Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face recognition and face automatic database building algorithm for security gate based on multi-camera fusion

A multi-camera, security doorman technology, applied in the direction of character and pattern recognition, computing, computer components, etc., to achieve the effect of ensuring the frontal rate, improving the recognition rate, and increasing the speed of security inspection

Active Publication Date: 2021-08-24
BEIJING BORUISHI TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of fast security inspection of the security inspection door, the present invention proposes a security inspection door face recognition and face automatic database building algorithm based on multi-camera fusion

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face recognition and face automatic database building algorithm for security gate based on multi-camera fusion
  • Face recognition and face automatic database building algorithm for security gate based on multi-camera fusion
  • Face recognition and face automatic database building algorithm for security gate based on multi-camera fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further explained below in conjunction with the accompanying drawings and specific examples. It should be pointed out that the examples described below are intended to better understand the present invention, and are only a part of the present invention, and therefore do not limit the protection scope of the present invention.

[0023] Such as figure 2 As shown, the present invention realizes face detection, face tracking, face quality evaluation, face pose estimation, face alignment calibration, face feature extraction, face feature comparison, and face automatic construction by multiple cameras simultaneously. library and a series of steps.

[0024] In step 201, an empty face database is created, or a face-related information database index is established using manually collected faces as an initial base database. Allocate disk storage space and memory space for each security gate face recognition system.

[0025] In step 202, N camer...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

In order to solve the problem of fast security inspection of the security inspection door, the present invention proposes an algorithm for face recognition at the security inspection door and automatic face database building based on multi-camera fusion. The algorithm of the present invention does not need the active cooperative face scanning of the inspected person, but only needs to walk according to the normal route, which belongs to the non-cooperative face recognition algorithm. Multiple cameras are installed on the security gate along the direction of people entering. These cameras collect video at the same time for face detection. The detected faces are screened by the face quality evaluation module after face tracking, and the screened faces pass through The corresponding upper body matching algorithm selects faces belonging to the same person, and then deletes faces with too large angles through pose estimation, and then aligns and calibrates the faces and inputs them into a deep convolutional neural network to extract features. Based on the facial features extracted above, the multi-camera face comparison algorithm is used for face matching and automatic database building. The multi-camera fusion face recognition algorithm of the security gate of the present invention significantly improves the speed of security check and reduces safety hazards such as crowding caused by security check.

Description

technical field [0001] The invention belongs to the field of security and security inspection, and relates to pattern recognition, graphic image processing, machine learning, etc., using multiple cameras to collect faces, and merging these faces through face pose estimation and face recognition technology based on deep learning, Then automatically build a multi-camera face recognition library. Background technique [0002] The world seems to be peaceful, but it is not safe. Terrorism and extremism are quietly infiltrating people's lives, so security precautions are still a very important topic. To a certain extent, security inspection can detect dangerous goods in time to ensure the safety of people's lives and property. Security inspection equipment has been deployed in various public places such as airports, subways, and important venues. The security gate is a kind of equipment for detecting the human body. The domestic human body security check mainly adopts walk-throug...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/166G06V40/172G06V40/168G06N3/045
Inventor 张恩伟
Owner BEIJING BORUISHI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products