A multi-modal authentication method with high anti-spoofing based on competition and cooperation mechanism

Abstract

The invention discloses a high anti-spoofing multi-modal identity verification method based on a competition and cooperation mechanism, which belongs to the field of pattern recognition. Verify the dictionary, sparsely represent the input sample features, and calculate the matching degree and correlation between the input sample and the target class; S2 evaluates the quality of each modal input sample, and calculates the adaptive coding weight accordingly; The modal adaptive joint sparse representation is used to calculate the multimodal matching degree and correlation degree; S4 cascades the multimodal matching degree and correlation degree of each modal into a multimodal matching vector, which is input to the classifier for authentication. Before the system is deployed, use the multi-modal matching vector positive samples, common negative samples and spoofing sample sets to train the classifier together, so that it has the ability to identify common negative samples and spoofing samples, and effectively improve the anti-spoofing ability of multi-modal authentication. At the same time, the verification accuracy is not reduced.

Description

technical field [0001] The invention belongs to the field of biometric identity verification, mainly relates to pattern recognition technology, and in particular relates to a high anti-spoofing multimodal identity verification method based on a competition and cooperation mechanism. Background technique [0002] Spoofing attacks use fake biometrics such as silicone fingerprints, face photos, videos, 3D masks or head models on the sensor side to fool biometric authentication systems. If a single-modal authentication system cannot effectively verify that the biometric information collected is from a counterfeit object, the possibility of being cracked is very high. Multimodal biometrics are often considered high security because they require the user to input multiple types of biometrics. However, recent studies have shown that when one or several biometrics of the user are forged and used for spoofing attacks, the probability of successful deception of multimodal systems is ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a highly anti-spoofing multi-modal identity verification method based on a competition and cooperation mechanism to solve the above-mentioned problem of greatly reducing the verification accuracy in the case of ordinary verification without significantly improving the anti-spoofing performance of the system question

Images