Access control system for large traffic scene based on two-dimensional face recognition

Abstract

The invention discloses an access control system for a large traffic scene based on two-dimensional face recognition, the access control system comprises an access control terminal disposed at an entrance and exit, wherein the access control terminal is connected to a remote server, a user access record management website and a remote real-time monitoring terminal through a communication network.The access control terminal is provided with a Raspberry Pi camera, a face detection module, a face recognition module and an access control module, wherein a face information table is set in the remote server, the face information table includes user's photo code information, and the photo code information is obtained by performing 68 key point detection adjustment on a user's front face or sideface photo, and then encoding 128 parameters through a FaceNet deep convolutional neural network. The access control system has a good effect on recognition rate and security, does not require a largeamount of face data, and can greatly improve access control efficiency without strict user cooperation in the case of security. Data mining is performed by using user access information, and user's living habits are analyzed by recorded entrance and exit data for detection of user's abnormal states.

Description

technical field [0001] The invention belongs to the field of intelligent access control systems, and in particular relates to an access control system based on two-dimensional face recognition and facing large traffic scenes. Background technique [0002] With the continuous progress of society and the urgent requirements for fast and effective automatic identity verification, biometric technology has developed rapidly in recent decades. As an inherent attribute of human beings, with strong self-stability and individual differences, biometric features have become the most ideal basis for automatic identity verification. The current biometric recognition technologies mainly include: fingerprint recognition, retinal recognition, iris recognition, gait recognition, vein recognition, face recognition, etc. Compared with other recognition methods, face recognition has been widely researched and applied because of its direct, friendly and convenient features, without any psycholo...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the problems existing in the prior art, to provide a two-dimensional face recognition-based access control system for large-traffic scenes, and to solve the shortcomings of traditional face recognition detection that have high environmental requirements, slow detection speed and poor security , and run on the Raspberry Pi Internet of Things platform, and can solve the existing dilemma of using neural networks for face detection and facing difficulties in training data collection

Images