Anti-cheating method in face recognition system

A face recognition system and anti-spoofing technology, applied in the field of anti-spoofing, can solve the problems of weak generalization ability and weak discrimination ability, and achieve the effect of good detection effect, fast detection speed, and improved training effect.

Pending Publication Date: 2018-05-15
SEETATECH BEIJING TECH CO LTD
View PDF5 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The features extracted by this method are relatively simple, the discrimination ability is not s

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Anti-cheating method in face recognition system
  • Anti-cheating method in face recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] figure 1 An anti-spoofing method in a face recognition system shown, the specific steps are:

[0041] Step S1, acquire images and perform normalization processing:

[0042] Obtain an RGB image through the camera device, and then input the acquired RGB image to the cascade CNN face detection module; the face detection module performs face detection on the RGB image, and if a face is detected, the image of the face area in the figure is The input is given to the deep neural network to locate the key points of the face, and by calculating the affine transformation from the key points to the standard key points, the face pictures in different poses are transformed into the face pictures in the standard pose;

[0043] Step S2, feature extraction stage:

[0044] The following seven features are extracted:

[0045] a. Color diversit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an anti-cheating method in a face recognition system. The method comprises the following specific steps that: obtaining an image, carrying out normalization processing on the image, and carrying out a feature extraction step, a model design stage, a training stage and a prediction stage, wherein the feature extraction stage is used for extracting seven features including color diversity features, fuzzy degree features, picture moment features, definition features, spectral features, mirror image features and convolution features. By use of the method, a residual-mlp network is cooperated with face micro-textures and a support vector machine, the accuracy and the speed of face living body detection are greatly improved, and in addition, a better detection effect canbe achieved. In addition, by use of the method, hardware except the camera does not need to be added, in addition, super real-time face living body detection speed can be achieved without the operation of personnel to be detected, and the problem in the prior art that living body detection time is long, the hardware needs to be added and detection ability is poor can be solved.

Description

technical field [0001] The invention relates to an anti-spoofing method, in particular to an anti-spoofing method in a face recognition system, and belongs to the technical field of machine vision. Background technique [0002] Face recognition has gradually become an important encryption and decryption method due to its rapidity, effectiveness, and user-friendliness. However, many face recognition systems cannot distinguish the authenticity of faces. Therefore, in order to prevent fake faces from causing Introducing the liveness detection method in the face recognition system will improve the practicability and security of face recognition. At present, the main methods of face detection are as follows: [0003] (1) Interactive active liveness detection based on video stream: first, the system performs face detection and face key point positioning. If there is a face in the video, several actions are randomly generated. If the tester completes the specified action within th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/172G06V40/168G06V40/45G06N3/045
Inventor 张宇聪张杰刘昕山世光
Owner SEETATECH BEIJING TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products