Human face living body detection method and device

Abstract

The invention discloses a human face living body detection method and device. The method comprises the steps of collecting a to-be-detected human face image; performing feature extraction processing on the to-be-detected face image to generate a plurality of feature images; inputting the to-be-detected face image and the feature image into a face living body detection classification model obtainedthrough machine learning training in advance, and outputting a face living body detection result; performing feature extraction processing on the to-be-detected face image to generate a plurality offeature images, which comprises: performing illumination normalization processing on the to-be-detected face image to generate an illumination normalization processing image; performing feature extraction processing on the to-be-detected face image by adopting an LBP algorithm to generate a texture feature image; converting the face image to be detected into an HSV space from an RGB color space, and generating an HSV image; and performing DCT on the to-be-detected face image to generate a frequency spectrum image. The method is short in detection time and high in human face living body detection precision, and the influence of illumination on recognition can be reduced.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face liveness detection method and device. Background technique [0002] With the continuous development and progress of biometric recognition technology, face recognition has been widely used in business, security and other fields based on its characteristics of visualization and conforming to people's thinking habits. However, the face recognition system is vulnerable to malicious attacks by illegal users, which poses a great threat to the security performance of the face recognition system. For malicious attacks, it is very important to design a face anti-spoofing system with high detection accuracy, short time consumption, strong robustness, and strong generalization ability. The anti-spoofing detection of the face recognition system is also called face liveness detection. [0003] The living body detection technology used in the prior art can be divided into two...

AI Technical Summary

Problems solved by technology

[0003] The living body detection technology used in the prior art can be divided into two categories: one is based on multi-frame pictures or video sequences to calculate, using interactive or non-interactive detection mode, by analyzing the motion information in continuous multi-frame images, identifying The authenticity of the face, but this type of method is computationally complex and takes a long time

The other type is based on single-frame image input, and is identified by analyzing the texture, frequency spectrum, and degree of reflection in the image. However, this type of method relies on the common judgmental features of a large number of forged faces, and the accuracy of human face detection lower

Images