Living body detection method, device and apparatus based on face recognition

Abstract

The invention discloses a living body detection method based on face recognition. The method comprises the steps of obtaining an original picture of a to-be-detected user; segmenting the original picture by using a pyramid scene analysis network to obtain a preliminary feature map corresponding to the original picture; cutting the preliminary feature map by using a preset face detection frame to cut out a region feature map containing face features; calculating a confidence coefficient obtained by fusing the preliminary feature map and the regional feature map; and determining a living body detection result according to a size relationship between the confidence coefficient and a preset confidence coefficient threshold. The invention further discloses a living body detection device based on face recognition and living body detection equipment based on face recognition. By adopting the embodiment of the invention, the space-time information can be fully utilized, the noise influence ofa single picture is reduced, the fitting capability for the actual situation is high, and the recognition accuracy is high.

Description

technical field [0001] The present invention relates to the field of face recognition, in particular to a face recognition-based living body detection method, device and equipment. Background technique [0002] With the wide application of face recognition technology, prosthetic face attacks such as face photos, face videos, and 3D masks emerge in an endless stream, and face liveness detection has attracted more and more attention from industry and academia. Face liveness detection has gradually become an indispensable link in the face recognition system. From the perspective of processing image types, the current common face detection method is the traditional face recognition system. Through the improved scheme of LBP, the discrimination of living body texture is realized. In addition, based on this scheme combined with tracking technology, the detection of living body Stability, and a supporting embedded hardware device is proposed. [0003] However, the design of the t...

AI Technical Summary

Problems solved by technology

[0003] However, the design of the traditional method is mainly based on manual work, the design is cumbersome, and the effect is limited, the ability to fit the actual situation is not high, and there is a certain bottleneck in the situation that can be dealt with

Moreover, the scheme based on texture discrimination has single features, limited application range, and low recognition accuracy

Images