CN210038881U

CN210038881U - Anti-following face recognition management system

Info

Publication number: CN210038881U
Application number: CN201920798223.5U
Authority: CN
Inventors: 韩子天; 李立标
Original assignee: Zhongshan Anxintong Robot Manufacturing Co Ltd
Current assignee: Zhuhai Quanxintong Technology Co ltd
Priority date: 2019-05-29
Filing date: 2019-05-29
Publication date: 2020-02-07
Anticipated expiration: 2029-05-29

Abstract

A kind of anti-following human face recognition management system, including security center, server and setting up in the recognition detection system of every entrance; the server is connected with the security center through an intranet; the recognition detection system comprises an entrance camera, an entrance face recognition host, an exit camera, an exit face recognition host, a radar, a voice player and a display screen which are connected to the extension network switch; all the extension network switches of the identification and detection system are connected to the switchboard network switch; switchboard network switch is connected with this server, carries out face identification in order to judge legal identity and statistics number when like this taking with the help of the camera, and the number is listened to the rethread radar, passes through when the number between them is unanimous, has just so avoided appearing leaking the condition of judging or erroneous judgement when pasting too closely entering the attendance zone between the people mutually to reach the face identification purpose of preventing following, consequently the utility model discloses an attendance is more accurate.

Description

Anti-following face recognition management system

Technical Field

The utility model relates to a face identification technical field specifically is a prevent following face identification management system.

Background

As is known in the art, people distinguishing management based on face recognition are more and more widely used, for example, occasions such as enterprise attendance, stations, customs entry and exit, etc., a gate mode is often adopted in the current technical scheme, and only a specific interval of a person in the near day is limited for recognition, so that the application cost is obviously increased, and some occasions are not suitable for management by using gate equipment, for example, attendance management at a dormitory doorway or a classroom doorway.

In a face recognition occasion which is not suitable for being limited by an installation gate machine, other face recognition schemes are proposed, for example, a utility model patent application with the patent application number of CN201910025123 is provided, which is based on a face recognition system and a method thereof, and comprises a front-end camera, the face recognition system, a staff face information database and a control module, wherein the front-end camera is used for automatically shooting an attendance area image and outputting the image to the face recognition system, the face recognition system is used for automatically recognizing the face of the obtained image, comparing the recognition result with the staff face information database, recognizing the identity of the staff according to a set threshold value, and obtaining the attendance result by screening and processing the data, the staff only need to pass through the attendance area without being in sight with the camera or staying in front of the camera for a short time, and the single processing amount of the mode is large, and then promoted attendance efficiency and quality, but can't solve the erroneous judgement or the problem of failing to judge when two people relatively closely got into the attendance region to cause very big inconvenience for the unit of using the system.

Patent application number is CN 201910024160's a face identification gate machine, including entrance guard main control module, set up the camera of the support RTSP agreement at the gate and the power management module for each module power supply, entrance guard main control module includes main control unit and the wired network module who is connected with main control unit respectively, wireless network module and electronic lock or gate execution module, wired network module pass through the net twine with the camera is connected, the camera is used for acquireing the face information that is located the gate, and transmit the face information who acquires for main control unit through wired network and carry out face identification, main control unit is used for passing the cloud ware with the face identification result after discerning face information, compare the face identification result that authority information and the main control unit of opening the door that store in the cloud ware transmitted, judge whether to open the door. The main control part and the camera for face snapshot are separated and can independently operate, the main control part is not limited by the installation limit of environment and position, but the problem of misjudgment or missed judgment when people are close to each other cannot be solved

For the occasions (such as students' dormitories and the like) where people need to be strictly limited to go out, an attendance method for preventing people from going out without identification is necessary. Therefore, some people improve the current attendance, such as a method, a device and a face recognition system for attendance by multiple people with the patent application number of CN201811615540, wherein the method comprises a first camera and a second camera, and the method comprises the following steps: acquiring a current image of a designated area acquired by a first camera; analyzing whether one or more attendance checking persons exist in the designated area or not according to the current image; if one or more attendance checking persons exist in the designated area, analyzing the attendance checking persons to form an analysis result; determining whether to start a second camera according to the analysis result so as to acquire a first face image; and performing face recognition attendance according to the first face image. The method for attendance by multiple people can be used for the multiple people to carry out face recognition attendance, and the attendance efficiency based on face recognition is effectively improved.

The applicant proposes to use a camera and a radar to combine to solve the problem of follow-up prevention during attendance checking.

Disclosure of Invention

An object of the utility model is to overcome prior art not enough, provide a more accurate face identification management system of following of preventing of attendance.

In order to solve the technical problem, the utility model adopts the following technical scheme:

an anti-following face recognition management system comprises a security center, a server and a recognition detection system arranged at each entrance, wherein:

the security center comprises a plurality of monitors;

the server stores face pictures of all the personnel to be checked, and the face pictures are connected with the security center through an intranet;

the identification detection system comprises an entrance camera, an entrance face identification host, an exit camera, an exit face identification host, a radar, a voice player and a display screen, which are connected to the extension network switch; all the extension network switches of the identification and detection system are connected to the switchboard network switch; the switchboard network switch is connected with the server.

Compared with the prior art, the beneficial effects of the utility model are that: because when carrying out face identification with the help of the shooting of camera in order to judge legal identity and statistics number, the number is listened to the rethread radar, passes through when the number between them is unanimous, has just so avoided appearing leaking the condition of judging or erroneous judgement when pasting too closely entering the attendance zone between the people to reach the face identification purpose of preventing following, consequently the utility model discloses an attendance is more accurate.

The invention will be described in further detail with reference to the following detailed description and accompanying drawings:

[ description of the drawings ]

Fig. 1 is a schematic connection diagram of an embodiment of the present invention.

[ detailed description ] embodiments

The utility model relates to a prevent following face identification management system, as shown in fig. 1, including security center 1, server 2 and establish at the discernment detecting system 3 of every entrance, wherein:

the security center 1 comprises a plurality of monitors 11 for personnel in the security room to check the personnel entering and exiting conditions at each entrance and exit;

the server 2 stores face pictures of all the persons to be checked, and is connected with the security center 1 through an intranet 4;

the recognition detection system 3 comprises an entrance camera 31, an entrance face recognition host 32, an exit camera 33, an exit face recognition host 34, a radar 35, and a voice player and display screen 36, which are connected to an extension network switch 37; all the extension network switches 37 of the identification detection system 3 are connected to the switchboard network switch 6; the switchboard network switch 6 is connected to the server 2. The radar 35 and the camera monitor the personnel entering the identification area;

when in use, the utility model has the following working method:

1) when attendance personnel (such as students) enter the identification range of the identification detection system, the radar human shape detection and the human face detection are started, so that the radar and the camera start to work; for example, when a person wants to enter, the radar, the entrance camera and the entrance face recognition host work, and when the person wants to exit, the radar, the exit camera and the exit face recognition host work;

2) identifying the number of people entering the area through radar monitoring;

3) extracting a face picture with the best quality from a video stream transmitted by the camera and sending the face picture to a server for personnel legal identity verification;

4) when the number of people detected by the radar is consistent with the number of people with legal identities, the radar passes through the attendance checking area, so that the condition of missing judgment or misjudgment when people are close to each other and enter the attendance checking area is avoided, and the purpose of anti-following face identification is achieved.

5) When an illegal identity is found (namely the face recognized by the face recognition host does not correspond to the face picture stored in the server), alarm information is sent to the security center to indicate that a person enters, and at the moment, the voice player gives a voice prompt;

6) when the number of people detected by the radar is inconsistent with the number of people with legal identities, alarm information is sent to a security center, and at the moment, a voice player gives out a sound prompt to indicate that the condition of missing judgment or misjudgment occurs;

7) and when the human shape detection result does not have the face recognition result, sending alarm information to the security center to indicate that a person enters.

From the above, when carrying out face identification with the help of the shooting of camera in order to judge legal identity and statistics number, the number is listened to the rethread radar, passes through when the number between them is unanimous, has just so avoided appearing the condition of missing judgement or erroneous judgement when pasting too closely entering the attendance zone between the people to reach the face identification purpose of preventing following, consequently the utility model discloses an attendance is more accurate.

Although the present invention has been described in detail with reference to the above embodiments, it will be apparent to those skilled in the art from this disclosure that various changes or modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims. Therefore, the detailed description of the embodiments of the present disclosure is to be construed as merely illustrative, and not limitative of the present disclosure, but rather to limit the scope thereof by the appended claims.

Claims

1. The utility model provides a prevent following face identification management system, includes security center, server and establishes the discernment detecting system at every entrance, its characterized in that:

the security center comprises a plurality of monitors;