.
  • the face image feature method used in this step can refer to the specific extraction method of S222.
  • step S7 when the certificate is verified to be true and the face video is a real person, the image characteristics of the certificate are compared with the image characteristics of the face in the face video to determine whether the certificate holder belongs to the certificate.
  • the facial image characteristics of the certificate extracted in step S222 may be compared with the facial image characteristics in the facial video.
  • the comparison can be performed by comparing the feature vectors of the same facial feature points, and comparing the shape and size of the facial feature points.
  • the comparison may be performed by a deep learning image processing method, and an image similarity algorithm may be used to calculate the similarity for determination.
  • a certain similarity threshold may be set, and when the similarity is within the threshold, the comparison can be considered as passing. By setting the similarity threshold, it is possible to eliminate the influence of the comparison of objective conditions such as light and clarity.
  • the display terminal prompts that the comparison is passed; if the comparison fails, it displays that the comparison is not passed, prompting the holder to compare again or exit.
  • the authenticity of the certificate can be effectively verified, and at the same time, it can be further authenticated whether the certificate holder is the current person.
  • FIG. 2 shows an exemplary configuration block diagram of an apparatus 2000 for verifying a certificate and a certificate holder according to an embodiment of the present disclosure.
  • the apparatus 2000 may include a processing circuit 2010.
  • the processing circuit 2010 of the device 2000 provides various functions of the device 2000.
  • the processing circuit 2010 of the device 2000 may be configured to execute the method for verifying a document and a certificate holder described above with reference to FIG. 1.
  • the processing circuit 2010 may refer to various implementations of a digital circuit system, an analog circuit system, or a mixed signal (combination of analog and digital) circuit system that performs functions in a computing system.
  • Processing circuits may include, for example, circuits such as integrated circuits (ICs), application specific integrated circuits (ASICs), parts or circuits of individual processor cores, entire processor cores, individual processors, such as field programmable gate arrays (FPGA) Programmable hardware devices, and/or systems that include multiple processors.
  • ICs integrated circuits
  • ASICs application specific integrated circuits
  • FPGA field programmable gate arrays
  • the processing circuit 2010 may include a first video acquisition module 2020, a first extraction module 2030, a first verification module 2040, a second video acquisition module 2050, a second verification module 2060, a second extraction module 2070, To the module 2080.
  • the first video acquisition module 2020 is used for real-time acquisition of a video of the certificate with a prescribed sequence of projection angles; the first extraction module 2030 is used for extracting the image features of the certificate under different projection angles in the video; the first verification module 2040 is used for according to the image characteristics of the certificate , Verify the authenticity of the certificate; the second video acquisition module 2050 is used to obtain face video in real time; the second verification module 2060 is used to verify whether the face video is a real person; the second extraction module 2070 is used to extract the person in the face video The image characteristics of the face; the comparison module 2080 is used to compare the image characteristics of the certificate with the image characteristics of the face in the face video when the verification certificate is true and the face video is a real person to determine the holder Whether it belongs to the certificate.
  • the above-mentioned modules 2020-2080 may be respectively configured to execute steps S1 to S7 in the method for verifying a document and a certificate holder shown in FIG. 1.
  • the device 2000 may further include a memory (not shown).
  • the memory of the device 2000 may store information generated by the processing circuit 2010 and programs and data used for the operation of the device 2000.
  • the memory may be volatile memory and/or non-volatile memory.
  • the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read only memory (ROM), and flash memory.
  • the apparatus 2000 may be implemented at the chip level, or may also be implemented at the device level by including other external components.
  • each of the foregoing modules may be implemented as an independent physical entity, or may also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), integrated circuit, etc.).
  • the device 2000 may include a third verification module 2090, which is used to verify whether the video acquisition of the certificate under the prescribed sequence of projection angles is completed according to the image characteristics of the certificate under different projection angles.
  • the third verification module 2090 may be configured to perform the aforementioned step S8, for example.
  • the first extraction module 2030 may include the following modules: a split sub-module 2031 for splitting the video into multiple pictures by frame; and a first extraction sub-module 2032 for extracting the multiple pictures The image features of the certificates in each picture; the first processing sub-module 2033 is used to calculate the projection angle of each picture according to the position of the certificate in each of the multiple pictures; the recording sub-module 2034: used to record the The image characteristics of the certificate in each of the multiple pictures and the projection angle of the corresponding picture.
  • the aforementioned modules 2031 to 2034 may be configured to execute the aforementioned steps S21 to S24, for example.
  • the authenticity of the document can be effectively verified, and at the same time, it can be further verified whether it is the current holder of the certificate.
  • FIG. 3 shows an exemplary configuration of a computing device 300 according to an embodiment of the present invention.
  • the computing device 1200 is an example of a hardware device to which the aforementioned aspects of the present invention can be applied.
  • the computing device 300 may be any machine configured to perform processing and/or calculations.
  • the computing device 300 may be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal data assistant (PDA), a smart phone, a vehicle-mounted computer, or a combination thereof.
  • PDA personal data assistant
  • the computing device 300 may include one or more elements that can be connected to or communicate with the bus 302 via one or more interfaces.
  • Bus 302 may include, but is not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standard Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, etc.
  • the computing device 300 may include, for example, one or more processors 304, one or more input devices 306, and one or more output devices 308.
  • the one or more processors 304 may be any kind of processors, and may include, but are not limited to, one or more general-purpose processors or special-purpose processors (such as special-purpose processing chips).
  • the processor 304 may correspond to the processing circuit 1010 in FIG. 1, for example, and is configured to implement the functions of each module of the verification document and the certificate holder device of the present disclosure.
  • the input device 306 may be any type of input device capable of inputting information to the computing device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a microphone, and/or a remote controller.
  • the output device 308 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video/audio output terminal, a vibrator, and/or a printer.
  • the computing device 300 may also include or be connected to a non-transitory storage device 314.
  • the non-transitory storage device 314 may be any storage device that is non-transitory and can realize data storage, and may include, but is not limited to, disk drives, optical Storage device, solid state memory, floppy disk, flexible disk, hard disk, tape or any other magnetic medium, compact disk or any other optical medium, cache memory and/or any other storage chip or module, and/or computer can read data from it , Instructions and/or any other medium of code.
  • the computing device 300 may also include random access memory (RAM) 310 and read only memory (ROM) 312.
  • the ROM 312 may store programs, utility programs, or processes to be executed in a nonvolatile manner.
  • the RAM 310 may provide volatile data storage and store instructions related to the operation of the computing device 300.
  • the computing device 300 may also include a network/bus interface 316 coupled to the data link 318.
  • the network/bus interface 316 may be any kind of equipment or system capable of enabling communication with external devices and/or networks, and may include, but is not limited to, modems, network cards, infrared communication equipment, wireless communication equipment, and/or chipsets (such as Bluetooth (TM) device, an 802.11 device, WiFi equipment, WiMax, cellular communication facilities, etc.).
  • Scheme 1 A device for school verification documents and certificate holders, including:
  • One or more processors are One or more processors;
  • Solution 3 In the verification document and certificate holder device of Solution 1, the computer-executable instructions, when executed by the one or more processors, cause the one or more processors to:
  • Solution 4 In the verification document and certificate holder device of Solution 1, the computer-executable instructions, when executed by the one or more processors, cause the one or more processors to:
  • the image characteristics of the certificate include the visual anti-counterfeiting characteristics of the certificate and the image characteristics of the face in the certificate,
  • the image feature of the face in the certificate is compared with the image feature of the face in the face video to determine whether the certificate holder is the person who belongs to the certificate.
  • Plan 6 In the school verification document and the device of the certificate holder in Plan 5,
  • the visual anti-counterfeiting features include dynamic visual anti-counterfeiting features that change with the change of the projection angle.
  • the aforementioned embodiments may be embodied as computer-readable codes on a computer-readable medium.
  • the computer-readable medium is any data storage device that can store data, which can be thereafter read by a computer system. Examples of computer readable media include read only memory, random access memory, CD-ROM, DVD, magnetic tape, hard disk drive, solid state drive, and optical data storage device.
  • the computer-readable medium may also be distributed in computer systems coupled to a network so that the computer-readable code is stored and executed in a distributed manner.
  • Hardware circuits may include combinational logic circuits, clock storage devices (such as floppy disks, flip-flops, latches, etc.), finite state machines, memories such as static random access memories or embedded dynamic random access memories, custom-designed circuits, Any combination of programmable logic array, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

本发明公开一种校验证件与持证人的方法及装置,该方法包括:实时获取证件具有规定序列投影角度的视频;提取所述视频中不同投影角度下证件的图像特征;根据所述证件的图像特征,验证所述证件的真假;实时获取人脸视频;验证所述人脸视频中是否为真人;提取所述人脸视频中人脸的图像特征;当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。

Description

一种校验证件与持证人的方法及装置 技术领域
本发明涉及计算机技术领域,特别涉及一种校验证件与持证人的方法及装置。
背景技术
防伪技术指能对伪造行为起到遏制作用的某种手段,它能较大地增加伪造的难度和成本,或降低伪造的仿真度。形式防伪是指产品之外的防伪技术,一般具有很强的适应性和较长的防伪生命周期。由于它借助于产品之外的防伪手段,因此防伪标识必须与产品或其包装紧密结合在一起而形成密不可分的整体。例如防揭粘贴标签、烫印标签、直接印刷或模压等技术。目前绝大多数防伪技术和方法都属于形式防伪,如包装防伪、密码防伪、各种防伪标识或商标等。
图像处理是指对图像进行分析、加工、和处理,使其满足视觉、心理或其他要求的技术。图像处理是信号处理在图像领域上的一个应用。目前大多数的图像均是以数字形式存储,因而图像处理很多情况下指数字图像处理。此外,基于光学理论的处理方法依然占有重要的地位。图像处理是信号处理的子类,另外与计算机科学、人工智能等领域也有密切的关系。
随着互联网的普及,需要线上办理业务的场景越来越多。线上办理业务需要用户上传个人的证件影像,例如身份证、护照、驾驶证等等,在一些场景下需要校验证件的真伪。
发明内容
在下文中给出了关于本公开的简要概述,以便提供关于本公开的一些方面的基本理解。但是,应当理解,这个概述并不是关于本公开的穷举性概述。它并不是意图用来确定本公开的关键性部分或重要部分,也不是意图用来限定本公开的范围。其目的仅仅是以简化的形式给出关于本公开的某些概念,以此作为稍后给出的更详细描述的前序。
根据本公开的一个方面,提供了一种校验证件与持证人的方法,所述方法包括如下步骤:
实时获取证件具有规定序列投影角度的视频;
提取所述视频中不同投影角度下证件的图像特征;
根据所述证件的图像特征,验证所述证件的真假;
实时获取人脸视频;
验证所述人脸视频中是否为真人;
提取所述人脸视频中人脸的图像特征;
当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
根据本公开的另一方面,提供了一种校验证件与持证人的装置,所述装置包括:
第一视频获取模块:用于实时获取证件具有规定序列投影角度的视频;
第一提取模块:用于提取所述视频中不同投影角度下证件的图像特征;
第一验证模块:用于根据所述证件的图像特征,验证所述证件的真假;
第二视频获取模块:用于实时获取人脸视频;
第二验证模块:用于验证所述人脸视频中是否为真人;
第二提取模块:用于提取所述人脸视频中人脸的图像特征;
比对模块:用于当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
根据本公开的又一方面,提供了一种校验证件与持证人的装置,所述装置包括:
一个或多个处理器;
存储器,其上存储有计算机可执行指令,所述计算机可执行指令在由所述一个或多个处理器执行时使得所述一个或多个处理器:
实时获取证件具有规定序列投影角度的视频;
提取所述视频中不同投影角度下证件的图像特征;
根据所述证件的图像特征,验证所述证件的真假;
实时获取人脸视频;
验证所述人脸视频中是否为真人;
提取所述人脸视频中人脸的图像特征;
当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
根据本公开的又一方面,提供了一种计算机可读存储介质,其上存储有计算机程序,所述程序被处理器运行时,使所述处理器执行如下处理:
实时获取证件具有规定序列投影角度的视频;
提取所述视频中不同投影角度下证件的图像特征;
根据所述证件的图像特征,验证所述证件的真假;
实时获取人脸视频;
验证所述人脸视频中是否为真人;
提取所述人脸视频中人脸的图像特征;
当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
根据本公开的一个或多个实施例,能够在有效验证证件真假的同时,进一步认证当前是否为本人持证状态。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是根据本公开的实施例的校验证件与持证人的方法的示例性流程图;
图2是根据本公开的实施例的校验证件与持证人的装置的示例性配置框图;
图3是可以实现根据本公开的实施例的计算设备的示例性配置。
具体实施方式
为使本发明的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
在线上办理业务时,有时会要求上传个人的证件影像,以验证证件的真伪。本公开的发明人知晓的一种方式是上传证件图像。然而,这种方式并不能确保证件是真实的,例如有可能上传伪造的证件图像。另外,也不能保证上传证件图像的用户是持证人本人。因此,这样的方式可能会对业务办理带来一定的风险。
本公开提供了一种校验证件与持证人的方法及装置,其通过不同投影角度校验证件真伪、校验是否为真人持证、真人人脸图像特征与证件上人脸图像特征并比对来校验是否为本人持证。根据本公开的一个或多个实施例,能够在有效验证证件真假的同时,进一步认证当前是否为本人持证状态。
下面参照图1~图3来说明根据本公开的校验证件与持证人的方法和装置。
图1示出根据本公开的实施例的校验证件与持证人的方法的示例性流程图。
如图1所示,在步骤S1中,实时获取证件具有规定序列投影角度的视频。
在一些实施例中,视频例如可以通过安装在终端装置(例如用于校验证件与持证人的专用设备、智能电脑、平板计算机等移动终端)上的摄像头来实时采集。
在步骤S1中,为了获取具有规定序列投影角度的视频,在一些实施例中,可以获取持证人手持证件完成规定序列动作的视频,规定序列动作使证件具有规定序列投影角度。在这样的实施例中,由持证人本人完成规定序列动作,不需要配置额外的人力和硬件设备,能够降低人力、物理成本。
在一些实施例中,可以通过采集辅助设备抓取证件完成规定序列动作的视频,规定序列动作使证件具有规定序列投影角度。采集辅助设备例如可以是程序控制的机械手。在这样的实施例中,通过采集辅助设备完成规定序列动作的视频,所获取的视频中的规定序列投影角度更规范,能够使得后续的证件验证过程更准确。
另外,在一些实施例中,也可以通过配置的工作人员持证操作,来获取具有规定序列投影角度的视频。
为便于说明,以下采用持证人本人持证完成规定序列动作的视频为例进行撰述。
在一些实施例中,在步骤S1之前,还可以包括如下步骤:随机调取若干个规范证件动作画面,生成具有序列动作的视频并进行前端展示,提示持证人按照示意完成该规定序列动作。持证人在完成序列动作时,能使证件依次处于不同位置,并具有不同的投影角度。
本实施例中的投影角度例如可以是证件与相机投影面之间所成的角度。具体可以为,证件中心点与相机投影面中心点的连线与相机投影面所称的角度。
规定序列投影角度的数量可以是一个或多个。在一些实施例中,通过设置不同方向和/或不同角度范围的多个投影角度,能够获取不同方向和/或不同投影角度下的证件图像特征,从而提高校验的可靠性。
示例性地,一组证件序列投影角度可以包括:上方45°、左侧45°、下方45°、右侧45°、中间90°。持证使证件依次位于相机投影面中心点的上方45°、左侧45°、下方45°、右侧45°及相机投影面中心点正前方处。可以通过前端展示,向持证人展示上述各投影角度,从而提示持证人按照示意完成该规定序列动作。
在步骤S2中,提取视频中不同投影角度下证件的图像特征。
在一些实施例中,步骤S2可以包括如下子步骤:
S21、将视频按帧拆分成多个图片;
S22、提取每一图片中证件的图像特征;
S23、根据每一图片中证件的位置,计算图片的投影角度;
S24、记录每一图片中证件的图像特征以及对应的图片的投影角度。
步骤S22中的证件的图像特征可以包括证件的视觉防伪特征以及证件中人脸的图像特征。可以使用计算机视觉相关技术来提取证件的图像特征。在一些实施例中,可采用SIFT、SURF、BRIEF、ORB等算法来提取。
在一些实施例中,步骤S22可以包括步骤S221:提取图片中证件的视觉防伪特征。
证件的视觉防伪特征可以包括静态视觉防伪特征。静态视觉防伪特征例如包括纹理、颜色、文字等,不会随着证件与相机投影面的投影角度的变化而变化。可以通过计算机视觉算法对静态视觉防伪特征进行验证。另外,证件的视觉防伪特征可以包括动态视觉防伪特征。动态视觉防伪特征可以包括颜色、形状等,会随着投影角度的变化而变化。动态视觉防伪特征例如可以是镭射防伪码,可以通过计算机视觉的方法记录不同角度镭射防伪码的变化,验证动态视觉防伪特征。
在一些实施例中,步骤S22可以包括步骤S222:提取所述图片中证件的人脸图像特征。
在一些实施例中,步骤S222可以具体包括如下子步骤:
S2221、定义及定位人脸特征点,可以利用图像梯度的方向定义和定位图片中的人脸特征点;
S2222、提取步骤S2221中人脸特征点的特征向量;
S2223、利用一个考虑了人脸特征点的特征及相对关系的统计模型,采用统计推理的方法,标注人脸特征点,从而确定需要的人脸特征点的位置。
一般的,人脸特征点可以包括:眼、鼻等特征。
在一些实施例中,步骤S23可以包括如下子步骤:
S231、通过特征匹配算法获取每一图片中证件的位置,具体为,通过查找计算homograph(单应矩阵)后,通过放射变换计算证件的具体位置。
S232、根据步骤S231计算获得每一图片中证件位置与相机投影面之间所成的角度计算证件的投影角度。
在步骤S3中,根据证件的图像特征,验证证件的真假。
在一些实施例中,步骤S3可以包括如下子步骤:
S31、调取规定序列证件动作画面中证件在每一动作下所具有的规范投影角度范围,以及该规范投影角度范围内静态防伪特征与动态防伪特征的规范数据范围;
S32、将提取到相应图片中证件的视觉防伪特征与视觉方位特征的规范数据范围进行比对。当图片中的视觉防伪特征属于视觉防伪特征规范数据范围时,确定证件为真,进入 下一步骤;否则证件为假,终止校验并提示持证人进一步核实证件。在一些实施例中,当视觉防伪特征包括静态视觉防伪特征以及动态视觉防伪特征时,将静态视觉防伪特征、动态视觉防伪特征分别与静态视觉防伪特征规范数据范围、动态视觉防伪特征规范数据范围进行比对,以确认证件的真假。
通过设置每一动作下所具有的规范投影角度范围,允许校验者完成规定序列证件动作时存在小幅度的偏差。因此,即使校验者具有身高差异和/或感官判断差异,也能够顺利地完成校验,降低校验的虚警率。
在一些实施例中,在步骤S3之前,还可以包括步骤S8:根据不同投影角度下证件的图像特征,验证是否完成规定序列投影角度下证件的视频采集。若是,则执行步骤S3;若否,则再次获取针对证件的视频。
在一些实施例中,可以通过验证按帧拆分后图像中的图片的投影角度是否符合证件在规定序列投影下应有的投影角度,来验证是否完成规定序列投影角度下证件的采集,即验证持证人是否完成序列动作。
在步骤S4中,实时获取人脸视频。
在一些实施例中,先获取证件的视频,在证件校验通过的前提下,进一步获取人脸视频来进行持证人校验。通过这样的方式,如果证件校验未通过,则无需继续进行持证人校验,能够加快验证过程,节省系统开销。
在一些实施例中,人脸视频与证件视频可以在同一视频中获取。例如,可以从持证人手持证件完成规定序列动作的视频,获取证件具有规定序列投影角度的视频以及人脸视频。在这样的实施例中,可以利用同一视频获取模块来获取人脸视频与证件视频。
通过获取同时具有证件与持证人的视频,分别进行证件与持证人校验,如此,不仅简化流程,提高用户满意度,还可进一步确保真人持真证、本人持本证,进一步提高校验可靠性。
在步骤S5中,验证人脸视频中是否为真人。
在一些实施例中,可以通过活体检验来进行步骤S5中的验证过程。活体检测是在一些身份验证场景确定对象真实生理特征的方法,可用于刷脸支付、远程身份验证等场景。在人脸识别应用中,活体检测能通过眨眼、张嘴、摇头、点头等组合动作,使用人脸关键点定位和人脸追踪等技术,验证用户是否为真实活体本人操作。可有效抵御照片、换脸、面具、遮挡以及屏幕翻拍等常见的攻击手段,从而协助甄别欺诈行为,保障用户的利益。活体检测的检测方式可以是立体性活体检测、亚平面检测或红外FMP检测,本实施例中优选立体性活体检测的方式。
在一些实施例中,可以按帧对人脸视频进行活体检测。
在一些实施例中,在验证人脸视频中不是真人时,可以直接停止验证过程,而无需继续进行后述的人脸视频中人脸图像特征的提取和图像特征的比对。
在步骤S6中,提取人脸视频中人脸的图像特征。
在一些实施例中,可以按帧对人脸视频提取人脸图像特征。该步骤采用的人脸图像特征方法可参照S222的具体提取方式。
在步骤S7中,当验证证件为真,且人脸视频中为真人时,将证件的图像特征与人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
在一些实施例中,可以将在步骤S222中提取的证件的人脸图像特征与人脸视频中人脸的图像特征进行比对。
在进行比对时,可通过相同的人脸特征点的特征向量比对、以及人脸特征点的形状及大小的比对进行。在一些实施例中,可通过深度学习图像处理的方法来进行比对,可以采用图像相似度算法计算相似度来判定。在一些实施例中,可以设定一定相似度阈值,当相似度位于该阈值内时,可认为比对通过。通过设定相似度阈值,可以排除光线、清晰度等客观条件对比对造成的影响。
当比对通过,则证明持证人为证件所属人,当比对不通过,则证明持证人不是证件所属人。在一些实施例中,若比对通过,则显示端提示比对通过,若比对不通过,则显示比对不通过,提示持证人再次比对或退出。
根据本公开的校验证件与持证人的方法,能够在有效验证证件真假的同时,进一步认证当前是否为本人持证状态。
图2示出根据本公开的实施例的校验证件与持证人的装置2000的示例性配置框图。
在一些实施例中,装置2000可以包括处理电路2010。装置2000的处理电路2010提供装置2000的各种功能。在一些实施例中,装置2000的处理电路2010可以被配置为执行以上参照图1描述的校验证件与持证人的方法。
处理电路2010可以指在计算系统中执行功能的数字电路系统、模拟电路系统或混合信号(模拟和数字的组合)电路系统的各种实现。处理电路可以包括例如诸如集成电路(IC)、专用集成电路(ASIC)这样的电路、单独处理器核心的部分或电路、整个处理器核心、单独的处理器、诸如现场可编程门阵列(FPGA)的可编程硬件设备、和/或包括多个处理器的系统。
在一些实施例中,处理电路2010可以包括第一视频获取模块2020、第一提取模块2030、第一验证模块2040、第二视频获取模块2050、第二验证模块2060、第二提取模块2070、 比对模块2080。
第一视频获取模块2020用于实时获取证件具有规定序列投影角度的视频;第一提取模块2030用于提取视频中不同投影角度下证件的图像特征;第一验证模块2040用于根据证件的图像特征,验证证件的真假;第二视频获取模块2050用于实时获取人脸视频;第二验证模块2060用于验证人脸视频中是否为真人;第二提取模块2070用于提取人脸视频中人脸的图像特征;比对模块2080用于当验证证件为真,且人脸视频中为真人时,将证件的图像特征与人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。上述模块2020~2080可以分别被配置为执行前述图1中所示的校验证件与持证人的方法中的步骤S1~步骤S7。
在一些实施例中,装置2000还可以包括存储器(未图示)。装置2000的存储器可以存储由处理电路2010产生的信息以及用于装置2000操作的程序和数据。存储器可以是易失性存储器和/或非易失性存储器。例如,存储器可以包括但不限于随机存取存储器(RAM)、动态随机存取存储器(DRAM)、静态随机存取存储器(SRAM)、只读存储器(ROM)以及闪存存储器。另外,装置2000可以以芯片级来实现,或者也可以通过包括其它外部部件而以设备级来实现。
应当理解,上述各个模块仅是根据其所实现的具体功能所划分的逻辑模块,而不是用于限制具体的实现方式。在实际实现时,上述各个模块可被实现为独立的物理实体,或者也可由单个实体(例如,处理器(CPU或DSP等)、集成电路等)来实现。
在一些实施例中,装置2000可以包括第三验证模块2090,用于根据不同投影角度下证件的图像特征,验证是否完成规定序列投影角度下证件的视频获取。第三验证模块2090例如可以被配置为执行前述步骤S8。
在一些实施例中,第一提取模块2030可以包括如下模块:拆分子模块2031,用于将视频按帧拆分成多个图片;第一提取子模块2032,用于提取所述多个图片中的各图片中证件的图像特征;第一处理子模块2033,用于根据所述多个图片中的各图片中证件的位置,计算各图片的投影角度;记录子模块2034:用于记录所述多个图片中的各图片中证件的图像特征以及对应的图片的投影角度。上述模块2031~2034例如可以分别被配置为执行前述步骤S21~S24。
根据本公开的校验证件与持证人的装置,能够在有效验证证件真假的同时,进一步认证当前是否为本人持证状态。
图3示出了可以实现根据本发明的实施例的计算设备300的示例性配置。计算设备1200是可以应用本发明的上述方面的硬件设备的实例。计算设备300可以是被配置为执行 处理和/或计算的任何机器。计算设备300可以是但不限制于工作站、服务器、台式计算机、膝上型计算机、平板计算机、个人数据助手(PDA)、智能电话、车载计算机或以上组合。
如图3所示,计算设备300可以包括可以经由一个或多个接口与总线302连接或通信的一个或多个元件。总线302可以包括但不限于,工业标准架构(Industry Standard Architecture,ISA)总线、微通道架构(Micro Channel Architecture,MCA)总线、增强ISA(EISA)总线、视频电子标准协会(VESA)局部总线、以及外设组件互连(PCI)总线等。计算设备300可以包括例如一个或多个处理器304、一个或多个输入设备306、以及一个或多个输出设备308。一个或多个处理器304可以是任何种类的处理器,并且可以包括但不限于一个或多个通用处理器或专用处理器(诸如专用处理芯片)。处理器304例如可以对应于图1中的处理电路1010,被配置为实现本公开的校验证件与持证人的装置的各模块的功能。输入设备306可以是能够向计算设备输入信息的任何类型的输入设备,并且可以包括但不限于鼠标、键盘、触摸屏、麦克风和/或远程控制器。输出设备308可以是能够呈现信息的任何类型的设备,并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。
计算设备300还可以包括或被连接至非暂态存储设备314,该非暂态存储设备314可以是任何非暂态的并且可以实现数据存储的存储设备,并且可以包括但不限于盘驱动器、光存储设备、固态存储器、软盘、柔性盘、硬盘、磁带或任何其他磁性介质、压缩盘或任何其他光学介质、缓存存储器和/或任何其他存储芯片或模块、和/或计算机可以从其中读取数据、指令和/或代码的其他任何介质。计算设备300还可以包括随机存取存储器(RAM)310和只读存储器(ROM)312。ROM 312可以以非易失性方式存储待执行的程序、实用程序或进程。RAM 310可提供易失性数据存储,并存储与计算设备300的操作相关的指令。计算设备300还可包括耦接至数据链路318的网络/总线接口316。网络/总线接口316可以是能够启用与外部装置和/或网络通信的任何种类的设备或系统,并且可以包括但不限于调制解调器、网络卡、红外线通信设备、无线通信设备和/或芯片集(诸如蓝牙 TM设备、802.11设备、WiFi设备、WiMax设备、蜂窝通信设施等)。
另外,本公开的一个或多个实施例可以如下实施。
方案1:一种校验证件与持证人的装置,包括:
一个或多个处理器;
存储器,其上存储有计算机可执行指令,所述计算机可执行指令在由所述一个或多个处理器执行时使得所述一个或多个处理器:
实时获取证件具有规定序列投影角度的视频;
提取所述视频中不同投影角度下证件的图像特征;
根据所述证件的图像特征,验证所述证件的真假;
实时获取人脸视频;
验证所述人脸视频中是否为真人;
提取所述人脸视频中人脸的图像特征;
当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
方案2:在方案1的校验证件与持证人的装置中,
从持证人手持证件完成规定序列动作的视频,获取所述证件具有规定序列投影角度的视频以及所述人脸视频,其中,所述规定序列动作使证件具有规定序列投影角度。
方案3:在方案1的校验证件与持证人的装置中,所述计算机可执行指令在由所述一个或多个处理器执行时使得所述一个或多个处理器:
根据不同投影角度下证件的图像特征,验证是否完成规定序列投影角度下证件的视频获取。
方案4:在方案1的校验证件与持证人的装置中,所述计算机可执行指令在由所述一个或多个处理器执行时使得所述一个或多个处理器:
将所述视频按帧拆分成多个图片;
提取所述多个图片中的各图片中证件的图像特征;
根据所述多个图片中的各图片中证件的位置,计算各图片的投影角度;
记录所述多个图片中的各图片中证件的图像特征以及对应的图片的投影角度。
方案5:在方案1的校验证件与持证人的装置中,
所述证件的图像特征包括所述证件的视觉防伪特征以及所述证件中人脸的图像特征,
根据所述证件的视觉防伪特征来验证所述证件的真假,
将所述证件中人脸的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
方案6:在方案5的校验证件与持证人的装置中,
所述视觉防伪特征包括随着投影角度的变化而变化的动态视觉防伪特征。
应当理解,本说明书中“实施例”或类似表达方式的引用是指结合该实施例所述的特定特征、结构、或特性系包括在本公开的至少一具体实施例中。因此,在本说明书中,“在本公开的实施例中”及类似表达方式的用语的出现未必指相同的实施例。
可单独地或以任何组合方式来使用前述实施例的各个方面、实施方案、具体实施或特 征。可由软件、硬件或硬件与软件的组合来实现前述实施方案的各个方面。
例如,前述实施例可体现为计算机可读介质上的计算机可读代码。计算机可读介质为可存储数据的任何数据存储设备,所述数据其后可由计算机系统读取。计算机可读介质的示例包括只读存储器、随机存取存储器、CD-ROM、DVD、磁带、硬盘驱动器、固态驱动器和光学数据存储设备。计算机可读介质还可分布在网络耦接的计算机系统中使得计算机可读代码以分布式方式来存储和执行。
例如,前述实施例可采用硬件电路的形式。硬件电路可以包括组合式逻辑电路、时钟存储设备(诸如软盘、触发器、锁存器等)、有限状态机、诸如静态随机存取存储器或嵌入式动态随机存取存储器的存储器、定制设计电路、可编程逻辑阵列等的任意组合。
注意,上述仅为本发明的较佳实施例及所运用技术原理。本领域技术人员会理解,本发明不限于这里所述的特定实施例,对本领域技术人员来说能够进行各种明显的变化、重新调整和替代而不会脱离本发明的保护范围。因此,虽然通过以上实施例对本发明进行了较为详细的说明,但是本发明不仅仅限于以上实施例,在不脱离本发明构思的情况下,还可以包括更多其他等效实施例,而本发明的范围由所附的权利要求范围决定。

Claims (13)

  1. 一种校验证件与持证人的方法,其特征在于,所述方法包括如下步骤:
    实时获取证件具有规定序列投影角度的视频;
    提取所述视频中不同投影角度下证件的图像特征;
    根据所述证件的图像特征,验证所述证件的真假;
    实时获取人脸视频;
    验证所述人脸视频中是否为真人;
    提取所述人脸视频中人脸的图像特征;
    当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
  2. 根据权利要求1所述的校验证件与持证人的方法,其特征在于,
    从持证人手持证件完成规定序列动作的视频,获取所述证件具有规定序列投影角度的视频以及所述人脸视频,其中,所述规定序列动作使证件具有规定序列投影角度。
  3. 根据权利要求1所述的校验证件与持证人的方法,其特征在于,所述方法还包括:
    根据不同投影角度下证件的图像特征,验证是否完成规定序列投影角度下证件的视频获取。
  4. 根据权利要求1所述的校验证件与持证人的方法,其特征在于,所述提取所述视频中不同投影角度下证件的图像特征,包括如下子步骤:
    将所述视频按帧拆分成多个图片;
    提取所述多个图片中的各图片中证件的图像特征;
    根据所述多个图片中的各图片中证件的位置,计算各图片的投影角度;
    记录所述多个图片中的各图片中证件的图像特征以及对应的图片的投影角度。
  5. 根据权利要求1所述的校验证件与持证人的方法,其特征在于,
    所述证件的图像特征包括所述证件的视觉防伪特征以及所述证件中人脸的图像特征,
    根据所述证件的视觉防伪特征来验证所述证件的真假,
    将所述证件中人脸的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
  6. 根据权利要求5所述的校验证件与持证人的方法,其特征在于,
    所述视觉防伪特征包括随着投影角度的变化而变化的动态视觉防伪特征。
  7. 一种校验证件与持证人的装置,其特征在于,所述装置包括:
    第一视频获取模块:用于实时获取证件具有规定序列投影角度的视频;
    第一提取模块:用于提取所述视频中不同投影角度下证件的图像特征;
    第一验证模块:用于根据所述证件的图像特征,验证所述证件的真假;
    第二视频获取模块:用于实时获取人脸视频;
    第二验证模块:用于验证所述人脸视频中是否为真人;
    第二提取模块:用于提取所述人脸视频中人脸的图像特征;
    比对模块:用于当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
  8. 根据权利要求7所述的校验证件与持证人的装置,其特征在于,
    所述第一视频获取模块和所述第二视频获取模块从持证人手持证件完成规定序列动作的视频,分别获取所述证件具有规定序列投影角度的视频以及所述人脸视频,其中,所述规定序列动作使证件具有规定序列投影角度。
  9. 根据权利要求7所述的校验证件与持证人的装置,其特征在于,所述装置还包括:
    第三验证模块:用于根据不同投影角度下证件的图像特征,验证是否完成规定序列投影角度下证件的视频获取。
  10. 根据权利要求7所述的校验证件与持证人的装置,其特征在于,所述第一提取模块包括:
    拆分子模块:用于将所述视频按帧拆分成多个图片;
    第一提取子模块:用于提取所述多个图片中的各图片中证件的图像特征;
    第一处理子模块:用于根据所述多个图片中的各图片中证件的位置,计算各图片的投影角度;
    记录子模块:用于记录所述多个图片中的各图片中证件的图像特征以及对应的图片的投影角度。
  11. 根据权利要求7所述的校验证件与持证人的装置,其特征在于,
    所述证件的图像特征包括所述证件的视觉防伪特征以及所述证件中人脸的图像特征,
    所述第一验证模块根据所述证件的视觉防伪特征来验证所述证件的真假,
    所述比对模块将所述证件中人脸的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
  12. 根据权利要求11所述的校验证件与持证人的装置,其特征在于,
    所述视觉防伪特征包括随着投影角度的变化而变化的动态视觉防伪特征。
  13. 一种计算机可读存储介质,其上存储有计算机程序,其特征在于,所述程序被处 理器运行时,使所述处理器执行如下处理:
    实时获取证件具有规定序列投影角度的视频;
    提取所述视频中不同投影角度下证件的图像特征;
    根据所述证件的图像特征,验证所述证件的真假;
    实时获取人脸视频;
    验证所述人脸视频中是否为真人;
    提取所述人脸视频中人脸的图像特征;
    当验证所述证件为真,且所述人脸视频中为真人时,将所述证件的图像特征与所述人脸视频中人脸的图像特征进行比对,以确定持证人是否为证件所属人。
PCT/CN2019/092928 2019-04-29 2019-06-26 一种校验证件与持证人的方法及装置 WO2020220453A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
SG11202011107PA SG11202011107PA (en) 2019-04-29 2019-06-26 Method and apparatus for verifying certificate and certificate holder
JP2019547640A JP7071991B2 (ja) 2019-04-29 2019-06-26 証明書と持証者とを検査する方法及び装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910365958.3A CN110210312A (zh) 2019-04-29 2019-04-29 一种校验证件与持证人的方法及系统
CN201910365958.3 2019-04-29

Publications (1)

Publication Number Publication Date
WO2020220453A1 true WO2020220453A1 (zh) 2020-11-05

Family

ID=67785383

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/092928 WO2020220453A1 (zh) 2019-04-29 2019-06-26 一种校验证件与持证人的方法及装置

Country Status (4)

Country Link
JP (1) JP7071991B2 (zh)
CN (2) CN110210312A (zh)
SG (1) SG11202011107PA (zh)
WO (1) WO2020220453A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114333037A (zh) * 2022-02-25 2022-04-12 北京结慧科技有限公司 包含身份证的翻拍照片识别方法及系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110210312A (zh) * 2019-04-29 2019-09-06 众安信息技术服务有限公司 一种校验证件与持证人的方法及系统
CN111275105B (zh) * 2020-01-19 2023-10-20 支付宝实验室(新加坡)有限公司 一种证件验证方法、装置及电子设备
CN111275042B (zh) * 2020-01-21 2023-07-18 支付宝实验室(新加坡)有限公司 伪造证件的识别方法、装置及电子设备
CN112200136A (zh) * 2020-10-29 2021-01-08 腾讯科技(深圳)有限公司 证件真伪识别方法、装置、计算机可读介质及电子设备
CN113688698B (zh) * 2021-08-09 2022-09-16 河南职业技术学院 基于人工智能的人脸转正识别方法和系统
CN117237682A (zh) * 2023-10-17 2023-12-15 支付宝(杭州)信息技术有限公司 一种证件验证方法、装置、存储介质及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105844206A (zh) * 2015-01-15 2016-08-10 北京市商汤科技开发有限公司 身份认证方法及设备
CN106982426A (zh) * 2017-03-30 2017-07-25 广东微模式软件股份有限公司 一种远程实现旧卡实名制的方法与系统
CN107066983A (zh) * 2017-04-20 2017-08-18 腾讯科技(上海)有限公司 一种身份验证方法及装置
CN109117688A (zh) * 2017-06-22 2019-01-01 腾讯科技(深圳)有限公司 身份认证方法、装置及移动终端

Family Cites Families (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4972476A (en) * 1989-05-11 1990-11-20 Nathans Robert L Counterfeit proof ID card having a scrambled facial image
JP4011362B2 (ja) 2002-02-15 2007-11-21 浩 近藤 パスポートの偽造防止情報作成システム、パスポート及び偽造パスポート検出システム
JP2005122395A (ja) * 2003-10-15 2005-05-12 Toshiba Corp 証明用媒体、証明用媒体発行装置および顔照合装置
JP2008009617A (ja) 2006-06-28 2008-01-17 Glory Ltd 個人生体情報照合装置、個人生体情報照合プログラムおよび個人生体情報照合方法
NL2010045C2 (en) * 2012-12-21 2014-06-24 Morpho B V Identity document comprising a ghost image based on a two- dimensional image.
DE102013103522A1 (de) * 2013-04-09 2014-10-09 Bundesdruckerei Gmbh Bildaufnahmesystem zur Bildaufnahme eines Merkmals eines Identifikationsdokumentes
CN103440482A (zh) * 2013-09-02 2013-12-11 北方工业大学 基于隐蔽视频的身份证件持有人识别方法、系统和装置
CN104361274B (zh) * 2014-10-30 2018-02-16 深圳市富途网络科技有限公司 一种基于视频识别的身份认证方法及其系统
CN105825243A (zh) * 2015-01-07 2016-08-03 阿里巴巴集团控股有限公司 证件图像检测方法及设备
CN105989263A (zh) * 2015-01-30 2016-10-05 阿里巴巴集团控股有限公司 身份认证方法、开户方法、装置及系统
CN106302330B (zh) * 2015-05-21 2021-01-05 腾讯科技(深圳)有限公司 身份验证方法、装置和系统
CN105243357A (zh) * 2015-09-15 2016-01-13 深圳市环阳通信息技术有限公司 一种基于身份证件的人脸识别方法及人脸识别装置
CN105933280B (zh) * 2016-03-15 2019-01-08 天地融科技股份有限公司 身份认证方法和系统
CN105956578B (zh) * 2016-05-23 2019-05-14 深圳华中科技大学研究院 一种基于身份证件信息的人脸验证方法
CN106778525B (zh) * 2016-11-25 2021-08-10 北京旷视科技有限公司 身份认证方法和装置
CN106650646A (zh) * 2016-12-09 2017-05-10 南京合荣欣业金融软件有限公司 一种基于动作识别的活体人脸识别方法及系统
CN108573202A (zh) * 2017-03-17 2018-09-25 北京旷视科技有限公司 身份认证方法、装置和系统以及终端、服务器和存储介质
JP6803804B2 (ja) * 2017-06-05 2020-12-23 株式会社日立製作所 画像情報検証装置
CN107341839A (zh) * 2017-07-07 2017-11-10 成都东软学院 一种证件图像处理方法、装置及设备
CN107844748B (zh) * 2017-10-17 2019-02-05 平安科技(深圳)有限公司 身份验证方法、装置、存储介质和计算机设备
CN107944339B (zh) * 2017-10-20 2020-01-21 阿里巴巴集团控股有限公司 一种证件验证、身份验证方法和装置
CN108052814A (zh) * 2017-12-07 2018-05-18 四川大学 一种3d身份验证系统
CN207867529U (zh) * 2018-02-07 2018-09-14 广东万峯信息科技有限公司 多摄像头的人证核验机
CN108647576A (zh) * 2018-04-10 2018-10-12 阳光暖果(北京)科技发展有限公司 一种基于视频序列人脸识别的活体身份认证方法
JP6481073B1 (ja) 2018-07-31 2019-03-13 株式会社メルカリ プログラム、情報処理方法、情報処理装置
CN109389153B (zh) * 2018-08-31 2021-03-02 众安信息技术服务有限公司 一种全息防伪码校验方法及装置
CN109446900A (zh) * 2018-09-21 2019-03-08 平安科技(深圳)有限公司 证件真伪验证方法、装置、计算机设备及存储介质
CN109543551A (zh) * 2018-10-26 2019-03-29 平安科技(深圳)有限公司 身份证鉴别处理方法、装置、计算机设备及存储介质
CN109684987B (zh) * 2018-12-19 2021-02-23 南京华科和鼎信息科技有限公司 一种基于证件的身份验证系统及方法
CN110210312A (zh) * 2019-04-29 2019-09-06 众安信息技术服务有限公司 一种校验证件与持证人的方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105844206A (zh) * 2015-01-15 2016-08-10 北京市商汤科技开发有限公司 身份认证方法及设备
CN106982426A (zh) * 2017-03-30 2017-07-25 广东微模式软件股份有限公司 一种远程实现旧卡实名制的方法与系统
CN107066983A (zh) * 2017-04-20 2017-08-18 腾讯科技(上海)有限公司 一种身份验证方法及装置
CN109117688A (zh) * 2017-06-22 2019-01-01 腾讯科技(深圳)有限公司 身份认证方法、装置及移动终端

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114333037A (zh) * 2022-02-25 2022-04-12 北京结慧科技有限公司 包含身份证的翻拍照片识别方法及系统
CN114333037B (zh) * 2022-02-25 2022-05-13 北京结慧科技有限公司 包含身份证的翻拍照片识别方法及系统

Also Published As

Publication number Publication date
SG11202011107PA (en) 2020-12-30
JP2021524946A (ja) 2021-09-16
JP7071991B2 (ja) 2022-05-19
CN110210312A (zh) 2019-09-06
CN112507889A (zh) 2021-03-16

Similar Documents

Publication Publication Date Title
US11669607B2 (en) ID verification with a mobile device
WO2020220453A1 (zh) 一种校验证件与持证人的方法及装置
Yang et al. Preventing deepfake attacks on speaker authentication by dynamic lip movement analysis
Fathy et al. Face-based active authentication on mobile devices
CN108804884B (zh) 身份认证的方法、装置及计算机存储介质
US7873189B2 (en) Face recognition by dividing an image and evaluating a similarity vector with a support vector machine
US10824849B2 (en) Method, apparatus, and system for resource transfer
WO2016172872A1 (zh) 用于验证活体人脸的方法、设备和计算机程序产品
CN107133608A (zh) 基于活体检测和人脸验证的身份认证系统
TWI712980B (zh) 理賠資訊提取方法和裝置、電子設備
WO2019200872A1 (zh) 身份验证方法和装置、电子设备、计算机程序和存储介质
Wanyonyi et al. Open-source face recognition frameworks: A review of the landscape
KR20230007250A (ko) 안면윤곽선 인식 인공지능을 사용한 ubt 시스템 및 그 방법
McQuillan Is lip-reading the secret to security?
Mahesh et al. Face Recognition Based Automated Student Attendance System using Deep Learning
Chauhan et al. Image-Based Attendance System using Facial Recognition
Mishra et al. Integrating State-of-the-Art Face Recognition and Anti-Spoofing Techniques into Enterprise Information Systems
Ahlawat et al. Online invigilation: A holistic approach
US20240086508A1 (en) System and method for facilitating multi-factor face authentication of user
US20240177519A1 (en) Digital Verification of Users Based On Real-time Video Stream
Muratuly et al. Biometric authentication of students to control the learning process in online education
Findling Pan shot face unlock: Towards unlocking personal mobile devices using stereo vision and biometric face information from multiple perspectives
Bharathi Cloud Based Attendance Application Using Face Recognition
Chauhan et al. An Automated Attendance System Using Face Recognition Technique based on Haar Cascade with LBPH
Karki et al. Smart Attendance Monitoring System Using Face Recognition for People with Disabilities (PwDs)

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2019547640

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 19927368

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24.02.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19927368

Country of ref document: EP

Kind code of ref document: A1