Method and device for human face liveness detection

Abstract

The present application discloses a human face detection method and device. The method includes: obtaining multiple human face image sequences, the multiple human face image sequences are human face image sequences of the same detection object under multiple spectrums; using a convolutional neural network Feature extraction is performed on multiple face image sequences to generate multiple sets of face feature images, wherein the convolutional neural network includes multiple sub-neural networks, and each sub-neural network is used to process a face image sequence in the multiple face image sequences Perform feature extraction to generate a set of face feature images; input multiple sets of face feature images to the same convolutional layer of the convolutional neural network, and process multiple sets of face feature images according to the preset processing method to obtain detection objects Liveness features of the face; according to the liveness features of the face, the liveness of the detection object is judged. This method can overcome the disadvantage of unstable detection under visible light and the problem of low detection accuracy when a single frame of face image is used for live body detection.

Description

technical field [0001] The present application relates to the technical field of biological feature recognition, and in particular to a method and device for detecting human face liveness. Background technique [0002] With the advancement of technology, biometric identification technology is increasingly used in daily life. As a biometric identification technology, face recognition technology has been widely used due to its characteristics of easy collection, non-contact, and high recognition rate. Face liveness detection technology is an important part of the face recognition system. By distinguishing whether the object in front of the camera is a real person or a prosthesis, the security of the face recognition system can be effectively improved. The current human face liveness detection method mainly uses the method of machine learning to recognize a single frame of human face images under visible light, so as to determine the liveness of the detection object. Among th...

AI Technical Summary

Problems solved by technology

[0003] The present application provides a human face liveness detection method and device to solve the problem that in the existing face liveness detection method, when the light changes greatly, the detection effect is unstable and the lack of timing information of the image leads to low detection accuracy. question

Images