Living body detection and recognition method based on multi-modal data fusion

Abstract

The invention relates to in-vivo detection and identification, and particularly relates to a living body detection and recognition method based on multi-modal data fusion. The method comprises the following steps: collecting a fingerprint image to be detected, a palm vein distribution image and an iris image, collecting a forward face image and an infrared non-front face image, extracting matrixesobtained by discrete cosine transform of the fingerprint image and the palm vein distribution image, comparing the data with data in a living body database, judging whether the collected fingerprintimage and palm vein distribution image are living body images or not, extracting matrixes obtained by discrete cosine transform of the fingerprint image and the palm vein distribution image respectively, comparing the matrixes with data in the living body database, and judging whether the collected fingerprint image and palm vein distribution image are living body images or not. The technical scheme provided by the invention can effectively overcome the defects of easy camouflage attack, detection limitation and lack of human face image association recognition in various forms in the prior art.

Description

technical field [0001] The invention relates to living body detection and recognition, in particular to a living body detection and recognition method based on multimodal data fusion. Background technique [0002] Biometric identification technology can identify personal identity through facial features, fingerprint features, vein features, palmprint features, voiceprint features and even iris features. At present, it is the most convenient and safe identification technology, and it is easy to cooperate with computers to realize automatic management, so it is widely used. However, with the continuous emergence of high-tech means such as artificial headgear, holographic projection, and face tracking, the method of using a single biometric feature for identification and authentication has been greatly compromised in terms of accuracy and security. It is an inevitable trend of biometric identification. [0003] Existing biometric technology often adopts single-dimensional bio...

AI Technical Summary

Problems solved by technology

[0003] Existing biometric technology often adopts single-dimensional biometric identification. Due to the variety of attack methods and different attack modes of live detection attacks, single-dimensional biometric features are easily forged, resulting in accurate live detection and recognition. The degree is reduced, and there are also detection limitations in practical applications

In addition, in the process of face image detection and recognition, there is a lack of associated recognition of face images in various forms, resulting in the inability to determine whether multiple face images from different angles come from the same living body

Images