An automatic computer authentication method for photographic faces and living faces

A computer and photo human technology, applied in the field of identification of photo human faces and living human faces, can solve problems such as influence

Active Publication Date: 2008-07-09
ZHEJIANG UNIV
View PDF0 Cites 66 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

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
  • An automatic computer authentication method for photographic faces and living faces
  • An automatic computer authentication method for photographic faces and living faces
  • An automatic computer authentication method for photographic faces and living faces

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The computer automatic identification method of photograph human face and live human face of the present invention, its step is as follows (as shown in Figure 1):

[0033] 1. Face detection and eye positioning:

[0034] For each frame of the input video, the center of the eye needs to be located first. The method of detecting the position of the face first, and then further locating the center of the eyes on the intercepted face picture is adopted.

[0035] Combining Haar similar features with the cascaded Adaboost method, the face position is detected for 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 fea...

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 a computer automatic identification method of photo face and live face, which comprises the following steps: (1) performing face detection and eye location; (2) capturing an eye area; (3) calculating an opening-closing level of the eyes in a normalized image; (4) establishing a model for judging wink actions through applying conditional random field theory; (5) processing each frame image in an unidentified video as per steps (1) to (3), and judging whether the wink action exists in the unidentified video through applying the model and the reasoning method of the conditional random field theory in the step (4), thereby completing the automatic identification of the photo face and the live face. The invention realizes the computer automatic identification of the photo face and the live face with a single camera head.

Description

technical field [0001] The invention relates to a method for discriminating between photographic human faces and living human faces. 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 using a legitimate user's photo, and attack the liveness detection method in the face recognition system through the folding, translation, rotation and other movements of the photo , thus posing 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 and other analysis methods. However, some of these methods require the movement of the user's head or face, while others are greatly affected by external environment...

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): G06K9/00
Inventor 吴朝晖潘纲孙霖
Owner ZHEJIANG UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap