Rapid living body detection method and system

Abstract

The invention discloses a rapid living body detection method and system, and belongs to the field of living body detection. According to the method, spectrograms of a real face image and a secondarily shot face image under the multi-scale and multi-rotation-angle conditions are constructed, and the projection vectors of the spectrograms in the horizontal and vertical directions are used as the feature vectors, so that the moire features of the images can be fully extracted without depending on a complex neural network structure, and rapid detection of the video replay attack means is realized. According to the method, blood volume distribution is constructed by using the correlation between the overall face signal of the face image and the local interested signal, the frequency peak value distribution is calculated on this basis, the accurate positioning of the region containing the physiological signal is realized in combination with the threshold segmentation model, and the high-precision detection can be performed on the high-simulation mask and high-definition image attack. According to the invention, it is not needed to specify face actions to cooperate with detection, comprehensive detection can be carried out only by collecting face videos, main living body detection attack modes are covered, and the detection precision and detection speed are high.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method and system for fast living body detection. Background technique [0002] At present, the realization of live attack detection based on signal processing technology and deep learning technology has high practical value, so it is a hot and difficult point of current research. Liveness detection is mostly used in security verification. It has high requirements for the detection accuracy, detection speed and detection range of live attacks. It often requires the subject to be detected to perform random specified facial movements to cooperate with the detection. However, this detection method cannot completely prevent high The accuracy simulates methods such as mask attacks, and users are likely to feel uncomfortable or embarrassed during the detection process. Common problems in the prior art: single detection method or method cannot effectively cover most typical liveness d...

AI Technical Summary

Problems solved by technology

Liveness detection is mostly used in security verification. It has high requirements for the detection accuracy, detection speed and detection range of live attacks. It often requires the subject to be detected to perform random specified facial movements to cooperate with the detection. However, this detection method cannot completely prevent high Accurate simulation of mask attacks and other methods, and users are likely to feel uncomfortable or embarrassed during the detection process

Common problems in the existing technology: the single detection method or method cannot effectively cover most of the typical living detection attack methods, and the single detection method is prone to obvious loopholes, which are easy to be identified and exploited

Images