A Binocular Face Recognition Liveness Detection Method Based on Access Control System

Abstract

The invention discloses a binocular face recognition living body detection method based on an access control system. It specifically includes the following steps: (1) adopt binocular acquisition system to carry out video image acquisition; (2) carry out face detection to the collected color video image; and infrared video images are analyzed; (4) the SVM living body detection classifier of machine learning is used to classify and detect photos and living bodies; (5) the collected faces and the face bottom library are matched and identified, and if the matching is successful, then If the face recognition is successful, the access control system will open the door; if the matching fails, the access control system will not open the door. The beneficial effects of the present invention are: not only the cost is small, but also the algorithm speed is fast, and the algorithm effect can also be guaranteed; in addition, the detection accuracy rate of living body detection can be greatly improved by cooperating with the analysis of color images and infrared images, without the cooperation of users Do actions more quickly and conveniently.

Description

technical field [0001] The invention relates to the technical field related to biological pattern recognition, in particular to a binocular face recognition living body detection method based on an access control system. Background technique [0002] With the development of biometric technology and pattern recognition technology, face recognition technology has become mature, and the face recognition system can already perform face detection and recognition very well, but for the access control system, users can rely on photos to deceive the system. , Therefore, for the above-mentioned defects existing in the current prior art, it is necessary to conduct research to provide a solution to solve the defects existing in the prior art and avoid the crisis of using photos to break through the access control system. [0003] The existing binocular face recognition liveness detection mainly adopts three types of schemes: 1. Liveness detection with actions, the user needs to coopera...

AI Technical Summary

Problems solved by technology

2. Use the image algorithm to determine whether the video captured by the monocular camera is a living body. Since the live face and photos collected by the camera are two-dimensional images, it is difficult to distinguish whether it is a photo or a human face with a simple image algorithm, and the detection rate is low.

3. Use the depth camera for 3D modeling to judge whether it is a living body, but this method not only needs to add a depth camera, the depth camera is expensive and expensive, but also the 3D modeling algorithm is complex and the operation speed is slow

Images