Face fraud detection method and system based on static texture, and storage medium

Abstract

The invention discloses a face fraud detection method and system based on static texture, and the method comprises the steps: reading a training set video, carrying out the frame-by-frame face image detection of an inputted video, obtaining an image with face position information, and carrying out the face clipping of a corresponding image; performing texture feature extraction in each color channel of the selected color space by adopting a DQ _ LBP feature extraction method; adopting a spatial pyramid algorithm to perform direct square information on the texture feature pictures, and cascading the texture feature pictures to form a one-dimensional vector representing color texture features of the pictures; cascading the color texture feature vectors in each complementary color space to form a final representation representing the features of the current picture; normalizing the training set data obtained through the above steps, and putting the normalized training set data into a support vector machine of a linear kernel for classification. The method has the advantages of being high in transportability, free of user cooperation, high in matching speed, simple and efficient.

Description

technical field [0001] The invention relates to the technical field of image processing and pattern recognition, in particular to a face fraud detection method based on static texture. Background technique [0002] Today, face recognition technology has been widely used in human daily life, ranging from the security inspection system of airport stations to the identity verification function on mobile terminals that can be seen everywhere. Face recognition technology not only greatly improves the efficiency of identity information verification, but also brings users a fast and convenient life experience. However, a fraudulent attack occurs when someone fakes a customer's face and tries to pass the verification of a facial recognition system. [0003] At present, most of the anti-fraud operations based on facial recognition in identity verification software require human-computer interaction. For example, customers need to perform combined actions according to the system prom...

AI Technical Summary

Problems solved by technology

[0007] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a static texture-based face fraud detection method, which can solve the problem of low accuracy of face fraud detection in the prior art. The present invention also provides a Face Fraud Detection System Based on Static Texture

Images