Identification method for video and living body faces based on background comparison

A background, living technology, applied in the field of automatic identification of video faces and living faces, can solve problems such as influence

Active Publication Date: 2011-11-23
浙江浙大西投脑机智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some of these methods require the cooperation of the user's head or face, while others are greatly affected by external environmental conditions.

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
  • Identification method for video and living body faces based on background comparison
  • Identification method for video and living body faces based on background comparison
  • Identification method for video and living body faces based on background comparison

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Determination of face positioning and background comparison area:

[0035] For each frame image of the input video, the face location must be performed first. Using Haar similar features and cascade Adaboost method (refer to: P.Viola, M.J.Jones, Rapid Object Detection using a Boosted Cascade of Simple Features. IEEE Conference on. Computer Vision and Pattern Recognition, pp.511-518, 2001.) combination, Face position detection is performed on each frame of the input video. The cascaded Adaboost method is to cascade several Adaboost classifiers, that is, to use the classification result of the previous classifier as the classification content of the next classifier to improve the classification performance. The Adaboost classifier uses face images and non-face images as samples to train parameters. The features extracted from the sample are Haar-like features, because Haar-like features can effectively express important features such as eyes, nose bridge, and mouth in h...

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 identification method for video and living faces based on background comparison, comprising the following steps of: firstly, detecting the face position of each frame of an image of input video, and determining a background comparison district according to the detected face position; secondly, selecting an extreme point of the input video and the background comparison district on dimension space as a characteristic point of the background comparison district to obtain a background characteristic point set (Pt); thirdly, describing the characteristics of the image I on the background characteristic point set (Pt) by Gabor wavelet transformation; and fourthly, defining a living body value (L) by the result of the third step, wherein if the living body value (L) islarger than the threshold theta, the living body is determined, and otherwise, the living body is fake video. The invention mainly solves the problem of the computer automatic identification of videofaces and living body faces only by a single camera.

Description

technical field [0001] The invention relates to the technical field of video and image computer processing, in particular to a method for automatically distinguishing video human faces and live human faces through background comparison. Background technique [0002] Live face detection is an important guarantee for the security of computer face recognition systems. For two-dimensional face recognition systems, it is a common attack method to impersonate a user in front of the camera by using the video of a legitimate user. The video contains physiological information such as head movement, eye blinking, and lip movement, which are very different from living human faces. Large commonality, thus poses a great threat to the security of the identification system. [0003] So far, there are not many studies on live face detection technology, mainly including three-dimensional depth estimation, facial expression changes, optical flow, spectrum, blink detection and other analysis ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
Inventor 潘纲吴朝晖孙霖
Owner 浙江浙大西投脑机智能科技有限公司
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