Living body detection method based on color change

Abstract

The invention provides a living body detection method based on color change. A plurality of different color sequence light sources are adopted to perform human face video image acquisition on a detection object, a human face image of a corresponding color is presented through a color verification code sequence, the consistency of color verification codes is judged through a color recognition neural network, and whether fraud exists or not is detected through an anti-fraud network. According to the embodiment of the invention, the method enables a user to passively complete the living body detection in a mode of using the color verification code, reduces the tedious degree of use for the user, can achieve the obvious difference after the interpolation calculation of a plurality of frames offace images in different colors because of the different reflection degrees on different media, and can effectively improve the accuracy of the living body detection.

Description

technical field [0001] The present application relates to the technical field of deep learning and artificial intelligence, and is a method for detecting living bodies based on color changes. Background technique [0002] Compared with biometric features such as fingerprints and iris, facial features are the easiest to obtain. Face recognition systems are gradually being commercialized, and are developing towards an automated and unsupervised trend. However, at present, face recognition technology can identify the identity of a face image but cannot accurately identify the authenticity of the input face. So how to automatically and effectively distinguish the authenticity of images and resist spoofing attacks to ensure system security has become an urgent problem to be solved in human recognition technology. [0003] There are several ways of general liveness detection: [0004] Discrimination using texture information from recaptured color images of human faces. Because ...

AI Technical Summary

Problems solved by technology

This technology needs to calibrate the internal parameters of the camera, and the accuracy of the calibration of the internal parameters of the camera, the rotation and displacement relationship between the cameras that take different images, and the quality of the image have a great impact on the reconstructed human depth value. The method has a high false detection rate for live detection

[0008] In the process of research and practice of existing technologies, it is found that the algorithm used in the existing living body detection scheme has a low judgment accuracy and cannot effectively resist synthetic face attacks. In addition, cumbersome active interaction is also difficult It will greatly reduce the pass rate of correct samples. Therefore, on the whole, the living body detection effect of the existing scheme is not good, which greatly affects the accuracy and security of identity verification.

Images