WO2019091012A1 - 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 - Google Patents

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 Download PDF

Info

Publication number
WO2019091012A1
WO2019091012A1 PCT/CN2018/076138 CN2018076138W WO2019091012A1 WO 2019091012 A1 WO2019091012 A1 WO 2019091012A1 CN 2018076138 W CN2018076138 W CN 2018076138W WO 2019091012 A1 WO2019091012 A1 WO 2019091012A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
identity information
information card
gate
passenger
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2018/076138
Other languages
English (en)
French (fr)
Inventor
陈林
张国辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019091012A1 publication Critical patent/WO2019091012A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a security detection method based on face recognition, an application server, and a computer readable storage medium.
  • biometrics technology has become a safer and more convenient personal identification technology, which has received more and more attention.
  • Face recognition technology is based on human facial feature information for identity recognition. It is a new biometric recognition technology that has emerged in recent years with the rapid advancement of computer, image processing, pattern recognition and other technologies. More and more applications In the fields of information security, identity authentication, security, and intelligent monitoring.
  • the station now fully implements real-name authentication, and the use of face recognition for identification and identification at the station brings great convenience to the station staff.
  • the high-speed rail station is generally used.
  • the passenger swipes the ID card and the ticket in front of the gate. After the collection is successful, the face is aimed at the camera, the face is collected, and the comparison is made. After the verification is passed, the gate is opened and released.
  • One of the most serious problems in this way is that the speed is very slow, and the passenger stays for a longer period of time, which leads to a large crowd of follow-up personnel. From the verification of the ticket, the ID card to the subsequent identification, the entire operation will last for 3-5 seconds, which will cause a lot of queues during the peak period.
  • the present application proposes a security detection method based on face recognition, an application server, and a computer readable storage medium, which can enable the face recognition process to be completed during the travel of the passenger without occupying the waiting time of the passenger and avoiding Causing congestion and improving user experience.
  • the present application provides a security detection method based on face recognition, which is applied to an application server, and the method includes:
  • the plurality of cameras are controlled to capture the passenger's face avatar multiple times at the same time;
  • the second gate is opened.
  • the present application further provides an application server, where the application server includes a memory and a processor, and the memory stores a face recognition-based security system that can be run on the processor.
  • the security system based on face recognition is implemented by the processor to implement the following steps:
  • the plurality of cameras capture the passenger's face avatar multiple times at the same time;
  • the second gate is opened.
  • the present application further provides a computer readable storage medium storing a security system based on face recognition, and the security system based on face recognition may be at least one
  • the processor executes to cause the at least one processor to perform the steps of the face recognition based security method as described above.
  • the application server, the face recognition based security detection method and the computer readable storage medium proposed by the present application first acquire an image of the identity information card when the identity information card is detected; Opening the first gate of the information card; then, after opening the first gate, capturing a passenger's face; further, walking toward the second gate at the passenger And comparing the positive face avatar with the acquired image of the identity information card; finally, when the face avatar matches the acquired image of the identity information card, the opening is performed.
  • the second gate In this way, it is possible to avoid the defect that the ID card authentication, the ticket authentication and the face recognition authentication are concentrated in one place in the prior art, which causes the defect of the passenger security check, and also enables the face recognition of the passenger to be completed during the travel process. Does not take up passengers' waiting time and improve user experience.
  • FIG. 1 is a schematic diagram of an optional application environment of each embodiment of the present application.
  • FIG. 2 is a schematic diagram of an optional hardware architecture of the application server of FIG. 1;
  • FIG. 3 is a schematic diagram of a program module of a first embodiment of a security detection system based on face recognition according to the present application;
  • FIG. 4 is a schematic diagram of a program module of a second embodiment of a security detection system based on face recognition according to the present application;
  • FIG. 5 is a schematic diagram of a program module of a third embodiment of a security detection system based on face recognition according to the present application;
  • FIG. 6 is a schematic flow chart of a first embodiment of a security detection method based on face recognition according to the present application
  • FIG. 7 is a schematic flowchart of a second embodiment of a security method based on face recognition according to the present application.
  • FIG. 8 is a schematic flowchart diagram of a third embodiment of a security method based on face recognition according to the present application.
  • FIG. 9 is a schematic flow chart of a fourth embodiment of a security method based on face recognition according to the present application.
  • FIG. 1 it is a schematic diagram of an optional application environment of each embodiment of the present application.
  • the present application is applicable to an application environment including, but not limited to, an application server 2, an image capture device 3, an security gate 4, and a network 6.
  • the application server 2 may be a computing device such as a rack server, a blade server, a tower server, or a rack server.
  • the application server 2 may be an independent server or a server cluster composed of multiple servers. .
  • the image capture device 3 includes a plurality of cameras (not shown in Figure 1).
  • the security gate 4 employs a double gate, including a first gate and a second gate (not shown in Figure 1).
  • the network 6 may be an intranet, an Internet, a Global System of Mobile communication (GSM), a Wideband Code Division Multiple Access (WCDMA), a 4G network, Wireless or wired networks such as 5G networks, Bluetooth, Wi-Fi, etc.
  • GSM Global System of Mobile communication
  • WCDMA Wideband Code Division Multiple Access
  • the application server 2 is respectively connected to one or more of the image collection device 3 and the security gate 4 through the network 6 for data transmission and interaction.
  • the application server 2 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus. It is to be noted that FIG. 2 only shows the application server 2 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), and 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 11 may be an internal storage unit of the application server 2, such as a hard disk or memory of the application server 2.
  • the memory 11 may also be an external storage device of the application server 2, such as a plug-in hard disk equipped on the application server 2, a smart memory card (SMC), and a secure digital number. (Secure Digital, SD) card, flash card, etc.
  • the memory 11 can also include both the internal storage unit of the application server 2 and its external storage device.
  • the memory 11 is generally used to store an operating system installed on the application server 2 and various types of application software, such as a program code of the face recognition-based security system 200. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the application server 2, such as performing control and processing related to data interaction or communication with the mobile terminal 1.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as running the face recognition based security system 200 and the like.
  • the network interface 13 may include a wireless network interface or a wired network interface, which is generally used to establish communication between the application server 2 and other electronic devices (eg, the image capture device 3, security gate 4) connection.
  • the present application proposes a security detection system 200 based on face recognition.
  • FIG. 3 it is a program module diagram of the first embodiment of the security detection system 200 based on the face recognition of the present application.
  • the face recognition based security system 200 controls the switch of the double gate of the security gate, and the face recognition based security system 200 uses the image acquisition device 3 to capture the passenger face avatar.
  • the face recognition based security system 200 includes a series of computer program instructions stored on the memory 11, and when the computer program instructions are executed by the processor 12, the embodiments of the present application may be implemented based on Security check operation for face recognition.
  • the face recognition based security system 200 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 3, the face recognition based security system 200 can be divided into an acquisition module 201, an opening module 202, a capture module 203, and a matching module 204. among them:
  • the obtaining module 201 is configured to acquire an image of the identity information card when the identity information card is detected.
  • the opening module 202 is configured to open the first gate when the image of the identity card is successfully acquired.
  • the capturing module 203 is configured to capture an image of a passenger face after the first gate is opened.
  • the application server 2 uses the image capture device 3 to capture a passenger's face avatar.
  • the image capturing device 3 is disposed on the second gate of the gate, and the focal length is aligned with the first gate, and when the passenger passes, the passenger's face is captured.
  • the application server 2 sets a shooting area, and the shooting area is set between the first gate and the second gate, when the application server detects that the passenger reaches the shooting designation.
  • the image capture device 3 begins capturing the face of the passenger.
  • the image capturing device 3 comprises a plurality of cameras, and the cameras are respectively installed on two sides of the second gate and the different heights of the second gate of the gate, capturing the face of the passenger from multiple angles to avoid the problem of the height of the passenger. , or look around, or look down on the phone and not capture the image of the passenger's face.
  • the matching module 203 is configured to compare the face avatar captured by the plurality of cameras to filter out the front face avatar of the passenger.
  • the matching module 203 is further configured to compare the front face avatar with the acquired image of the identity information card during a time when the passenger walks toward the second gate.
  • the opening module 204 is further configured to: when the image of the face is successfully matched with the image of the acquired identity information card, the second gate is opened.
  • the application server 2 issues an alert message to alert the security staff.
  • the alarm information includes, but is not limited to, a passenger's avatar information, and specific location information of the current passenger.
  • the face recognition based security system 200 further includes a calculation module 205, wherein
  • the obtaining module 201 is further configured to acquire facial feature data according to the captured facial avatar;
  • the calculating module 205 is configured to calculate a similarity score according to the comparison between the facial feature data and the image of the identity information card;
  • the similarity score is greater than the preset value
  • the face avatar and the image of the identity information card are successfully matched.
  • the similarity score is less than the preset value, the matching of the face avatar with the image of the identity information card is unsuccessful.
  • the image capturing device 3 includes a plurality of cameras, and the cameras are disposed at different positions, that is, multiple face avatars of the same passenger can be collected by multiple cameras.
  • the application server 2 filters a plurality of captured face avatars, for example, removing face avatars with closed eyes, removing face avatars that are hidden by facial features, removing blurred avatars, etc., and filtering out clear face avatars, Each face avatar is analyzed to obtain facial feature data.
  • the calculation module 205 calculates a similarity score according to the comparison between the facial feature data and the image of the identity information card, and determines whether the matching is successful by the similarity score.
  • the face recognition-based security system 200 further includes a storage module 206 and a retrieval module 207, where:
  • the storage module 206 is further configured to set a memory space, and store an image of the acquired identity information card.
  • the retrieving module 207 is configured to retrieve an image of the identity information card from the memory space for comparison when capturing a positive face avatar of the passenger.
  • a memory space is allocated in the memory of the application server 2 for storing an image of the acquired identity information card.
  • the application server 2 captures the face avatar of the passenger, the image of the acquired identity information card is retrieved from the memory space for matching and comparison.
  • the application server 2 also sets an access interface of the memory space, and retrieves an image of the acquired identity information card through the access interface.
  • the storage module 206 is further configured to: when the image of the face is successfully matched with the image of the acquired identity information card, erase an image of the identity information card from the memory space.
  • the traffic of the security check is high.
  • the storage module 206 is The memory space erases the image of the identity card.
  • the present application also proposes a security detection method based on face recognition.
  • FIG. 6 it is a schematic flowchart of the first embodiment of the security detection method based on face recognition of the present application.
  • the order of execution of the steps in the flowchart shown in FIG. 6 may be changed according to different requirements, and some steps may be omitted.
  • Step S301 when an identity information card is detected, an image of the identity information card is acquired.
  • a single gate is generally used. After the passenger swipes the ID card, the ticket, verify the ID card and the ticket is successful, the person faces the camera and collects the face. The face avatar is compared with the avatar of the ID card. After the verification is passed, the gate is opened and released. However, the verification of the ticket, the ID card and the face recognition are performed before the single gate. The whole operation will last for 3-5 seconds. During the peak period (especially during the holidays), a lot of queues will be caused. It brings great inconvenience to passengers.
  • the security gate 4 adopts a double gate, the double gate includes a first gate and a second gate, and the application server 2 Performing a face recognition based security system 200 to control the switches of the first gate and the second gate.
  • the passenger places the identity information card in the sensing area of the first gate, and when the application server 2 detects the identity information card, the application server 2 acquires an image of the identity information card regarding the passenger.
  • the identity information card may be, but not limited to, a resident ID card, a passport, a Hong Kong and Macao Pass, and the like.
  • Step S302 when the image of the identity information card is successfully acquired, the first gate is opened.
  • the application server 2 when the application server 2 successfully acquires an image of the identity information card when the double door gate is applied to a place such as a customs office, the application server 2 turns on the first gate.
  • the application server 2 also detects the real-name ticket to verify whether the identity information card and the real-name ticket correspond, when the image of the identity information card is successfully obtained and the identity information card is verified to be the same as the real-name ticket.
  • the application server 2 opens the first gate.
  • Step S303 after the first gate is opened, the plurality of cameras capture the passenger's face avatar multiple times at the same time.
  • the application server 2 uses the image capture device 3 to capture a passenger's face avatar.
  • the image capturing device 3 is disposed on the second gate of the gate, and the focal length is aligned with the first gate, and when the passenger passes, the passenger's face is captured.
  • the image capture device 3 includes a plurality of cameras, and the cameras are respectively mounted on two sides of the second gate, and at different heights of the square of the second gate, capturing passengers from multiple angles. Face avatar, to avoid passengers due to height problems, or to look around, or to play with the phone and catch the image of the passenger's face.
  • Step S304 comparing the face avatar captured by the plurality of cameras to filter out the front face avatar of the passenger.
  • the application server 2 acquires and compares the plurality of cameras at the same time and captures the passenger at multiple angles through the matching module 203. Face avatar to screen out the front face of the passenger.
  • Step S304 comparing the positive face avatar with the acquired image of the identity information card during the time when the passenger goes to the second gate.
  • the application server 2 analyzes the face avatar, acquires facial feature data, and compares the facial feature data with the acquired image of the identity information card.
  • Step S305 when the image of the face is successfully matched with the image of the acquired identity information card, the second gate is opened.
  • the image capturing device 3 captures the face avatar of the passenger, and compares the captured avatar of the passenger with the acquired image of the identity information card.
  • the application server 2 performs avatar comparison, the passenger continues to move toward the second gate, and when the image of the face is successfully matched with the image of the acquired identity information card, the application server 2 is
  • the second gate is opened to complete the matching and contrasting of the images during the passenger's walking, thereby saving the waiting time of the passenger and avoiding a large backlog of personnel.
  • the application server 2 issues an alert message to alert the security staff.
  • the alarm information includes, but is not limited to, a passenger's avatar information, and specific location information of the current passenger.
  • the face recognition based security detection method proposed by the present application first acquires an image of the identity information card when the identity information card is detected; and then, when the image of the identity information card is successfully acquired, the office is opened.
  • the first gate is described; then, after the first gate is opened, the passenger's face is captured; further, the captured face of the passenger is compared with the acquired image of the identity card; Finally, when the face avatar matches the image of the acquired identity information card, the second gate is opened.
  • FIG. 7 is a schematic flowchart diagram of a second embodiment of the data conversion method of the present application.
  • the step of capturing a passenger's face avatar after the first gate is opened includes the following steps:
  • step S401 the shooting area is set.
  • Step S402 when the passenger arrives at the shooting area, the passenger's face avatar is captured.
  • the application server 2 sets a shooting area, and the shooting area is set between the first gate and the second gate, when the application server detects that the passenger reaches When the designated area is photographed, the image capture device 3 starts capturing the face of the passenger.
  • the distance between the first gate and the second gate is 30 meters, and the shooting area is set at 10 meters from the first gate and 20 meters from the second gate.
  • the image capturing device 3 starts capturing the passenger's face.
  • the passenger continues to move toward the second gate.
  • the application server 2 completes the comparison process of whether the image of the passenger's face and the acquired identity card match, and when the matching is successful, the first
  • the second gate opens when the passenger arrives.
  • the application only carries out identity information and ticket verification at the first gate, so that the time for the passenger to pass the first gate can be greatly reduced, and only takes about 1 second, and the second gate uses the time of the passenger to perform image matching. Controlling the opening of the second gate, so that the entire face recognition is completed during the travel process, does not occupy the waiting time of the passenger, and avoids causing a large backlog of personnel.
  • the face recognition based security detection method proposed by the present application can set a shooting area, which is located between the first gate and the second gate, when the passenger arrives at the shooting area.
  • the image of the passenger face is captured, so that the application server 2 uses the time forward of the passenger to perform image matching and comparison, and does not occupy the waiting time of the passenger, thereby avoiding causing a large backlog of personnel.
  • FIG. 8 is a schematic flowchart diagram of a third embodiment of a security method based on face recognition according to the present application.
  • the step of comparing the captured person's face avatar with the acquired image of the identity information card includes:
  • Step S501 acquiring facial feature data according to the captured facial avatar
  • Step S502 calculating a similarity score according to comparison between the facial feature data and the image of the identity information card;
  • Step S503 when the similarity score is greater than the preset value, it is determined that the image of the face avatar and the identity information card are successfully matched.
  • the image capturing device 3 includes a plurality of cameras, and the cameras are disposed at different positions, that is, a plurality of face avatars of the same passenger can be collected by the plurality of cameras.
  • the application server 2 filters a plurality of captured face avatars, for example, removing face avatars with closed eyes, removing face avatars that are hidden by facial features, removing blurred avatars, etc., and filtering out clear face avatars, Each face avatar is analyzed to obtain facial feature data. Then, according to the comparison between the facial feature data and the image of the identity information card, the similarity score is calculated, and the similarity score is used to determine whether the matching is successful.
  • the face recognition based security detection method proposed by the present application can also acquire facial feature data according to the face avatar, and calculate the similarity score of the face feature data and the identity information card image.
  • the similarity score is used to determine that the face avatar matches the image of the identity information card, and the accuracy of the judgment is improved.
  • the security method based on face recognition further includes:
  • Step S601 setting a memory space, and storing an image of the acquired identity information card
  • Step S602 when the face avatar of the passenger is captured, the image of the identity information card is retrieved from the memory space for comparison;
  • a memory space is allocated in the memory of the application server 2 for storing an image of the acquired identity information card.
  • the application server 2 captures the face avatar of the passenger, the image of the acquired identity information card is retrieved from the memory space for matching and comparison.
  • the application server 2 also sets an access interface of the memory space, and retrieves an image of the acquired identity information card through the access interface.
  • Step S603 after the image of the face is successfully matched with the image of the acquired identity information card, the image of the identity information card is erased from the memory space.
  • the traffic of the security check is high.
  • the storage module 206 is The memory space erases the image of the identity card.
  • the face recognition-based security checking method proposed by the present application can also set a memory space, store an image of the acquired identity information card, and capture the face of the passenger.
  • the image of the identity information card is retrieved from the memory space for comparison, and after the matching is successful, the image of the identity information card is erased from the memory space to alleviate the operating pressure of the application server.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Collating Specific Patterns (AREA)
  • Devices For Checking Fares Or Tickets At Control Points (AREA)

Abstract

一种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，方法包括：当检测到身份信息卡时，获取身份信息卡的图像(S301)；成功获取身份信息卡的图像时，开启第一闸机门(S302)；开启第一闸机门后，控制多个摄像头同时多次捕捉旅客人脸头像(S303)；对比多个摄像头捕捉到的人脸头像以筛选出旅客的正脸头像(S304)；将捕捉到正脸像与获取到的身份信息卡的图像进行对比(S305)；正脸头像与获取到的身份信息卡的图像匹配成功时，开启第二闸机门(S306)。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可以使得人脸识别过程是在旅客的行进过程中完成，并不占用旅客的等待时间，避免造成拥堵。

Description

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
本申请要求于2017年11月8日提交中国专利局、申请号为201711087790.1、发明名称为“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”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种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。
背景技术
随着信息化的不断推进，生物特征识别技术成为一种更加安全、方便的个人身份鉴别技术，越来越受到关注。人脸识别技术基于人的脸部特征信息进行身份识别，是近年来随着计算机、图像处理、模式识别等技术的迅速进步而出现的一种崭新的生物特征识别技术，越来越多的应用在信息安全、身份认证识别、安保、智能监控等领域。
特别是如今车站全面实行实名认证，在车站利用人脸识别进行身份认证识别给车站工作人员带来很大的便利，但是目前在人脸识别闸机场景中，例如高铁站，普遍采用的是单道闸门，旅客在闸机前刷身份证，车票，采集成功后将人脸对准摄像头，采集人脸，进行比对，验证通过后，闸门打开放行。这种方式存在一个最严重的问题，就是速度很慢，旅客整体停留的时间较长，会导致后续人员大量拥挤。从验证车票，身份证开始到后续识别，整个操作大概会持续3-5秒，在高峰期的时候会造成大量排队。
发明内容
有鉴于此，本申请提出一种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，能够使得人脸识别过程是在旅客的行进过程中完成，并不占用旅客的等待时间，避免造成拥堵，提高用户体验。
首先，为实现上述目的，本申请提出一种基于人脸识别的安检方法，该方法应用于应用服务器，所述方法包括：
当检测到身份信息卡时，获取身份信息卡的图像；
当成功获取身份信息卡的图像时，开启所述第一闸机门；
当开启所述第一闸机门后，控制多个摄像头同时多次捕捉旅客人脸头像；
对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像；
在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比；
当所述正脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
此外，为实现上述目的，本申请还提供一种应用服务器，所述应用服务器包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的基于人脸识别的安检系统，所述基于人脸识别的安检系统被所述处理器执行时实现如下步骤：
当检测到身份信息卡时，获取身份信息卡的图像；
当成功获取身份信息卡的图像时，开启所述第一闸机门；
当开启所述第一闸机门后，所述多个摄像头同时多次捕捉旅客人脸头像；
对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像；
在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比；
当所述正脸头像头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
进一步地，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存储有基于人脸识别的安检系统，所述基于人脸识 别的安检系统可被至少一个处理器执行，以使所述至少一个处理器执行如上述的基于人脸识别的安检方法的步骤。
相较于现有技术，本申请所提出的应用服务器、基于人脸识别的安检方法及计算机可读存储介质，首先当检测到身份信息卡时，获取身份信息卡的图像；然后，当成功获取身份信息卡的图像时，开启所述第一闸机门；接着，当开启所述第一闸机门后，捕捉旅客人脸头像；进一步地，在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比；最后，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。这样，既可以避免现有技术中一身份证认证、车票认证、人脸识别认证集中在一个地方认证，造成旅客安检拥堵的缺陷，也可以使得旅客的人脸脸识别都是在行进过程中完成，并不占用旅客的等待时间，提高用户体验。
附图说明
图1是本申请各个实施例一可选的应用环境示意图；
图2是图1中应用服务器一可选的硬件架构的示意图；
图3是本申请基于人脸识别的安检系统第一实施例的程序模块示意图；
图4是本申请基于人脸识别的安检系统第二实施例的程序模块示意图；
图5是本申请基于人脸识别的安检系统第三实施例的程序模块示意图；
图6为本申请基于人脸识别的安检方法第一实施例的流程示意图；
图7为本申请基于人脸识别的安检方法第二实施例的流程示意图；
图8为本申请基于人脸识别的安检方法第三实施例的流程示意图；
图9为本申请基于人脸识别的安检方法第四实施例的流程示意图；
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。基于本申请中的实施例，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，都属于本申请保护的范围。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的，而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
参阅图1所示，是本申请各个实施例一可选的应用环境示意图。
在本实施例中，本申请可应用于包括，但不仅限于，应用服务器2、图像采集装置3、安检闸机4、网络6的应用环境中。其中，所述应用服务器2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等计算设备，该应用服务器2可以是独立的服务器，也可以是多个服务器所组成的服务器集群。所述图像采集装置3包括多个摄像头(图1中未示出)。所述安检闸机4采用双门闸机，包括第一闸机门和第二闸机门(图1中未示出)。所述网络6可以是企业内部网(Intranet)、互联网(Internet)、全球移动通讯系统(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。
其中，所述应用服务器2中通过所述网络6分别与一个或多个所述图像采集装置3、安检闸机4通信连接，以进行数据传输和交互。
参阅图2所示，是图1中应用服务器2一可选的硬件架构的示意图。本实施例中，所述应用服务器2可包括，但不仅限于，可通过系统总线相互通信连接存储器11、处理器12、网络接口13。需要指出的是，图2仅示出了具有组件11-13的应用服务器2，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
其中，所述存储器11至少包括一种类型的可读存储介质，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11可以是所述应用服务器2的内部存储单元，例如该应用服务器2的硬盘或内存。在另一些实施例中，所述存储器11也可以是所述应用服务器2的外部存储设备，例如该应用服务器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11还可以既包括所述应用服务器2的内部存储单元也包括其外部存储设备。本实施例中，所述存储器11通常用于存储安装于所述应用服务器2的操作系统和各类应用软件，例如基于人脸识别的安检系统200的程序代码等。此外，所述存储器11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12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12通常用于控制所述应用服务器2的总体操作，例如执行与所述移动终端1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12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行所述的基于人脸识别的安检系统200等。
所述网络接口13可包括无线网络接口或有线网络接口，该网络接口13通常用于在所述应用服务器2与其他电子设备(例如所述图像采集装置3、安检 闸机4)之间建立通信连接。
至此，己经详细介绍了本申请各个实施例的应用环境和相关设备的硬件结构和功能。下面，将基于上述应用环境和相关设备，提出本申请的各个实施例。
首先，本申请提出一种基于人脸识别的安检系统200。
参阅图3所示，是本申请基于人脸识别的安检系统200第一实施例的程序模块图。本实施例中，所述基于人脸识别的安检系统200控制安检闸口的双门闸机的开关，所述基于人脸识别的安检系统200采用图像采集装置3进行捕捉旅客人脸头像。
本实施例中，所述基于人脸识别的安检系统200包括一系列的存储于存储器11上的计算机程序指令，当该计算机程序指令被处理器12执行时，可以实现本申请各实施例的基于人脸识别的安检操作。在一些实施例中，基于该计算机程序指令各部分所实现的特定的操作，基于人脸识别的安检系统200可以被划分为一个或多个模块。例如，在图3中，所述基于人脸识别的安检系统200可以被分割成获取模块201、开启模块202、捕捉模块203、以及匹配模块204。其中：
所述获取模块201，用于在当检测到身份信息卡时，获取身份信息卡的图像。
所述开启模块202，用于当成功获取身份信息卡的图像时，开启所述第一闸机门。
所述捕捉模块203，用于当开启所述第一闸机门后，图像采集装置3捕捉旅客人脸头像。
具体地，当所述第一闸机门打开，旅客从第一闸机门进入，走向第二闸机门。在本实施例中，所述应用服务器2采用图像采集装置3捕捉旅客人脸头像。所述图像采集装置3设置于第二闸机门上，焦距对准第一道闸门，当旅客通过时，捕捉旅客人脸头像。
在本实施例中，所述应用服务器2设定一拍摄区域，所述拍摄区域设置与第一闸机门与第二闸机门之间，当所述应用服务器侦2测到旅客达到拍摄指定区域时，所述图像采集装置3开始捕捉旅客的人脸头像。
所述图像采集装置3包含多个摄像头，摄像头分别安装在第二闸机门的两侧，及第二闸机门正方的不同高度上，从多角度捕捉旅客人脸头像，避免旅客因身高问题，或者左右看望，或者低头玩手机而捕捉不到旅客正脸的图像。
所述匹配模块203，用于对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像。
所述匹配模块203，还用于在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比。
所述开启模块204，还用于当所述人脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
在本申请的其他实施例中，当所述人脸头像与所述获取到的身份信息卡的图像不匹配成功时，所述应用服务器2发出警报信息，以提醒安检工作人员。其中所述警报信息包括但不限于，旅客的头像信息，当前旅客的具体位置信息。
进一步地，基于本申请基于人脸识别的安检系统200的上述第一实施例，提出本申请的第二实施例(如图4所示)。本实施例中，所述基于人脸识别的安检系统200还包括计算模块205，其中，
所述获取模块201，还用于根据所述捕捉到的人脸头像获取人脸特征数据；
所述计算模块205，用于根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分；
当相似度得分大于预设值时，所述人脸头像与所述身份信息卡的图像匹配成功。当相似度得分小于预设值时，所述人脸头像与所述身份信息卡的图 像匹配不成功。
具体地，从上文可知，在第一实施例中，所述图像采集装置3包含多个摄像头，且摄像头设置在不同的位置，即通过多个摄像头可以采集同一个旅客的多个人脸头像。所述应用服务器2筛选多张捕捉到的人脸头像，例如去除闭眼睛的人脸头像，去除五官被遮住的人脸头像，去除模糊的头像等，筛选出拍摄清晰的正脸头像，对每一张人脸头像进行分析获取人脸特征数据。进而通过计算模块205根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分，通过相似度得分判断是否匹配成功。
进一步地，基于本申请基于人脸识别的安检系统200的上述第一实施例，提出本申请的第三实施例(如图5所示)。本实施例中，所述的基于人脸识别的安检系统200还包括存储模块206及调取模块207，其中：
所述存储模块206，还用于设定一个内存空间，存储所述获取到的身份信息卡的图像。
所述调取模块207，用于当捕捉到所述旅客的正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比。
具体地，在所述应用服务器2的内存划分一个存储空间，用于存储所述获取到的身份信息卡的图像。当所述应用服务器2捕捉到所述旅客的人脸头像时，则从所述内存空间调取所述获取到的身份信息卡的图像，进行匹配对比。在本实施例中，所述应用服务器2还设定所述内存空间的访问接口，通过访问接口调取所述获取到的身份信息卡的图像。
所述存储模块206，还用于当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
通常，每天过安检的人流量大，为了保证所述应用服务器2的运行速度，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，所述存储模块206从所述内存空间擦除所述身份信息卡的图像。
此外，本申请还提出一种基于人脸识别的安检方法。
参阅图6所示，是本申请基于人脸识别的安检方法第一实施例的流程示意图。在本实施例中，根据不同的需求，图6所示的流程图中的步骤的执行顺序可以改变，某些步骤可以省略。
步骤S301，当检测到身份信息卡时，获取身份信息卡的图像。
通常地，在人脸识别闸机场景中，例如车站，普遍采用的是单道闸门，旅客在闸机前刷身份证，车票，验证身份证和车票成功后，将人脸对准摄像头，采集人脸头像，进行身份证的头像进行比对，验证通过后，闸门打开放行。然而，验证车票，身份证以及进行人脸识别的动作都是在单闸闸机前执行，整个操作过程大概会持续3-5秒，在高峰期(特别是节假日的时候)会造成大量排队，给旅客带来很大的不便。
因此，为了避免在安检过程中造成拥堵，在本实施方式中，安检闸机4采用双门闸机，所述双门闸机包括第一闸机门和第二闸机门，所述应用服务器2执行基于人脸识别的安检系统200以控制第一闸机门和第二闸机门的开关。
具体地，旅客将身份信息卡放置在第一闸机门的感应区域，当所述应用服务器2检测到身份信息卡时，所述应用服务器2获取身份信息卡的关于旅客的图像。在本实施例中，身份信息卡可以为但不限于居民身份证、护照、港澳通行证等等。
步骤S302，当成功获取身份信息卡的图像时，开启所述第一闸机门。
具体地，当所述双门闸机应用在海关等地方时，所述应用服务器2成功获取身份信息卡的图像时，所述应用服务器2开启所述第一闸机。当所述双门闸机应用在车站时，所述应用服务器2还检测实名车票，以验证身份信息卡和实名车票是否对应，当成功获取身份信息卡的图像且验证身份信息卡和实名车票一致时，所述应用服务器2开启所述第一闸机门。
步骤S303，当开启所述第一闸机门后，多个摄像头同时多次捕捉旅客人脸头像。
具体地，当所述第一闸机门打开，旅客从第一闸机门进入，走向第二闸机门。在本实施例中，所述应用服务器2采用图像采集装置3捕捉旅客人脸头像。所述图像采集装置3设置于第二闸机门上，焦距对准第一道闸门，当旅客通过时，捕捉旅客人脸头像。
在本申请的其他实施例中，所述图像采集装置3包含多个摄像头，摄像头分别安装在第二闸机门的两侧，及第二闸机门正方的不同高度上，从多角度捕捉旅客人脸头像，避免旅客因身高问题，或者左右看望，或者低头玩手机而捕捉不到旅客正脸的图像。
步骤S304，对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像。
具体地，旅客的侧脸或者低头垂目的照片都不利于判断是否人证一致，因此，所述应用服务器2通过所述匹配模块203获取并对比所述多个摄像头同时多角度地捕捉旅客的人脸头像，以筛选出所述旅客的正脸头像。
步骤S304，在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比。
具体地，所述应用服务器2分析所述人脸头像，获取人脸特征数据，将人脸特征数据与获取到的身份信息卡的图像进行对比。
步骤S305，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
具体地，旅客到达所述拍摄区域时，所述图像采集装置3捕捉旅客的人脸头像，并将捕捉到旅客人脸头像与获取到的所述身份信息卡的图像进行对比。在所述应用服务器2进行头像对比的时候，旅客继续向第二闸机门前行，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功时，所述应用服务器2在旅客到达所述第二闸机门时，开启所述第二闸机门，实现在旅客行走中完成图像的匹配对比，节省旅客的等待时间，避免造成人员大量积压。
在本申请的其他实施例中，当所述人脸头像与所述获取到的身份信息卡 的图像不匹配成功时，所述应用服务器2发出警报信息，以提醒安检工作人员。其中所述警报信息包括但不限于，旅客的头像信息，当前旅客的具体位置信息。
通过上述步骤S301-305，本申请所提出的基于人脸识别的安检方法，首先当检测到身份信息卡时，获取身份信息卡的图像；然后，当成功获取身份信息卡的图像时，开启所述第一闸机门；接着，当开启所述第一闸机门后，捕捉旅客人脸头像；进一步地，将捕捉到旅客人脸头像与获取到的所述身份信息卡的图像进行对比；最后，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。这样，既可以避免现有技术中一身份证认证、车票认证、人脸识别认证集中在一个地方认证，造成旅客安检拥堵的缺陷，也可以使得旅客的人脸脸识别都是在行进过程中完成，并不占用旅客的等待时间，提高用户体验。
进一步地，基于本申请基于人脸识别的安检方法的上述第一实施例，提出本申请基于人脸识别的安检方法的第二实施例。
如图7所示，是本申请数据转化方法第二实施例的流程示意图。本实施例中，所述当开启所述第一闸机门后，捕捉旅客人脸头像的步骤，具体包括如下步骤：
步骤S401，设定拍摄区域。
步骤S402，当旅客到达拍摄区域时，捕捉旅客人脸头像。
从上文可知，在第一实施例中，当所述第一闸机门打开，旅客从第一闸机门进入，走向第二闸机门。因此，在本实施例中，所述应用服务器2设定一拍摄区域，所述拍摄区域设置与第一闸机门与第二闸机门之间，当所述应用服务器侦2测到旅客达到拍摄指定区域时，所述图像采集装置3开始捕捉旅客的人脸头像。
为了更好的解释本申请，以下举例说明，可以理解的是，并不作为本申请的限定。
在本申请一实施例中，第一闸机门与第二闸机门的距离为30米，拍摄区域设置在距离第一闸机门10米，距离第二闸机门20米的地方，当旅客通过第一闸机门到达拍摄区域时，图像采集装置3开始捕捉旅客人脸头像。旅客继续向第二闸机门前行，在到达第二闸机门前，应用服务器2完成旅客人脸头像与获取到的身份信息卡的图像的是否匹配的对比过程，当匹配成功时，第二闸机门在旅客到达时打开。本申请通过在第一闸机门只进行身份信息和车票验证，这样旅客通过第一道闸门的时间能大大减少，只需要1秒左右，第二闸机门利用旅客行走的时间进行图像匹配，控制第二闸机门打开，使得整个人脸识别都是在行进过程中完成，并不占用旅客的等待时间，避免造成造成人员大量积压。
通过上述步骤S401-S402，本申请所提出的基于人脸识别的安检方法，可以设定拍摄区域，该拍摄区域位于第一闸机门与第二闸机门之间，当旅客到达拍摄区域时，捕捉旅客人脸头像，使得应用服务器2利用旅客前行的时间进行图像匹配对比，不占用旅客的等待时间，避免造成造成人员大量积压。
进一步地，基于本申请基于人脸识别的安检方法的上述第一和第二实施例，提出本申请基于人脸识别的安检方法的第三实施例。
如图8所示，是本申请基于人脸识别的安检方法第三实施例的流程示意图。本实施例中，所述将捕捉到旅客人脸头像与获取到的所述身份信息卡的图像进行对比的步骤，具体包括：
步骤S501，根据所述捕捉到的人脸头像获取人脸特征数据；
步骤S502，根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分；
步骤S503，当相似度得分大于预设值时，判断所述人脸头像与所述身份信息卡的图像匹配成功。
具体地，从上文可知，在第一实施例中，所述图像采集装置3包含多个摄像头，且摄像头设置在不同的位置，即通过多个摄像头可以采集同一个旅 客的多个人脸头像。所述应用服务器2筛选多张捕捉到的人脸头像，例如去除闭眼睛的人脸头像，去除五官被遮住的人脸头像，去除模糊的头像等，筛选出拍摄清晰的正脸头像，对每一张人脸头像进行分析获取人脸特征数据。进而根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分，通过相似度得分判断是否匹配成功。
通过上述步骤S501-S503，本申请所提出的基于人脸识别的安检方法，还能够根据人脸头像获取人脸特征数据，并计算所述人脸特征数据与身份信息卡的图像的相似度得分，通过相似度得分判断所述人脸头像与所述身份信息卡的图像匹配成功，提高判断的准确性。
进一步地，基于本申请基于人脸识别的安检方法的上述第一实施例，提出本申请基于人脸识别的安检方法的第四实施例。
如图9所示，是本申请基于人脸识别的安检方法第四实施例的流程示意图。本实施例中，所述基于人脸识别的安检方法还包括：
步骤S601，设定一个内存空间，存储所述获取到的身份信息卡的图像；
步骤S602，当捕捉到所述旅客的人脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
具体地，在所述应用服务器2的内存划分一个存储空间，用于存储所述获取到的身份信息卡的图像。当所述应用服务器2捕捉到所述旅客的人脸头像时，则从所述内存空间调取所述获取到的身份信息卡的图像，进行匹配对比。在本实施例中，所述应用服务器2还设定所述内存空间的访问接口，通过访问接口调取所述获取到的身份信息卡的图像。
步骤S603，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
通常，每天过安检的人流量大，为了保证所述应用服务器2的运行速度，当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，所述存储模块206从所述内存空间擦除所述身份信息卡的图像。
通过上述步骤S601-S603，本申请所提出的基于人脸识别的安检方法，还能够设定一个内存空间，存储所述获取到的身份信息卡的图像，并在捕捉到所述旅客的人脸头像时，从内存空间调取所述身份信息卡的图像进行对比，并且在匹配成功后，从所述内存空间擦除所述身份信息卡的图像，以减轻应用服务器的运行压力。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
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。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
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 (20)

  1. 一种基于人脸识别的安检方法，应用于应用服务器，其特征在于，所述方法包括：
    当检测到身份信息卡时，获取身份信息卡的图像；
    当成功获取身份信息卡的图像时，开启所述第一闸机门；
    当开启所述第一闸机门后，控制多个摄像头同时多次捕捉旅客人脸头像；
    对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像；
    在所述旅客走向所述第二闸机门的时间内，将所述正脸头像捕捉到旅客人脸头像与获取到的所述身份信息卡的图像进行对比；
    当所述正脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
  2. 如权利要求1所述的基于人脸识别的安检方法，其特征在于，所述当开启所述第一闸机门后，捕捉旅客人脸头像的步骤，具体包括如下步骤：
    设定拍摄区域，其中，所述拍摄区域设置于第一闸机门与第二闸机门之间；
    当旅客到达拍摄区域时，捕捉旅客人脸头像；其中，
    采用图像采集装置进行捕捉旅客人脸头像，所述图像采集装置包含多个摄像头。
  3. 如权利要求1所述的基于人脸识别的安检方法，其特征在于，所述多个摄像头安装在所述第二闸机门的两侧及所述第二闸机门正方的不同高度。
  4. 如权利要求1所述的基于人脸识别的安检方法，其特征在于，所述在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比的步骤，具体包括：
    根据所述捕捉到的人脸头像获取人脸特征数据；
    根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分；
    当相似度得分大于预设值时，所述人脸头像与所述身份信息卡的图像匹配成功。
  5. 如权利要求1所述的基于人脸识别的安检方法，其特征在于，所述方法还包括：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
  6. 如权利要求2所述的基于人脸识别的安检方法，其特征在于，所述方法还包括：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
  7. 如权利要求3所述的基于人脸识别的安检方法，其特征在于，所述方法还包括：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
  8. 如权利要求4所述的基于人脸识别的安检方法，其特征在于，所述方法还包括：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
  9. 一种应用服务器，其特征在于，所述应用服务器包括存储器、处理器，所述存储器上存储有可在所述处理器上运行的基于人脸识别的安检系统，所述基于人脸识别的安检系统控制安检闸口的双门闸机的开关，所述基于人脸识别的安检系统被所述处理器执行时实现如下步骤：
    当检测到身份信息卡时，获取身份信息卡的图像；
    当成功获取身份信息卡的图像时，开启所述第一闸机门；
    当开启所述第一闸机门后，控制多个摄像头同时多次捕捉旅客人脸头像；
    对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像；
    在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比；
    当所述正脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
  10. 如权利要求9所述的应用服务器，其特征在于，所述当开启所述第一闸机门后，捕捉旅客人脸头像的步骤，具体包括如下步骤：
    设定拍摄区域，其中，所述拍摄区域设置于第一闸机门与第二闸机门之间；
    当旅客到达拍摄区域时，捕捉旅客人脸头像，其中，采用图像采集装置进行捕捉旅客人脸头像，所述图像采集装置包含多个摄像头。
  11. 如权利要求9所述的应用服务器，其特征在于，所述多个摄像头安装在所述第二闸机门的两侧及所述第二闸机门正方的不同高度。
  12. 如权利要求10所述的应用服务器，其特征在于，所述多个摄像头安装在所述第二闸机门的两侧及所述第二闸机门正方的不同高度。
  13. 如权利要求9所述的应用服务器，其特征在于，所述在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比的步骤，具体包括：
    根据所述捕捉到的人脸头像获取人脸特征数据；
    根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分；
    当相似度得分大于预设值时，所述人脸头像与所述身份信息卡的图像匹配成功。
  14. 如权利要求9所述的应用服务器，其特征在于，所述处理器还用于执行所述基于人脸识别的安检系统，以实现以下步骤：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述旅客的正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
  15. 一种计算机可读存储介质，所述计算机可读存储介质存储有基于人脸识别的安检系统，所述基于人脸识别的安检系统可被至少一个处理器执行，以使所述至少一个处理器执行时实现如下步骤：
    当检测到身份信息卡时，获取身份信息卡的图像；
    当成功获取身份信息卡的图像时，开启所述第一闸机门；
    当开启所述第一闸机门后，控制多个摄像头同时多次捕捉旅客人脸头像；
    对比所述多个摄像头捕捉到的人脸头像以筛选出所述旅客的正脸头像；
    在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比；
    当所述正脸头像与所述获取到的身份信息卡的图像匹配成功时，开启所述第二闸机门。
  16. 如权利要求15所述的计算机可读存储介质，其特征在于，所述当开启所述第一闸机门后，捕捉旅客人脸头像的步骤，具体包括如下步骤：
    设定拍摄区域，其中，所述拍摄区域设置于第一闸机门与第二闸机门之间；
    当旅客到达拍摄区域时，捕捉旅客人脸头像，其中，采用图像采集装置进行捕捉旅客人脸头像，所述图像采集装置包含多个摄像头。
  17. 如权利要求15所述的计算机可读存储介质，其特征在于，所述多个摄像头安装在所述第二闸机门的两侧及所述第二闸机门正方的不同高度。
  18. 如权利要求16所述的计算机可读存储介质，其特征在于，所述多个摄像头安装在所述第二闸机门的两侧及所述第二闸机门正方的不同高度。
  19. 如权利要求15所述的计算机可读存储介质，其特征在于，所述在所述旅客走向所述第二闸机门的时间内，将所述正脸头像与获取到的所述身份信息卡的图像进行对比的步骤，具体包括：
    根据所述捕捉到的人脸头像获取人脸特征数据；
    根据人脸特征数据与所述身份信息卡的图像进行的对比，计算相似度得分；
    当相似度得分大于预设值时，所述人脸头像与所述身份信息卡的图像匹配成功。
  20. 如权利要求15所述的计算机可读存储介质，其特征在于，所述处理器还用于执行所述基于人脸识别的安检系统，以实现以下步骤：
    设定一个内存空间，存储所述获取到的身份信息卡的图像；
    当捕捉到所述旅客的正脸头像时，从所述内存空间调取所述身份信息卡的图像进行对比；
    当所述人脸头像与所述获取到的身份信息卡的图像匹配成功后，从所述内存空间擦除所述身份信息卡的图像。
PCT/CN2018/076138 2017-11-08 2018-02-10 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 Ceased WO2019091012A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711087790.1A CN107945321B (zh) 2017-11-08 2017-11-08 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
CN201711087790.1 2017-11-08

Publications (1)

Publication Number Publication Date
WO2019091012A1 true WO2019091012A1 (zh) 2019-05-16

Family

ID=61933530

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/076138 Ceased WO2019091012A1 (zh) 2017-11-08 2018-02-10 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

Country Status (2)

Country Link
CN (1) CN107945321B (zh)
WO (1) WO2019091012A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111753710A (zh) * 2020-06-18 2020-10-09 北京同城必应科技有限公司 一种应用于物流配送的细分类神经网络人脸识别方法
CN117894098A (zh) * 2023-12-28 2024-04-16 全民认证科技（杭州）有限公司 一种人脸特征分割处理的人像锁
CN118397742A (zh) * 2024-04-08 2024-07-26 普天轨道交通技术（上海）有限公司 闸机设备控制方法、装置、计算机设备及介质

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109255303A (zh) * 2018-08-16 2019-01-22 南京西三艾电子系统工程有限公司 一种动态人流的人脸识别系统及方法
CN108846939B (zh) * 2018-09-10 2024-10-15 苏州奥腾电子科技有限公司 无人智能化安检通道系统及应用方法
CN109284711B (zh) * 2018-09-19 2021-09-21 重庆第二师范学院 图书馆借书证人证一致性检验的方法
CN110930569B (zh) * 2018-09-20 2022-04-26 杭州海康威视数字技术股份有限公司 一种安检控制方法和系统
CN109461233A (zh) * 2018-10-24 2019-03-12 平安科技（深圳）有限公司 访客管理方法、系统、计算机设备及存储介质
CN109102615A (zh) * 2018-11-09 2018-12-28 昆明船舶设备集团有限公司 一种带人脸信息采集的航站楼旅客分流引导系统
CN110111473A (zh) * 2019-05-28 2019-08-09 公安部第一研究所 一种人员身份信息无感快速核验通道
CN110689654B (zh) * 2019-09-17 2021-04-30 厦门朗畅信息技术有限公司 一种公寓安防系统
CN110751767A (zh) * 2019-10-31 2020-02-04 中国联合网络通信集团有限公司 一种图像处理方法和装置
CN111161430A (zh) * 2019-12-25 2020-05-15 杭州中威电子股份有限公司 一种实名制自助售票检票一体化装置及方法
CN113126506A (zh) * 2019-12-30 2021-07-16 佛山市云米电器科技有限公司 家电设备控制方法、控制设备及计算机可读存储介质
CN111079711A (zh) * 2019-12-31 2020-04-28 厦门瑞为信息技术有限公司 安检口智能人脸识别设备
CN111209868B (zh) * 2020-01-08 2023-05-09 中国铁道科学研究院集团有限公司电子计算技术研究所 一种客运站旅客与行李信息关联方法及装置
CN111882729A (zh) * 2020-06-30 2020-11-03 同方威视技术股份有限公司 闸机系统以及闸机系统的控制方法
CN111882728B (zh) * 2020-06-30 2022-06-21 同方威视技术股份有限公司 闸机系统以及闸机系统的控制方法
CN112597886A (zh) * 2020-12-22 2021-04-02 成都商汤科技有限公司 乘车逃票检测方法及装置、电子设备和存储介质
CN112560768A (zh) * 2020-12-25 2021-03-26 深圳市商汤科技有限公司 闸机通道控制方法、装置、计算机设备及存储介质
CN114187689A (zh) * 2021-11-17 2022-03-15 广东兆邦智能科技股份有限公司 一种基于ai智能人脸识别的出入境通道闸
CN114268791A (zh) * 2021-12-24 2022-04-01 弘成科技发展有限公司 一种基于移动端人脸识别图片压缩并进行方向旋转的方法
CN114926891A (zh) * 2022-06-01 2022-08-19 同方威视科技江苏有限公司 瞳孔检测方法、装置、存储介质及电子设备
CN115273300A (zh) * 2022-07-21 2022-11-01 平安信托有限责任公司 闸门控制方法、装置、设备及介质
CN115394001B (zh) * 2022-07-29 2024-04-26 北京旷视科技有限公司 身份认证系统、方法、电子设备和计算机可读介质
CN116820160B (zh) * 2023-08-29 2023-11-21 绵阳光耀新材料有限责任公司 基于玻璃微珠状态监测的球化机参数调控方法及系统
CN117912148B (zh) * 2024-03-19 2024-07-02 盛视科技股份有限公司 无感通行检测识别方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104715271A (zh) * 2015-03-23 2015-06-17 北京中盾安全技术开发公司 人证核验机
CN104751543A (zh) * 2013-12-30 2015-07-01 天津市百分百信息技术有限公司 人脸识别门禁
CN106056729A (zh) * 2016-08-03 2016-10-26 北海和思科技有限公司 一种基于人脸识别技术的门禁系统
CN106845368A (zh) * 2016-12-30 2017-06-13 中国民航信息网络股份有限公司 基于人脸识别的机场登机安检再确认系统和方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102147940A (zh) * 2010-02-09 2011-08-10 深圳市慧锐通电器制造有限公司 一种基于居住证、身份证门禁管理的平安社区技控系统
CN201820279U (zh) * 2010-06-08 2011-05-04 深圳市慧锐通电器制造有限公司 一种基于人像特征实现出入管理的门禁管理系统
CN104299305A (zh) * 2014-10-16 2015-01-21 易程(苏州)电子科技股份有限公司 具备人脸识别功能的闸机
CN104853277A (zh) * 2015-04-30 2015-08-19 江西至乐电子科技有限公司 一种具有行车记录功能的自行车音响
CN204680085U (zh) * 2015-06-13 2015-09-30 广东卫城锦峰数码科技有限公司 基于人脸识别的快速身份认证门禁系统
CN105869253A (zh) * 2016-05-27 2016-08-17 成都千帆科技开发有限公司 基于人脸识别的人-证-票综合验证人行闸机
CN206133752U (zh) * 2016-10-28 2017-04-26 合肥虹视信息工程有限公司 一种智能门锁安全管理系统
CN106600750B (zh) * 2016-11-21 2019-05-10 建荣半导体（深圳）有限公司 一种循环录像的方法、系统及行车记录仪
CN206271146U (zh) * 2016-12-19 2017-06-20 成都理工大学 一种基于计算机的智能监控系统
CN106780844A (zh) * 2017-02-23 2017-05-31 珠海格力电器股份有限公司 用于实现行车记录的移动终端及方法
CN107277775A (zh) * 2017-07-21 2017-10-20 山西大同大学 基于光电传感器的体育场安保系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104751543A (zh) * 2013-12-30 2015-07-01 天津市百分百信息技术有限公司 人脸识别门禁
CN104715271A (zh) * 2015-03-23 2015-06-17 北京中盾安全技术开发公司 人证核验机
CN106056729A (zh) * 2016-08-03 2016-10-26 北海和思科技有限公司 一种基于人脸识别技术的门禁系统
CN106845368A (zh) * 2016-12-30 2017-06-13 中国民航信息网络股份有限公司 基于人脸识别的机场登机安检再确认系统和方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111753710A (zh) * 2020-06-18 2020-10-09 北京同城必应科技有限公司 一种应用于物流配送的细分类神经网络人脸识别方法
CN117894098A (zh) * 2023-12-28 2024-04-16 全民认证科技（杭州）有限公司 一种人脸特征分割处理的人像锁
CN118397742A (zh) * 2024-04-08 2024-07-26 普天轨道交通技术（上海）有限公司 闸机设备控制方法、装置、计算机设备及介质

Also Published As

Publication number Publication date
CN107945321B (zh) 2021-02-09
CN107945321A (zh) 2018-04-20

Similar Documents

Publication Publication Date Title
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
US11256902B2 (en) People-credentials comparison authentication method, system and camera
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
WO2019134346A1 (zh) 人脸识别方法、应用服务器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
WO2019127273A1 (zh) 一种多人脸检测方法、装置、服务器、系统及存储介质
JP2015529365A5 (zh)
CN111553231B (zh) 基于信息融合的人脸抓拍与去重系统、方法、终端及介质
JP7251874B2 (ja) 顔認証装置、顔認証方法、プログラム、および記録媒体
CN108108711B (zh) 人脸布控方法、电子设备及存储介质
CN103856614A (zh) 一种避免移动终端误休眠方法及装置
CN110782228A (zh) 一种工作时长获得方法、装置、电子设备及存储介质
CN105868693A (zh) 身份认证方法及系统
CN112116745A (zh) 一种闸机、闸机控制方法、系统、电子设备及存储介质
CN109492509A (zh) 身份识别方法、装置、计算机可读介质及系统
WO2023279783A1 (zh) 人脸识别方法、设备及存储介质
CN105427480B (zh) 一种基于图像分析的柜员机
CN105825102A (zh) 一种基于眼纹识别的终端解锁方法和装置
CN113158730A (zh) 一种基于人形识别的多人在离岗识别方法、装置、电子装置和存储介质
CN108154070A (zh) 人脸识别方法及装置
KR102777663B1 (ko) 얼굴 인식 시스템 및 얼굴 인식 시스템을 위한 제어 방법
CN112241674B (zh) 一种人脸识别方法及系统
CN115147888A (zh) 基于人脸的门禁管理方法、门禁设备及计算机可读存储介质
US20120219192A1 (en) Method of controlling a session at a self-service terminal, and a self-service terminal
CN110020587B (zh) 识别系统智能提速的方法、系统、装置、设备和计算机可读介质

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: 18875886

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 1205 DATED 08/10/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18875886

Country of ref document: EP

Kind code of ref document: A1