Near-infrared face vivo detection method and system

Abstract

The invention provides a near-infrared face vivo detection method. The method comprises the steps: S1, original positive samples and original negative samples are collected through a near-infrared camera, S2, preprocessing the original samples through the face region detection model in deep learning so as to select the standard face images which can be fed into the network to be trained; S3, constructing a training set and a test set from the selected positive and negative samples suitable for network training and substituting the samples into the lightweight convolutional neural network to betrained so as to obtain the trained face vivo detection model; and S4, the images to be judged collected by the near-infrared camera are inputted into the face vivo detection model for vivo judgment.The parameter quantity is reduced through the lightweight convolutional neural network, the size of the model is reduced, transplanting to the mobile terminal is more convenient and thus the method and the system can be widely popularized in the field of biological characteristic identification technology for the above reasons.

Description

technical field [0001] The invention relates to the technical field of biological feature recognition, in particular to a near-infrared human face living body detection method and system. Background technique [0002] With the rapid development of computer technology, the recognition rate of biometric recognition technology is also steadily increasing. Among various recognition technologies, face recognition is characterized by high security, good stability, naturalness, non-contact and concealment. And other advantages, are widely used in criminal investigation, monitoring system and security detection technology. Fake face attack refers to illegal users attempting to obtain system access by providing false data, that is, duplicating legitimate user pictures, videos, and 3D molds. Among them, duplicating legitimate user pictures and videos to intercept user pictures, due to low cost and simple implementation, has become The main attack method used by illegal intruders. For...

AI Technical Summary

Problems solved by technology

[0003] The existing research on live face detection algorithms can be roughly divided into two categories: static detection algorithms and dynamic detection algorithms, but these two algorithms have a single method and cannot accurately describe the characteristics of live faces. The detection accuracy of face fraud is not high enough, it is not robust, and it is highly constrained by the scene. Due to the long time and easy disappearance of the gradient, it has not been applied to mobile terminals or embedded devices on a large scale

Images