WO2019085403A1 - 一种人脸识别智能比对方法、电子装置及计算机可读存储介质 - Google Patents

一种人脸识别智能比对方法、电子装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2019085403A1
WO2019085403A1 PCT/CN2018/083071 CN2018083071W WO2019085403A1 WO 2019085403 A1 WO2019085403 A1 WO 2019085403A1 CN 2018083071 W CN2018083071 W CN 2018083071W WO 2019085403 A1 WO2019085403 A1 WO 2019085403A1
Authority
WO
WIPO (PCT)
Prior art keywords
comparison
face
card
face recognition
user
Prior art date
Application number
PCT/CN2018/083071
Other languages
English (en)
French (fr)
Inventor
凌永辉
Original Assignee
平安科技(深圳)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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2019085403A1 publication Critical patent/WO2019085403A1/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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • 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
    • G06V40/178Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Definitions

  • the present application relates to an authentication method, and in particular, to an identification method, an electronic device, and a computer readable storage medium.
  • the face recognition technology is used to verify the identity of the user, and when the face recognition is performed, a fixed face recognition comparison threshold is adopted for all the crowds, which makes it difficult for a person with a large change in appearance to handle the business through face recognition.
  • the success rate of face matching in a specific group is reduced, and customers are prone to loss.
  • the purpose of the present application is to provide a face recognition intelligent comparison method, an electronic device, and a computer readable storage medium, thereby further overcoming the problems existing in the prior art to some extent.
  • the present application provides a method for intelligently comparing face recognition, including the following steps:
  • Step 01 Collect ID information of the user to be identified.
  • Step 02 Determine whether the ID card is valid, if it is valid, proceed to step S3, and if invalid, the prompt is invalid.
  • Step 03 Perform face recognition comparison to obtain a first comparison threshold.
  • Step 04 Determine the population to which the user belongs according to the ID card information, and obtain a face recognition comparison reference threshold value of the belonging group.
  • Step 05 Determine whether the first comparison threshold is greater than or equal to the face recognition comparison reference threshold, and if yes, prompt the recognition to pass, if otherwise, the recognition fails.
  • the present application further provides an electronic device including a memory and a processor for storing a face recognition intelligent comparison system executed by a processor, the face recognition intelligent comparison system comprising:
  • the identity information collection module is configured to collect the ID number, avatar and age range information of the user ID card.
  • the ID card validity judging module is configured to compare the collected ID card information with the information in the third-party ID card information network to determine whether the ID card is valid.
  • the face recognition module is configured to compare the collected scene face photos with the ID card avatar photos, and give a similarity comparison value, that is, a first comparison threshold.
  • the reference threshold judging module is configured to determine, according to the extracted user age segment information, a population of the user and a face recognition comparison reference threshold of the crowd.
  • the threshold comparison module is configured to compare the first alignment threshold with the face recognition comparison reference threshold and give a comparison result.
  • the present application further provides a computer readable storage medium having a breakpoint data follow-up system stored therein, the breakpoint data follow-up system being executable by at least one processor To achieve the following steps:
  • Step 01 collecting identity card information of the user to be identified
  • Step 02 Determine whether the ID card is valid, if yes, proceed to step S3, and if invalid, the prompt is invalid;
  • Step 03 Perform face recognition comparison to obtain a first comparison threshold
  • Step 04 Determine, according to the ID card information, the user belonging to the group, and obtain a reference threshold for the face recognition comparison of the belonging group;
  • Step 05 Determine whether the first comparison threshold is greater than or equal to the face recognition comparison reference threshold, and if yes, prompt the recognition to pass, if otherwise, the recognition fails.
  • the solution avoids the decrease of matching success rate caused by using a uniform comparison threshold, provides recognition success rate of different groups, improves business processing efficiency and customer satisfaction. degree.
  • FIG. 1 is a flow chart showing an embodiment of the present applicant's face recognition intelligent comparison method.
  • FIG. 2 is a flow chart showing still another embodiment of the present applicant's face recognition intelligent comparison method.
  • FIG. 3 is a schematic diagram of a program module of an embodiment of the present applicant's face recognition intelligent comparison system.
  • FIG. 4 is a schematic diagram showing a program module of still another embodiment of the present applicant's face recognition intelligent comparison system.
  • FIG. 5 is a schematic diagram showing a program module of still another embodiment of the present applicant's face recognition intelligent comparison system.
  • FIG. 6 is a schematic diagram showing the hardware architecture of an embodiment of an electronic device of the present application.
  • a method for intelligently matching a face recognition which includes the following steps:
  • Step 01 Collect ID information of the user to be identified.
  • the ID card number, the avatar photo, and the age segment information of the user are collected by the ID card collector.
  • the ID card number is used to match and validate the information in the third-party identity information network, and is used to extract the age information of the user, and the avatar photo is used for face recognition verification.
  • step 02 it is judged whether the ID card is valid, if it is valid, the process proceeds to step 03, and if it is invalid, the prompt is invalid.
  • the collected ID information is compared with the data of the third-party identity information network to determine whether the ID card is valid, and whether it is still within the validity period. If it is determined to be invalid or exceeds the validity period, the direct feedback is invalid or the overdue prompt is Do not follow the next steps or prompt to go to the manual counter; if it is judged to be valid, perform step 03, this step can improve the efficiency of the query, eliminating the need to spend more time on the authentication and ultimately failing due to the expiration of the ID card Inquire.
  • the third-party identity information network may be a public security information inquiry network, and the public information inquiry network is used to query and obtain the user's avatar photo and identity information through a dedicated interface.
  • step 03 a face recognition comparison is performed to obtain a first comparison threshold.
  • the camera is opened to take a photo of the face, and the user's face photo collected on the spot is compared with the avatar photo on the ID card, wherein the face recognition comparison includes face collection and face features. Positioning, face feature extraction and face feature similarity comparison.
  • the face collection includes marking the face coordinates and detecting whether there is a human face, evaluating the shooting quality, and screenshotting the face image. Specifically, including marking the face coordinates after opening the camera and detecting whether there is a face, evaluating the shooting quality, and screening the face. image. It is detected whether a human face can judge whether it has a positive facial features and has a complete facial contour according to the coordinates of the hit and the pre-existing range of facial features.
  • Evaluating the photographing quality may include a head angle evaluation, a brightness evaluation, and a motion blur evaluation
  • the head angle evaluation includes determining whether the head is up and down, for example, within 15 degrees, the left and right declination is within, for example, 15 degrees, and the rotational declination is, for example, Within 20°, if it is consistent, it is considered to meet the head angle assessment
  • the brightness evaluation includes determining whether the brightness is within, for example, [80,200], if it is met, it is considered to meet the brightness evaluation
  • the dynamic fuzzy evaluation includes judging the fuzzy value. Whether it is less than 0.2, for example, if it is met, it is considered to be in compliance with the dynamic fuzzy assessment.
  • evaluating the quality of the shot may also include determining whether the user wears thick-rimmed glasses, sunglasses, or whether the hair blocks the ears or other facial features.
  • the facial feature localization includes positioning a plurality of features of the human face including the organ, including positioning a plurality of features of the human face including the eyebrows, the eyes, the nose, the mouth, and the like.
  • the facial feature extraction includes extracting a plurality of feature information of each feature according to a preset extraction rule.
  • the face feature similarity comparison includes comparing the extracted feature information with the feature information of the ID card avatar photo and obtaining a first comparison threshold, wherein the face feature may include a length and a slope.
  • the parameters such as the gradation difference represent the three-dimensional size, the oblique direction, the distance from other parts, and the like, and the face feature may be a set of feature information.
  • the facial feature similarity comparison may be to compare the two sets of feature information one by one, and define each feature information to have a certain weight, for example, the weight of the important feature information, and the weight of the secondary feature information is relatively small, and may also be defined. Some feature information is a necessary condition for judging that it must be consistent.
  • the photo is detextured after the photo of the ID card is obtained to improve the recognition effect.
  • the step of adjusting the camera angle and the shooting parameters according to the user information such as age, gender, and region in the identity information before the face collecting step is performed, so as to facilitate shooting of users with different features. Verify the required photos, reduce the false positive rate and increase the pass rate.
  • Step 04 Determine the population to which the user belongs according to the ID card information, and obtain a face recognition comparison reference threshold value of the belonging group.
  • the age of the user is extracted from the collected ID number, the age of the user is compared with the age group of the preset crowd, the population to which the user belongs is determined, and the reference threshold of the face recognition of the user is obtained according to the belonging group. .
  • the population is divided into three categories according to gender and age: A, B, and C.
  • Class A is a male with age ⁇ 50
  • class B is a woman with age ⁇ 50
  • class C is an age group with age ⁇ 50.
  • the face recognition comparison threshold of the class A population is 66
  • the face recognition comparison threshold value of the B group is 60
  • the face recognition comparison threshold of the C group is 55.
  • the threshold is dynamically adjustable. The face recognition score of a specific group will be counted again for a period of time, and then the face recognition comparison reference threshold of each group is automatically adjusted according to the newly obtained value.
  • the baseline threshold for each population is set based on historical alignment data, such as statistically identifying the face recognition scores for the elderly, and then setting a comparison reference threshold based on statistical scores and business needs. According to the extracted age information of the on-site user, it is determined which one of the categories A, B, and C the user belongs to, and the reference threshold of the user face recognition comparison is determined according to the belonging group.
  • the corresponding face recognition reference threshold is set by a specific group, which improves the success rate of the population identification matching with the change of the age with the increase of the age, and improves the number of customers and the efficiency of business processing.
  • Step 05 Determine whether the first comparison threshold is greater than or equal to the face recognition comparison reference threshold, and if yes, prompt the recognition to pass, if otherwise, the recognition fails.
  • the first comparison threshold obtained in the face recognition comparison step is compared with the reference threshold. If the first comparison threshold is greater than or equal to the reference threshold, the user identity verification is passed, and the user is prompted to pass. After entering the next business process, if the first comparison threshold is less than the reference threshold, the authentication fails, prompting the user to identify the failure.
  • FIG. 2 another method for intelligently matching face recognition is shown, which includes the following steps:
  • Step 01 Collect ID information of the user to be identified.
  • the ID card number, the avatar photo, and the age segment information of the user are collected by the ID card collector.
  • the ID card number is used to match and validate the information in the third-party identity information network, and is used to extract the age information of the user, and the avatar photo is used for face recognition verification.
  • step 02 it is judged whether the ID card is valid, if it is valid, the process proceeds to step 03, and if it is invalid, the prompt is invalid.
  • the collected ID information is compared with the data of the third-party identity information network to determine whether the ID card is valid, and whether it is still within the validity period. If it is determined to be invalid or exceeds the validity period, the direct feedback is invalid or the overdue prompt is Do not follow the next steps or prompt to go to the manual counter; if it is judged to be valid, perform step 03, this step can improve the efficiency of the query, eliminating the need to spend more time on the authentication and ultimately failing due to the expiration of the ID card Inquire.
  • the third-party identity information network may be a public security information inquiry network, and the public information inquiry network is used to query and obtain the user's avatar photo and identity information through a dedicated interface.
  • step 03 a face recognition comparison is performed to obtain a first comparison threshold.
  • the camera is opened to take a photo of the face, and the user's face photo collected on the spot is compared with the avatar photo on the ID card, wherein the face recognition comparison includes face collection and face features. Positioning, face feature extraction and face feature similarity comparison.
  • the face collection includes marking the face coordinates and detecting whether there is a human face, evaluating the shooting quality, and screenshotting the face image. Specifically, including marking the face coordinates after opening the camera and detecting whether there is a face, evaluating the shooting quality, and screening the face. image. It is detected whether a human face can judge whether it has a positive facial features and has a complete facial contour according to the coordinates of the hit and the pre-existing range of facial features.
  • Evaluating the photographing quality may include a head angle evaluation, a brightness evaluation, and a motion blur evaluation
  • the head angle evaluation includes determining whether the head is up and down, for example, within 15 degrees, the left and right declination is within, for example, 15 degrees, and the rotational declination is, for example, Within 20°, if it is consistent, it is considered to meet the head angle assessment
  • the brightness evaluation includes determining whether the brightness is within, for example, [80,200], if it is met, it is considered to meet the brightness evaluation
  • the dynamic fuzzy evaluation includes judging the fuzzy value. Whether it is less than 0.2, for example, if it is met, it is considered to be in compliance with the dynamic fuzzy assessment.
  • evaluating the quality of the shot may also include determining whether the user wears thick-rimmed glasses, sunglasses, or whether the hair blocks the ears or other facial features.
  • the facial feature localization includes positioning a plurality of features of the human face including the organ, including positioning a plurality of features of the human face including the eyebrows, the eyes, the nose, the mouth, and the like.
  • the facial feature extraction includes extracting a plurality of feature information of each feature according to a preset extraction rule.
  • the face feature similarity comparison includes comparing the extracted feature information with the feature information of the ID card avatar photo and obtaining a first comparison threshold, wherein the face feature may include a length and a slope.
  • the parameters such as the gradation difference represent the three-dimensional size, the oblique direction, the distance from other parts, and the like, and the face feature may be a set of feature information.
  • the facial feature similarity comparison may be to compare the two sets of feature information one by one, and define each feature information to have a certain weight, for example, the weight of the important feature information, and the weight of the secondary feature information is relatively small, and may also be defined. Some feature information is a necessary condition for judging that it must be consistent.
  • the photo ie, the photo of the ID card in the public security system
  • the photo is detextured to improve the recognition effect.
  • the step of adjusting the camera angle and the shooting parameters according to the user information such as age, gender, and region in the identity information before the face collecting step is performed, so as to facilitate shooting of users with different features. Verify the required photos, reduce the false positive rate and increase the pass rate.
  • Step 04 Determine the population to which the user belongs according to the ID card information, and obtain a face recognition comparison reference threshold value of the belonging group.
  • the age of the user is extracted from the collected ID number, the age of the user is compared with the age group of the preset crowd, the population to which the user belongs is determined, and the reference threshold of the face recognition of the user is obtained according to the belonging group. .
  • the population is divided into three categories according to gender and age: A, B, and C.
  • Class A is a male with age ⁇ 50
  • class B is a woman with age ⁇ 50
  • class C is an age group with age ⁇ 50.
  • the face recognition comparison threshold of the class A population is 66
  • the face recognition comparison threshold value of the B group is 60
  • the face recognition comparison threshold of the C group is 55.
  • the threshold is dynamically adjustable. The face recognition score of a specific group will be counted again for a period of time, and then the face recognition comparison reference threshold of each group is automatically adjusted according to the newly obtained value.
  • the baseline threshold for each population is set based on historical alignment data, such as statistically identifying the face recognition scores for the elderly, and then setting a comparison reference threshold based on statistical scores and business needs. According to the extracted age information of the on-site user, it is determined which one of the categories A, B, and C the user belongs to, and the reference threshold of the user face recognition comparison is determined according to the belonging group.
  • the corresponding face recognition reference threshold is set by a specific group, which improves the success rate of the population identification matching with the change of the age with the increase of the age, and improves the number of customers and the efficiency of business processing.
  • Step 05 Determine whether the first comparison threshold is greater than or equal to the face recognition comparison reference threshold, and if yes, prompt the recognition to pass, if otherwise, the recognition fails.
  • the first comparison threshold obtained in the face recognition comparison step is compared with the reference threshold. If the first comparison threshold is greater than or equal to the reference threshold, the user identity verification is passed, and the user is prompted to pass and enter. In the next business process, if the first comparison threshold is less than the reference threshold, the authentication fails, prompting the user to identify the failure.
  • step 06 it is determined whether remote video assisted recognition is required, and if yes, the process proceeds to step 07, and if not, the process ends.
  • the user face recognition fails, prompting the user to identify the failure, prompting the user whether remote video assistance is required for recognition. If the user selects yes, the user proceeds to the next remote identification step. If the user selects no, the face recognition step ends. , the next step cannot be performed.
  • Step 07 Remote video assisted recognition, if the recognition is passed, the prompt recognition is passed, and if the recognition is not passed, the end is completed.
  • the remote agent sends a remote video request to the client.
  • the video recognition mode is enabled, and the remote end manually identifies whether the remote user is consistent with the ID card information. The user identification is confirmed to pass, and if the information is inconsistent, the user identification is not passed, and the identification step ends.
  • the remote video assisted recognition at the agent end is added, and the user identity is manually determined through the agent end.
  • the dual recognition method improves the success rate of the identity verification and improves the user experience.
  • a face recognition intelligent comparison system 20 is illustrated.
  • the face recognition intelligent comparison system 20 is divided into one or more program modules, and one or more program modules are stored.
  • the invention is implemented in a storage medium and executed by one or more processors.
  • a program module as used herein refers to a series of computer program instructions that are capable of performing a particular function. The following description will specifically describe the functions of each program module of this embodiment:
  • the ID card information collection module 201 is configured to collect the ID card number, the avatar, and the age group information of the user ID card.
  • the ID card validity judging module 202 is configured to compare the collected ID card information with the information in the third-party ID card information network to determine whether the ID card is valid.
  • the face recognition module 203 is configured to perform feature matching on the collected live face photo and the ID card avatar photo, and give a similarity comparison value, that is, a first comparison threshold.
  • the face recognition module 203 further includes a face collection sub-module 2031, a face feature locating sub-module 2032, a face feature extraction sub-module 2033, and a face similarity comparison sub-module 2034.
  • the reference threshold judging module 204 is configured to determine, according to the extracted user age segment information, a population to which the user belongs and a face recognition comparison reference threshold of the crowd.
  • the threshold comparison module 205 is configured to compare the first alignment threshold with the face recognition comparison reference threshold and give a comparison result.
  • FIG. 4 another face recognition intelligent comparison system 20 is illustrated.
  • the face recognition intelligent comparison system 20 is divided into one or more program modules, and one or more program modules are It is stored in a storage medium and executed by one or more processors to complete the application.
  • a program module as used herein refers to a series of computer program instructions that are capable of performing a particular function. The following description will specifically describe the functions of each program module of this embodiment:
  • the ID card information collection module 201 is configured to collect the ID card number, the avatar, and the age group information of the user ID card.
  • the ID card validity judging module 202 is configured to compare the collected ID card information with the information in the third-party ID card information network to determine whether the ID card is valid.
  • the face recognition module 203 is configured to perform feature matching on the collected live face photo and the ID card avatar photo, and give a similarity comparison value, that is, a first comparison threshold.
  • the face recognition module 203 further includes a face collection sub-module 2031, a face feature locating sub-module 2032, a face feature extraction sub-module 2033, and a face similarity comparison sub-module 2034.
  • the reference threshold judging module 204 is configured to determine, according to the extracted user age segment information, a population to which the user belongs and a face recognition comparison reference threshold of the crowd.
  • the threshold comparison module 205 is configured to compare the first comparison threshold with the face recognition comparison reference threshold and give a comparison result.
  • the secondary nucleus determining module 206 is configured to determine whether the user who does not pass the face recognition needs remote video assisted identification to verify the identity.
  • the remote video identification module 207 is configured to perform remote identification and authentication on a user who needs to perform remote video assistance identification.
  • the embodiment provides an electronic device. It is a schematic diagram of the hardware architecture of an embodiment of the electronic device of the present application.
  • the electronic device 2 is an apparatus capable of automatically performing numerical calculation and/or information processing in accordance with an instruction set or stored in advance.
  • it can be a smartphone, a tablet, a laptop, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster composed of multiple servers).
  • the electronic device 2 includes at least, but not limited to, a memory 21, a processor 22, a network interface 23, an ID card collector 24, a camera 25, and a face recognition intelligent comparison.
  • System 20 among them:
  • the memory 21 includes at least one type of computer readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 21 may be an internal storage module of the electronic device 2, such as a hard disk or a memory of the electronic device 2.
  • the memory 21 may also be an external storage device of the electronic device 2, such as a plug-in hard disk equipped on the electronic device 2, a smart memory card (SMC), and a secure digital device. (Secure Digital, SD) card, flash card, etc.
  • the memory 21 can also include both the internal storage module of the electronic device 2 and its external storage device.
  • the memory 21 is generally used to store an operating system installed in the electronic device 2 and various types of application software, such as program codes of the face recognition intelligent comparison system 20. Further, the memory 21 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 22 is typically used to control the overall operation of the electronic device 2, such as performing control and processing associated with data interaction or communication with the electronic device 2.
  • the processor 22 is configured to run program code or process data stored in the memory 21, such as running the face recognition intelligent comparison system 20 and the like.
  • the network interface 23 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the electronic device 2 and other electronic devices.
  • the network interface 23 is configured to connect the electronic device 2 to an external terminal through a network, establish a data transmission channel, a communication connection, and the like between the electronic device 2 and an external terminal.
  • the network may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, or a 5G network.
  • Wireless or wired networks such as network, Bluetooth, Wi-Fi, etc.
  • Figure 5 only shows the electronic device with components 21-25, but it should be understood that not all illustrated components may be implemented and that more or fewer components may be implemented instead.
  • the face recognition intelligent comparison system 20 stored in the memory 21 may also be divided into one or more program modules, and the one or more program modules are stored in the memory 21, and It is executed by one or more processors (the processor 22 in this embodiment) to complete the application.
  • FIG. 3 is a schematic diagram of a program module of the first embodiment of the face recognition intelligent comparison system 20.
  • the face recognition intelligent comparison system 20 can be divided into ID card information collection.
  • the program module referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function.
  • the specific functions of the program modules 201-205 are described in detail in the third embodiment, and details are not described herein again.
  • the ID card collector 24 is configured to be connected to the ID card information collection module 201, and collect ID information stored by the user, such as pre-stored information in the chip of the second generation ID card.
  • the camera 25 is configured to be activated and deactivated by the face recognition module 203 to collect a face image of the operation terminal device.
  • a flash 26 is also included that is configured to be activated and deactivated by the shooting adjustment subroutine and adjusted in brightness.
  • the embodiment provides a computer readable storage medium on which the face recognition intelligent comparison system 20 is stored, when the face recognition intelligent comparison system 20 is executed by one or more processors.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Abstract

一种人脸识别智能比对方法、***、电子装置及计算机存储介质,其中,该方法包括以下步骤:步骤01、采集待识别用户的身份证信息;步骤02、判断所述身份证是否有效,若有效则进入步骤03,若无效则提示无效;步骤03、进行人脸识别比对,获得第一比对阈值;步骤04、根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值;步骤05、判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。通过上述方法及***,避免了现有技术中因使用统一的比对阈值造成的匹配成功率下降,提高不同人群的识别成功率,提高业务办理效率以及客户满意度。

Description

一种人脸识别智能比对方法、电子装置及计算机可读存储介质
本申请申明享有2017年10月31日递交的申请号为201711055465.7、名称为“一种人脸识别智能比对方法、电子装置及计算机可读存储介质”的中国专利申请的优先权,该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及身份验证方法,具体涉及一种身份识别方法、电子装置及计算机可读存储介质。
背景技术
随着互联网技术的发展,证券、银行、保险等很多行业的业务办理也逐渐可以在互联网或远程终端设备上直接远程办理,而在保险行业,在客户签订了新契约之后,保险公司会在规定的时间内对客户进行回访以核实身份,传统的回访通过电话询问的方式,该方式存在恶意人员被冒充回访者的可能,导致保险公式无法准确对客户进行身份核实,如果将这些业务搬到互联网或远程终端设备上,进行客户端远程核身,则面临如何确定是客户本人持本人有效证件在办理,存在冒充身份后伪造身份证的可能,导致回访时不能准确的对客户进行身份核实。
现有技术通过人脸识别技术对用户进行身份核实,进行人脸识别时,对所有人群采用固定的人脸识别比对阈值,导致样貌改变较大的人群难以通过人脸识别办理业务,造成特定人群人脸匹配成功率下降,客户易流失。
发明内容
本申请的目的在于提供一种人脸识别智能比对方法、电子装置以及计算机可读存储介质,进而在一定程度上克服现有技术中存在的问题。
本申请是通过下述技术方案来解决上述技术问题:
本申请提供一种人脸识别智能比对方法,包括以下步骤:
步骤01、采集待识别用户的身份证信息。
步骤02、判断所述身份证是否有效,若有效则进入步骤S3,若无效则提示无效。
步骤03、进行人脸识别比对,获得第一比对阈值。
步骤04、根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值。
步骤05、判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
为实现上述目的,本申请还提供一种电子装置,包括存储器和处理器,所述存储器用于存储被处理器执行的人脸识别智能比对***,所述人脸识别智能比对***包括:
身份信息采集模块,用于采集用户身份证的身份证号码、头像以及年龄段信息。
身份证有效性判断模块,用于将采集到的身份证信息与第三方身份证信息网中的信息进行比对,判断身份证是否有效。
人脸识别模块,用于将采集到的现场人脸照片与身份证头像照片进行特征比对,并给出相似度比对值即第一比对阈值。
基准阈值判断模块,用于根据提取的用户年龄段信息,判断用户所属人群以及该人群的人脸识别比对基准阈值。
阈值比对模块,用于将第一比对阈值与人脸识别比对基准阈值进行比对,并给出比对结果。
为实现上述目的,本申请还提供一种计算机可读存储介质,所述计算机 可读存储介质内存储有断点数据跟进***,所述断点数据跟进***可被至少一个处理器所执行,以实现以下步骤:
步骤01、采集待识别用户的身份证信息;
步骤02、判断所述身份证是否有效,若有效则进入步骤S3,若无效则提示无效;
步骤03、进行人脸识别比对,获得第一比对阈值;
步骤04、根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值;
步骤05、判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
本方案通过针对不同的用户群体设置相应的人脸识别比对基准阈值,避免了因使用统一的比对阈值造成的匹配成功率下降,提供不同人群的识别成功率,提高业务办理效率以及客户满意度。
附图说明
图1示出了本申请人脸识别智能比对方法一实施例的流程图。
图2示出了本申请人脸识别智能比对方法又一实施例的流程图。
图3示出了本申请人脸识别智能比对***一实施例的程序模块示意图。
图4示出了本申请人脸识别智能比对***又一实施例的程序模块示意图。
图5示出了本申请人脸识别智能比对***又一实施例的程序模块示意图。
图6示出了本申请电子装置一实施例的硬件架构示意图。
具体实施方式
实施例一
参阅图1,示出了一种人脸识别智能比对方法,包括如下步骤:
步骤01,采集待识别用户的身份证信息。
在该步骤中,通过身份证采集器采集用户的身份证号码、头像照片以及年龄段信息。身份证号码用于与第三方身份信息网中的信息进行匹配和有效性判断,并用于提取用户的年龄信息,头像照片用于人脸识别验证。
步骤02,判断所述身份证是否有效,若有效则进入步骤03,若无效则提示无效。
该步骤中,将采集到的身份证信息与第三方身份信息网的数据进行比对,判断身份证是否有效,是否仍处于有效期内,若判断为无效或超过有效期,直接反馈无效或超期提示,不进行后续步骤或提示前往人工柜台办理;若判断为有效,则执行步骤03,本步骤可提高查询效率,免去了花了较多时间在身份验证上而最终却因身份证过期而导致无法查询。实际应用中,也可以在步骤01中采集到身份证有效期之后根据***当日日期直接判断身份证是否处于有效期内。其中第三方身份信息网可以为公安信息查询网,通过专用接口从公安信息查询网上查询并获得用户的头像照片以及身份信息。
步骤03,进行人脸识别比对,获得第一比对阈值。
在该步骤中,打开摄像头进行人脸照片的拍摄,并将现场采集到的用户人脸照片与身份证上的头像照片进行识别比对,其中人脸识别比对包括人脸采集、人脸特征定位、人脸特征提取和人脸特征相似度比对。
所述人脸采集包括打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像,具体的,包括在打开摄像头之后打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像。检测是否有人脸可以根据打上的坐标以及预存的五官位置范围,判断是否具有正面的五官并具有完整的人脸轮廓。评估拍摄质量可以包括头部角度评估、明亮度评估和动态模糊评估,头部角度评估包括判断头部是否上下偏角在例如15°以内、左右偏角在例如15°以内、旋转偏角在例如20°以内,若均符合,则认为符合头部角度评估;明 亮度评估包括判断明亮度是否在例如【80,200】以内,若符合,则认为符合明亮度评估;动态模糊评估包括判断模糊值是否例如小于0.2,若符合,则认为符合动态模糊评估。若拍摄质量评估不符合要求,则提示需要用户调整的内容,如“请摆正头部”、“请略微低头”、“请略微远离摄像头”,若明亮度评估不符合要求,还可以通过摄像头旁设置的闪光灯进行调节。此外,评估拍摄质量还可以包括判断用户是否佩戴粗框眼镜、墨镜,是否头发遮挡耳朵或其他五官。
所述人脸特征定位包括对人脸的多个包含器官的特征进行定位,包括对人脸的多个包含眉毛、眼睛、鼻子、嘴巴等器官的特征进行定位。
所述人脸特征提取包括根据预设提取规则,提取每个特征的多个特征信息。
所述人脸特征相似度比对包括将提取到的多个特征信息与身份证头像照片的特征信息进行逐一比对,并获得第一比对阈值,其中,人脸特征可以包括长度、斜度、灰度差等参数来表现各部位的三维尺寸、倾斜方向、与其他部位的距离等,人脸特征可以是一组特征信息。人脸特征相似度比对可以是将两组特征信息逐一比对,并定义每个特征信息具有一定的权重,例如重要特征信息的权重大,次要特征信息的权重相对较小,也可以定义一些特征信息为必须符合一致作为判断为通过验证的必要条件。
在一个较佳实施例中,在获取身份证照片之后对该照片进行去网纹处理,提高识别效果。
在一个较佳实施例中,本步骤在进行人脸采集步骤之前,先根据身份信息中的年龄、性别、地区等用户信息调整摄像头的角度和拍摄参数,以便于对不同特征的用户进行拍摄符合验证要求的照片,更降低误识率,提高通过率。
步骤04,根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值。
在该步骤中,从采集到的身份证号码中提取用户的年龄,将用户年龄与预设人群年龄段进行对比,判断用户所属人群,并根据所属人群获得该用户的人脸识别比对基准阈值。
具体的,其中所属人群按性别和年龄分为:A、B、C三类,A类即年龄<50的男性,B类即年龄<50的女性,以及C类年龄≥50的老人三种人群,A类人群的人脸识别比对基准阈值为66,B类人群的人脸识别比对基准阈值为60,C类人群的人脸识别比对基准阈值为55,阀值是可以动态调整的,特定人群的人脸识别分值会在一段时间内再次统计,然后根据新得到的值,自动调整各个群体的人脸识别比对基准阀值。每种人群基准阀值的设定根据历史比对数据设定,如统计老年人群人脸识别分值,然后根据统计分值和业务需要设定一个比对基准阀值。根据提取的现场用户的年龄信息,判断该用户属于A、B、C中的哪一类,根据所属人群判断用户人脸识别比对的基准阈值。
该步骤中,通过特定人群设置相应的人脸识别基准阈值,提高了随着年龄的增长导致样貌改变较大的人群识别匹配的成功率,提高客户数量以及业务办理效率。
步骤05,判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
在该步骤中,将人脸识别比对步骤中获得第一比对阈值与基准阈值进行比较,若第一比对阈值大于或等于基准阈值,则该用户身份验证通过,提示用户识别通过,可进入下一个业务流程,若第一比对阈值小于基准阈值,则身份验证未通过,提示用户识别失败。
实施例二
参阅图2,示出了另一种人脸识别智能比对方法,包括如下步骤:
步骤01,采集待识别用户的身份证信息。
在该步骤中,通过身份证采集器采集用户的身份证号码、头像照片以及年龄段信息。身份证号码用于与第三方身份信息网中的信息进行匹配和有效性判断,并用于提取用户的年龄信息,头像照片用于人脸识别验证。
步骤02,判断所述身份证是否有效,若有效则进入步骤03,若无效则提示无效。
该步骤中,将采集到的身份证信息与第三方身份信息网的数据进行比对,判断身份证是否有效,是否仍处于有效期内,若判断为无效或超过有效期,直接反馈无效或超期提示,不进行后续步骤或提示前往人工柜台办理;若判断为有效,则执行步骤03,本步骤可提高查询效率,免去了花了较多时间在身份验证上而最终却因身份证过期而导致无法查询。实际应用中,也可以在步骤01中采集到身份证有效期之后根据***当日日期直接判断身份证是否处于有效期内。其中第三方身份信息网可以为公安信息查询网,通过专用接口从公安信息查询网上查询并获得用户的头像照片以及身份信息。
步骤03,进行人脸识别比对,获得第一比对阈值。
在该步骤中,打开摄像头进行人脸照片的拍摄,并将现场采集到的用户人脸照片与身份证上的头像照片进行识别比对,其中人脸识别比对包括人脸采集、人脸特征定位、人脸特征提取和人脸特征相似度比对。
所述人脸采集包括打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像,具体的,包括在打开摄像头之后打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像。检测是否有人脸可以根据打上的坐标以及预存的五官位置范围,判断是否具有正面的五官并具有完整的人脸轮廓。评估拍摄质量可以包括头部角度评估、明亮度评估和动态模糊评估,头部角度评估包括判断头部是否上下偏角在例如15°以内、左右偏角在例如15°以内、旋转偏角在例如20°以内,若均符合,则认为符合头部角度评估;明亮度评估包括判断明亮度是否在例如【80,200】以内,若符合,则认为符合明亮度评估;动态模糊评估包括判断模糊值是否例如小于0.2,若符合,则 认为符合动态模糊评估。若拍摄质量评估不符合要求,则提示需要用户调整的内容,如“请摆正头部”、“请略微低头”、“请略微远离摄像头”,若明亮度评估不符合要求,还可以通过摄像头旁设置的闪光灯进行调节。此外,评估拍摄质量还可以包括判断用户是否佩戴粗框眼镜、墨镜,是否头发遮挡耳朵或其他五官。
所述人脸特征定位包括对人脸的多个包含器官的特征进行定位,包括对人脸的多个包含眉毛、眼睛、鼻子、嘴巴等器官的特征进行定位。
所述人脸特征提取包括根据预设提取规则,提取每个特征的多个特征信息。
所述人脸特征相似度比对包括将提取到的多个特征信息与身份证头像照片的特征信息进行逐一比对,并获得第一比对阈值,其中,人脸特征可以包括长度、斜度、灰度差等参数来表现各部位的三维尺寸、倾斜方向、与其他部位的距离等,人脸特征可以是一组特征信息。人脸特征相似度比对可以是将两组特征信息逐一比对,并定义每个特征信息具有一定的权重,例如重要特征信息的权重大,次要特征信息的权重相对较小,也可以定义一些特征信息为必须符合一致作为判断为通过验证的必要条件。
在一个较佳实施例中,在获取身份证照片之后对该照片(即公安***中的身份证照片)进行去网纹处理,提高识别效果。
在一个较佳实施例中,本步骤在进行人脸采集步骤之前,先根据身份信息中的年龄、性别、地区等用户信息调整摄像头的角度和拍摄参数,以便于对不同特征的用户进行拍摄符合验证要求的照片,更降低误识率,提高通过率。
步骤04,根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值。
在该步骤中,从采集到的身份证号码中提取用户的年龄,将用户年龄与预设人群年龄段进行对比,判断用户所属人群,并根据所属人群获得该用户 的人脸识别比对基准阈值。
具体的,其中所属人群按性别和年龄分为:A、B、C三类,A类即年龄<50的男性,B类即年龄<50的女性,以及C类年龄≥50的老人三种人群,A类人群的人脸识别比对基准阈值为66,B类人群的人脸识别比对基准阈值为60,C类人群的人脸识别比对基准阈值为55,阀值是可以动态调整的,特定人群的人脸识别分值会在一段时间内再次统计,然后根据新得到的值,自动调整各个群体的人脸识别比对基准阀值。每种人群基准阀值的设定根据历史比对数据设定,如统计老年人群人脸识别分值,然后根据统计分值和业务需要设定一个比对基准阀值。根据提取的现场用户的年龄信息,判断该用户属于A、B、C中的哪一类,根据所属人群判断用户人脸识别比对的基准阈值。
该步骤中,通过特定人群设置相应的人脸识别基准阈值,提高了随着年龄的增长导致样貌改变较大的人群识别匹配的成功率,提高客户数量以及业务办理效率。
步骤05,判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
在该步骤中,将人脸识别比对步骤中获得第一比对阈值与基准阈值进行比较,若第一比对阈值大于等于基准阈值,则该用户身份验证通过,提示用户识别通过,可进入下一个业务流程,若第一比对阈值小于基准阈值,则身份验证未通过,提示用户识别失败。
步骤06,判断是否需要远程视频协助识别,若是则进入步骤07,若否则结束。
若用户人脸识别失败,在提示用户识别失败的同时,提示用户是否需要远程视频协助识别,若用户选择是,则进入下一步的远程识别步骤,若用户选择否,则该人脸识别步骤结束,无法进行下一步操作。
步骤07,远程视频辅助识别,若识别通过则提示识别通过,若识别未通 过则结束。
若用户选择需要远程视频辅助识别,则远程坐席端向用户端发送远程视频请求,用户端接受后,开启视频识别模式,由坐席端人工识别远程用户是否与身份证信息一致,若信息一致,则确认用户身份识别通过,若信息不一致,则提示用户身份识别未通过,该识别步骤结束。
该实施例中,在人脸识别失败后,增加了坐席端远程视频辅助识别,通过坐席端人工判断用户身份,双重识别方式结合提高了身份识别验证的成功率,提高用户体验。
实施例三
参阅图3,示出了一种人脸识别智能比对***20,在本实施例中,人脸识别智能比对***20被分割成一个或多个程序模块,一个或者多个程序模块被存储于存储介质中,并由一个或多个处理器所执行,以完成本申请。本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段。以下描述将具体介绍本实施例各程序模块的功能:
身份证信息采集模块201,用于采集用户身份证的身份证号码、头像以及年龄段信息。
身份证有效性判断模块202,用于将采集到的身份证信息与第三方身份证信息网中的信息进行比对,判断身份证是否有效。
人脸识别模块203,用于将采集到的现场人脸照片与身份证头像照片进行特征比对,并给出相似度比对值即第一比对阈值。
人脸识别模块203还包括:人脸采集子模块2031、人脸特征定位子模块2032、人脸特征提取子模块2033和人脸相似度比对子模块2034。
基准阈值判断模块204,用于根据提取的用户年龄段信息,判断用户所属人群以及该人群的人脸识别比对基准阈值。
阈值比对模块205,用于将第一比对阈值与人脸识别比对基准阈值进行 比对,并给出比对结果。
实施例四
参阅图4,示出了另一种人脸识别智能比对***20,在本实施例中,人脸识别智能比对***20被分割成一个或多个程序模块,一个或者多个程序模块被存储于存储介质中,并由一个或多个处理器所执行,以完成本申请。本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段。以下描述将具体介绍本实施例各程序模块的功能:
身份证信息采集模块201,用于采集用户身份证的身份证号码、头像以及年龄段信息。
身份证有效性判断模块202,用于将采集到的身份证信息与第三方身份证信息网中的信息进行比对,判断身份证是否有效。
人脸识别模块203,用于将采集到的现场人脸照片与身份证头像照片进行特征比对,并给出相似度比对值即第一比对阈值。
人脸识别模块203还包括:人脸采集子模块2031、人脸特征定位子模块2032、人脸特征提取子模块2033和人脸相似度比对子模块2034。
基准阈值判断模块204,用于根据提取的用户年龄段信息,判断用户所属人群以及该人群的人脸识别比对基准阈值。
阈值比对模块205,用于将第一比对阈值与人脸识别比对基准阈值进行比对,并给出比对结果。
二次核身判断模块206,用于判断未通过人脸识别的用户是否需要远程视频协助识别以核实身份。
远程视频识别模块207,用于对需要进行远程视频协助识别的用户进行远程识别身份验证。
实施例五
参阅图5,本实施例提供一种电子装置。是本申请电子装置一实施例的硬件架构示意图。本实施例中,所述电子装置2是一种能够按照事先设定或者存储的指令,自动进行数值计算和/或信息处理的设备。例如,可以是智能手机、平板电脑、笔记本电脑、台式计算机、机架式服务器、刀片式服务器、塔式服务器或机柜式服务器(包括独立的服务器,或者多个服务器所组成的服务器集群)等。如图所示,所述电子装置2至少包括,但不限于,可通过***总线相互通信连接存储器21、处理器22、网络接口23、身份证采集器24、摄像头25以及人脸识别智能比对***20。其中:
所述存储器21至少包括一种类型的计算机可读存储介质,所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如,SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中,所述存储器21可以是所述电子装置2的内部存储模块,例如该电子装置2的硬盘或内存。在另一些实施例中,所述存储器21也可以是所述电子装置2的外部存储设备,例如该电子装置2上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。当然,所述存储器21还可以既包括所述电子装置2的内部存储模块也包括其外部存储设备。本实施例中,所述存储器21通常用于存储安装于所述电子装置2的操作***和各类应用软件,例如所述人脸识别智能比对***20的程序代码等。此外,所述存储器21还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器22在一些实施例中可以是中央处理器(Central Processing Unit,CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理 器22通常用于控制所述电子装置2的总体操作,例如执行与所述电子装置2进行数据交互或者通信相关的控制和处理等。本实施例中,所述处理器22用于运行所述存储器21中存储的程序代码或者处理数据,例如运行所述的人脸识别智能比对***20等。
所述网络接口23可包括无线网络接口或有线网络接口,该网络接口23通常用于在所述电子装置2与其他电子装置之间建立通信连接。例如,所述网络接口23用于通过网络将所述电子装置2与外部终端相连,在所述电子装置2与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯***(Global System of Mobile communication,GSM)、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
需要指出的是,图5仅示出了具有部件21-25的电子装置,但是应理解的是,并不要求实施所有示出的部件,可以替代的实施更多或者更少的部件。
在本实施例中,存储于存储器21中的所述人脸识别智能比对***20还可以被分割为一个或者多个程序模块,所述一个或者多个程序模块被存储于存储器21中,并由一个或多个处理器(本实施例为处理器22)所执行,以完成本申请。
例如,图3示出了所述人脸识别智能比对***20第一实施例的程序模块示意图,该实施例中,所述基于人脸识别智能比对***20可以被划分为身份证信息采集模块201、身份证有效性判断模块202、人脸识别模块203、基准阈值判断模块204、阈值比对模块205。其中,本申请所称的程序模块是指能够完成特定功能的一系列计算机程序指令段。所述程序模块201-205的具体功能在实施例三中已有详细描述,在此不再赘述。
身份证采集器24用于与身份证信息采集模块201相连,采集用户放置 的身份证信息,如二代身份证的芯片内预存信息。
摄像头25被配置为被人脸识别模块203所驱动启动和关闭,采集操作终端设备的人脸图像。
在一个较佳实施例中,还包括闪光灯26,被配置为被拍摄调整子程序所驱动启动和关闭,并被调整亮度。
实施例六
本实施例提供一种计算机可读存储介质,该计算机可读存储介质上存储有所述人脸识别智能比对***20,该人脸识别智能比对***20被一个或多个处理器执行时实现上述人脸识别智能比对方法或电子装置的操作。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (15)

  1. 一种人脸识别智能比对方法,其特征在于,包括以下步骤:
    步骤01、采集待识别用户的身份证信息;
    步骤02、判断所述身份证是否有效,若有效则进入步骤S3,若无效则提示无效;
    步骤03、进行人脸识别比对,获得第一比对阈值;
    步骤04、根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值;
    步骤05、判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
  2. 根据权利要求1所述的人脸识别智能比对方法,其特征在于,步骤04包括:从采集到的身份证号码中提取用户的年龄,将用户年龄与预设人群年龄段进行对比,判断用户所属人群,并根据所属人群获得该用户的人脸识别比对基准阈值。
  3. 根据权利要求1所述的人脸识别智能比对方法,其特征在于,步骤01包括通过摄像头采集身份证照片,并通过身份证采集器从拍摄到的照片中识别提取用户的身份证号码、头像照片以及年龄段信息。
  4. 根据权利要求1所述的人脸识别智能比对方法,其特征在于,步骤03中人脸识别比对包括:将现场采集到的用户照片与身份证上的头像照片进行识别比对,其中人脸识别比对包括人脸采集、人脸特征定位、人脸特征提取和人脸特征相似度比对。
  5. 根据权利要求4所述的人脸识别智能比对方法,其特征在于,所述人脸采集包括打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像;所述人脸特征定位包括对人脸的多个包含器官的特征进行定位;所述人脸特征提取包括根据预设提取规则,提取每个特征的多个特征信息;所述人 脸特征相似度比对包括将提取到的多个特征信息与身份证头像照片的特征信息进行逐一比对,并获得第一比对阈值。
  6. 根据权利要求1所述的人脸识别智能比对方法,其特征在于,所述步骤还包括:
    步骤06、判断是否需要远程视频协助识别,若是则进入步骤07,若否则结束;
    步骤07、远程视频辅助识别,若识别通过则提示识别通过,若识别未通过则结束。
  7. 一种电子装置,包括存储器和处理器,其特征在于,所述存储器用于存储被处理器执行的人脸识别智能比对***,所述人脸识别智能比对***包括:
    身份证信息采集模块,用于采集用户身份证的身份证号码、头像以及年龄段信息;
    身份证有效性判断模块,用于将采集到的身份证信息与第三方身份证信息网中的信息进行比对,判断身份证是否有效;
    人脸识别模块,用于将采集到的现场人脸照片与身份证头像照片进行特征比对,并给出相似度比对值即第一比对阈值;
    基准阈值判断模块,用于根据提取的用户年龄段信息,判断用户所属人群以及该人群的人脸识别比对基准阈值;
    阈值比对模块,用于将第一比对阈值与人脸识别比对基准阈值进行比对,并给出比对结果。
  8. 根据权利要求7所述的电子装置,其特征在于,所述人脸识别模块还包括:人脸采集子模块、人脸特征定位子模块、人脸特征提取子模块和人脸相似度比对子模块。
  9. 根据权利要求7所述的电子装置,其特征在于,所述人脸识别智能比对***还包括:
    二次核身判断模块,用于判断未通过人脸识别的用户是否需要远程视频协助识别以核实身份;
    远程视频识别模块,用于对需要进行远程视频协助识别的用户进行远程识别身份验证。
  10. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质内存储有断点数据跟进***,所述断点数据跟进***可被至少一个处理器所执行,以实现以下步骤:
    步骤01、采集待识别用户的身份证信息;
    步骤02、判断所述身份证是否有效,若有效则进入步骤S3,若无效则提示无效;
    步骤03、进行人脸识别比对,获得第一比对阈值;
    步骤04、根据身份证信息判断用户所属人群,并获取所属人群的人脸识别比对基准阈值;
    步骤05、判断第一比对阈值是否大于等于人脸识别比对基准阈值,若是,则提示识别通过,若否则提示识别失败。
  11. 根据权利要求10所述的计算机可读存储介质,其特征在于,步骤04包括:从采集到的身份证号码中提取用户的年龄,将用户年龄与预设人群年龄段进行对比,判断用户所属人群,并根据所属人群获得该用户的人脸识别比对基准阈值。
  12. 根据权利要求10所述的计算机可读存储介质,其特征在于,步骤01包括通过摄像头采集身份证照片,并通过身份证采集器从拍摄到的照片中识别提取用户的身份证号码、头像照片以及年龄段信息。
  13. 根据权利要求10所述的计算机可读存储介质,其特征在于,步骤03中人脸识别比对包括:将现场采集到的用户照片与身份证上的头像照片进行识别比对,其中人脸识别比对包括人脸采集、人脸特征定位、人脸特征提取和人脸特征相似度比对。
  14. 根据权利要求13所述的计算机可读存储介质,其特征在于,所述人脸采集包括打上人脸坐标并检测是否有人脸,评估拍摄质量,截图人脸图像;所述人脸特征定位包括对人脸的多个包含器官的特征进行定位;所述人脸特征提取包括根据预设提取规则,提取每个特征的多个特征信息;所述人脸特征相似度比对包括将提取到的多个特征信息与身份证头像照片的特征信息进行逐一比对,并获得第一比对阈值。
  15. 根据权利要求10所述的计算机可读存储介质,其特征在于,所述步骤还包括:
    步骤06、判断是否需要远程视频协助识别,若是则进入步骤07,若否则结束;
    步骤07、远程视频辅助识别,若识别通过则提示识别通过,若识别未通过则结束。
PCT/CN2018/083071 2017-10-31 2018-04-13 一种人脸识别智能比对方法、电子装置及计算机可读存储介质 WO2019085403A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711055465.7 2017-10-31
CN201711055465.7A CN107818308A (zh) 2017-10-31 2017-10-31 一种人脸识别智能比对方法、电子装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019085403A1 true WO2019085403A1 (zh) 2019-05-09

Family

ID=61604654

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/083071 WO2019085403A1 (zh) 2017-10-31 2018-04-13 一种人脸识别智能比对方法、电子装置及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN107818308A (zh)
WO (1) WO2019085403A1 (zh)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110490039A (zh) * 2019-05-30 2019-11-22 福建知鱼科技有限公司 一种智能人像比对***
CN110647805A (zh) * 2019-08-09 2020-01-03 平安科技(深圳)有限公司 一种网纹图像识别方法、装置及终端设备
CN111079568A (zh) * 2019-11-28 2020-04-28 乌鲁木齐明华智能电子科技有限公司 一种采用5g网络通讯的动态人脸识别终端
CN111144326A (zh) * 2019-12-28 2020-05-12 神思电子技术股份有限公司 一种用于人机交互的人脸防重识别方法
CN111213920A (zh) * 2020-01-08 2020-06-02 宁波高新区阶梯科技有限公司 一种电子烟及其启动控制方法、装置以及可读存储介质
CN111507165A (zh) * 2020-01-21 2020-08-07 北京明略软件***有限公司 人脸识别方法、装置、电子设备及计算机可读存储介质
CN111523103A (zh) * 2020-05-09 2020-08-11 支付宝(杭州)信息技术有限公司 用户身份识别方法、装置及电子设备
CN111597532A (zh) * 2020-04-10 2020-08-28 云知声智能科技股份有限公司 基于人脸识别实现儿童机器人童锁***的方法和***
CN111814551A (zh) * 2020-06-06 2020-10-23 中信百信银行股份有限公司 基于小程序的人脸识别方法、装置、设备及存储介质
CN112287830A (zh) * 2020-10-29 2021-01-29 泰康保险集团股份有限公司 一种图像的检测方法及装置
CN113379713A (zh) * 2021-06-23 2021-09-10 京东数科海益信息科技有限公司 证件图像的检测方法及其装置
CN113486319A (zh) * 2021-08-02 2021-10-08 安徽文香科技有限公司 一种在线教育平台的用户认证方法及装置
US11380115B2 (en) * 2019-06-04 2022-07-05 Idemia Identity & Security USA LLC Digital identifier for a document

Families Citing this family (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107818308A (zh) * 2017-10-31 2018-03-20 平安科技(深圳)有限公司 一种人脸识别智能比对方法、电子装置及计算机可读存储介质
CN108734235A (zh) * 2018-04-04 2018-11-02 四川骏逸富顿科技有限公司 一种用于电子处方的身份识别方法及***
CN108647651A (zh) * 2018-05-14 2018-10-12 深圳市科发智能技术有限公司 一种提高识别通过率的人脸识别方法、***及装置
CN108846968A (zh) * 2018-05-29 2018-11-20 禾麦科技开发(深圳)有限公司 一种信息处理方法及其设备、存储介质、电子设备
CN108922068A (zh) * 2018-05-29 2018-11-30 禾麦科技开发(深圳)有限公司 一种信息处理方法及其设备、存储介质、电子设备
CN108765778A (zh) * 2018-05-29 2018-11-06 禾麦科技开发(深圳)有限公司 一种信息处理方法及其设备、存储介质、电子设备
CN109145720A (zh) * 2018-07-06 2019-01-04 阿里巴巴集团控股有限公司 一种人脸识别方法和装置
CN109145801B (zh) * 2018-08-13 2021-02-02 浙江宇视科技有限公司 一种人脸识别方法及人脸识别***
CN109598192A (zh) * 2018-10-23 2019-04-09 平安科技(深圳)有限公司 基于图像识别技术审核简历的方法、装置和计算机设备
WO2020113571A1 (zh) * 2018-12-07 2020-06-11 深圳市欢太科技有限公司 人脸识别数据处理方法、装置、移动设备和计算机可读存储介质
CN109871755A (zh) * 2019-01-09 2019-06-11 中国平安人寿保险股份有限公司 一种基于人脸识别的身份验证方法
CN110008821B (zh) * 2019-02-02 2023-07-18 创新先进技术有限公司 一种预测人像底图更新的方法和设备
CN110287791B (zh) * 2019-05-23 2022-02-22 罗普特科技集团股份有限公司 一种用于人脸图片的筛选方法和***
CN110188678B (zh) * 2019-05-29 2021-04-13 Oppo广东移动通信有限公司 静脉识别方法及相关产品
CN110378587A (zh) * 2019-07-08 2019-10-25 上海辰尚信息科技有限公司 智能质检方法、***、介质以及设备
CN112241666A (zh) * 2019-07-18 2021-01-19 佳能株式会社 目标识别方法、装置及存储介质
CN110838102A (zh) * 2019-10-24 2020-02-25 开望(杭州)科技有限公司 一种智能化图像上传方法
CN110751129B (zh) * 2019-10-30 2023-05-30 深圳市丰巢科技有限公司 一种快递业务的身份验证方法、装置、设备和存储介质
CN111696239A (zh) * 2020-06-18 2020-09-22 江苏建筑职业技术学院 一种基于计算机的人工智能识别***
CN111861240A (zh) * 2020-07-27 2020-10-30 深圳前海微众银行股份有限公司 可疑用户识别方法、装置、设备及可读存储介质
CN112183394A (zh) * 2020-09-30 2021-01-05 江苏智库智能科技有限公司 一种人脸识别方法、装置和智能安防管理***
CN112364733B (zh) * 2020-10-30 2022-07-26 重庆电子工程职业学院 智能安防人脸识别***
CN112395580A (zh) * 2020-11-19 2021-02-23 联通智网科技有限公司 一种认证方法、装置、***、存储介质和计算机设备
CN114626036B (zh) * 2020-12-08 2024-05-24 腾讯科技(深圳)有限公司 基于人脸识别的信息处理方法、装置、存储介质及终端
CN113032047A (zh) * 2021-03-29 2021-06-25 京东方科技集团股份有限公司 人脸识别***应用方法、电子设备及存储介质
CN113052961A (zh) * 2021-04-01 2021-06-29 上海红阵信息科技有限公司 一种基于3d人脸模型的云端人证合一方法
CN113052145A (zh) * 2021-04-30 2021-06-29 中国银行股份有限公司 一种人脸识别结果的差异化判断方法和装置
CN113408421B (zh) * 2021-06-21 2023-04-07 湖北央中巨石信息技术有限公司 基于区块链的人脸识别方法及***
CN113449673A (zh) * 2021-07-09 2021-09-28 中国银行股份有限公司 一种证件识别核实方法和装置
CN113705537A (zh) * 2021-09-18 2021-11-26 中国银行股份有限公司 用户身份认证方法及装置
CN114863540B (zh) * 2022-07-05 2022-12-16 杭州魔点科技有限公司 基于人脸属性分析的人脸识别在线辅助方法及装置
CN116959064B (zh) * 2023-06-25 2024-04-26 上海腾桥信息技术有限公司 一种证件验证方法、装置、计算机设备和存储介质
CN117058803B (zh) * 2023-10-13 2024-01-05 浪潮智慧科技创新(山东)有限公司 一种基于深度学习的智能化数据采集方法及采集***

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060158307A1 (en) * 2005-01-13 2006-07-20 Samsung Electronics Co., Ltd. System and method for face recognition
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
CN105447367A (zh) * 2015-11-13 2016-03-30 中国建设银行股份有限公司 自助发卡设备及其身份认证***和身份认证方法
CN105930709A (zh) * 2016-04-21 2016-09-07 深圳泰首智能技术有限公司 人脸识别技术应用于人证一致性检验的方法及装置
CN107818308A (zh) * 2017-10-31 2018-03-20 平安科技(深圳)有限公司 一种人脸识别智能比对方法、电子装置及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060158307A1 (en) * 2005-01-13 2006-07-20 Samsung Electronics Co., Ltd. System and method for face recognition
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
CN105447367A (zh) * 2015-11-13 2016-03-30 中国建设银行股份有限公司 自助发卡设备及其身份认证***和身份认证方法
CN105930709A (zh) * 2016-04-21 2016-09-07 深圳泰首智能技术有限公司 人脸识别技术应用于人证一致性检验的方法及装置
CN107818308A (zh) * 2017-10-31 2018-03-20 平安科技(深圳)有限公司 一种人脸识别智能比对方法、电子装置及计算机可读存储介质

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110490039A (zh) * 2019-05-30 2019-11-22 福建知鱼科技有限公司 一种智能人像比对***
US11380115B2 (en) * 2019-06-04 2022-07-05 Idemia Identity & Security USA LLC Digital identifier for a document
CN110647805A (zh) * 2019-08-09 2020-01-03 平安科技(深圳)有限公司 一种网纹图像识别方法、装置及终端设备
CN110647805B (zh) * 2019-08-09 2023-10-31 平安科技(深圳)有限公司 一种网纹图像识别方法、装置及终端设备
CN111079568A (zh) * 2019-11-28 2020-04-28 乌鲁木齐明华智能电子科技有限公司 一种采用5g网络通讯的动态人脸识别终端
CN111144326A (zh) * 2019-12-28 2020-05-12 神思电子技术股份有限公司 一种用于人机交互的人脸防重识别方法
CN111144326B (zh) * 2019-12-28 2023-10-27 神思电子技术股份有限公司 一种用于人机交互的人脸防重识别方法
CN111213920A (zh) * 2020-01-08 2020-06-02 宁波高新区阶梯科技有限公司 一种电子烟及其启动控制方法、装置以及可读存储介质
CN111507165A (zh) * 2020-01-21 2020-08-07 北京明略软件***有限公司 人脸识别方法、装置、电子设备及计算机可读存储介质
CN111597532A (zh) * 2020-04-10 2020-08-28 云知声智能科技股份有限公司 基于人脸识别实现儿童机器人童锁***的方法和***
CN111597532B (zh) * 2020-04-10 2023-11-17 云知声智能科技股份有限公司 基于人脸识别实现儿童机器人童锁***的方法和***
CN111523103A (zh) * 2020-05-09 2020-08-11 支付宝(杭州)信息技术有限公司 用户身份识别方法、装置及电子设备
CN111814551A (zh) * 2020-06-06 2020-10-23 中信百信银行股份有限公司 基于小程序的人脸识别方法、装置、设备及存储介质
CN112287830A (zh) * 2020-10-29 2021-01-29 泰康保险集团股份有限公司 一种图像的检测方法及装置
CN113379713A (zh) * 2021-06-23 2021-09-10 京东数科海益信息科技有限公司 证件图像的检测方法及其装置
CN113379713B (zh) * 2021-06-23 2024-02-09 京东科技信息技术有限公司 证件图像的检测方法及其装置
CN113486319A (zh) * 2021-08-02 2021-10-08 安徽文香科技有限公司 一种在线教育平台的用户认证方法及装置

Also Published As

Publication number Publication date
CN107818308A (zh) 2018-03-20

Similar Documents

Publication Publication Date Title
WO2019085403A1 (zh) 一种人脸识别智能比对方法、电子装置及计算机可读存储介质
WO2019062080A1 (zh) 身份识别方法、电子装置及计算机可读存储介质
WO2019104930A1 (zh) 一种身份鉴定方法、电子装置及计算机可读存储介质
US10922529B2 (en) Human face authentication method and apparatus, and storage medium
US10997443B2 (en) User identity verification method, apparatus and system
CN109359548B (zh) 多人脸识别监控方法及装置、电子设备及存储介质
CN107220590B (zh) 一种基于活体检测的防作弊网络调研方法、装置及***
WO2019091012A1 (zh) 基于人脸识别的安检方法、应用服务器及计算机可读存储介质
CN104834849B (zh) 基于声纹识别和人脸识别的双因素身份认证方法及***
WO2019120115A1 (zh) 人脸识别的方法、装置及计算机装置
AU2017201463B2 (en) Methods and systems for authenticating users
WO2019134346A1 (zh) 人脸识别方法、应用服务器及计算机可读存储介质
WO2020024398A1 (zh) 生物特征辅助支付方法、装置、计算机设备及存储介质
WO2019047481A1 (zh) 房产信息查询方法、***、终端设备及存储介质
CN105930709A (zh) 人脸识别技术应用于人证一致性检验的方法及装置
US10268911B1 (en) System and method for liveness detection using facial landmarks
CN105518711A (zh) 活体检测方法、活体检测***以及计算机程序产品
CN105989263A (zh) 身份认证方法、开户方法、装置及***
WO2019178753A1 (zh) 支付方法、装置和***
CN111178233A (zh) 基于活体认证的身份认证方法及装置
CN207731302U (zh) 一种身份查验***
CN112949363A (zh) 一种人脸活体识别方法及装置
CN103902959A (zh) 基于人脸识别技术的智能推送***
TWI524277B (zh) Dynamic Image Identity Identification System and Method with Shape Characteristic Matching
US20230135488A1 (en) Systems and methods for user authentication to verify transaction legitimacy

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: 18874713

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 23/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18874713

Country of ref document: EP

Kind code of ref document: A1