Living body recognition method and recognition device based on eye change characteristics and electronic equipment

Abstract

The invention provides a living body recognition method and device based on eye change characteristics and electronic equipment. The method comprises the steps: randomly changing the display content of a detection screen, and obtaining a plurality of eye images of a user and a plurality of display content images of the detection screen at the same frame rate; inputting each eye image and each display content image into a pre-trained sequential neural network model to obtain a corresponding eye feature vector and a display content feature vector, furthermore, a first change feature vector and a second change feature vector which represent the eye image change process and the display content image change process respectively are obtained through a pre-trained recurrent neural network model, and whether the object to be recognized is a living body or not is determined by judging whether the change processes corresponding to the two change feature vectors are consistent or not. Compared with a mode that a user face picture forged in a mode of printing a picture and the like cannot be kept consistent with randomly-changed screen display content, the living body recognition accuracy and the identity authentication safety are improved.

Description

technical field [0001] The present application relates to the technical field of identity verification, and in particular to a living body identification method, identification device and electronic equipment based on eye change characteristics. Background technique [0002] With the popularization of smart devices, facial recognition has become one of the most convenient methods in the process of unlocking mobile phones, mobile payments, and remote identity verification. Compared with traditional password verification methods, facial recognition can more accurately determine Whether the verification process is performed by the person himself or not, at present, in order to prevent the use of printed photos or screen photos, etc. Nodding, shaking the head and other actions to determine that the object to be recognized is a living body. However, the recognition success rate of this method is low and the user's face is easily replaced by printed photos, screen photos, etc., an...

AI Technical Summary

Problems solved by technology

[0002] With the popularization of smart devices, facial recognition has become one of the most convenient methods in the process of unlocking mobile phones, mobile payments, and remote identity verification. Compared with traditional password verification methods, facial recognition can more accurately determine Whether the verification process is performed by the person himself or not, at present, in order to prevent the use of printed photos or screen photos, etc. Nodding, shaking the head and other actions to determine that the object to be recognized is a living body. However, the recognition success rate of this method is low and the user's face is easily replaced by printed photos, screen photos, etc., and the security is poor.

Images