Living body detection method and apparatus based on active state of human eye region

A human eye area and human eye detection technology, which is applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of video counterfeiting attacks and achieve the effect of preventing video counterfeiting attacks

Active Publication Date: 2015-12-09
CHINA THREE GORGES UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem that the existing living body detection technology is ineffective against video counterfeiting attacks,

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
  • Living body detection method and apparatus based on active state of human eye region
  • Living body detection method and apparatus based on active state of human eye region
  • Living body detection method and apparatus based on active state of human eye region

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0050] Example 1

[0051] figure 1 This is a flowchart of a method for detecting a living body based on the activity state of the human eye area provided in Embodiment 1 of the present invention. The execution subject of this embodiment is an electronic device. See figure 1 , the method includes:

[0052] 101: Perform human eye detection on the real-time video image according to the scale equalization algorithm, the face detection algorithm and the human eye detection algorithm to obtain the human eye area;

[0053] The scale equalization algorithm is an algorithm in which windows of different preset scales are traversed in images with different preset frame numbers. The preset size is the size of face detection. For example, the preset size can be 10×10, 20×20, 30×30, etc. Preferably, the preset size is 30×30. The preset number of frames is the number of image frames required for face detection. For example, the preset number of frames is 1, 2, 3, etc., preferably, the pre...

Example Embodiment

[0089] Embodiment 2

[0090] figure 2 It is a flowchart of a method for detecting a living body based on the activity state of the human eye region provided in the second embodiment of the present invention. When the random eye movement instruction is to move left or right, refer to figure 2 , the method includes:

[0091] 201: Perform face detection on the real-time video image according to the scale equalization algorithm and the face detection algorithm to obtain a face area;

[0092] The scale equalization algorithm is an algorithm in which windows of different preset scales are traversed in images with different preset frame numbers. The face detection algorithm needs to traverse all scales for each frame of image, which increases the computational load of electronic equipment and affects the real-time processing performance of face detection. The scale equalization algorithm evenly distributes all the scales in the face detection algorithm to multiple frames of imag...

Example Embodiment

[0110] Embodiment 3

[0111] image 3 This is a flowchart of a method for detecting a living body based on the activity state of the human eye region provided in Embodiment 3 of the present invention. When the random eye action instruction is to close the eyes, refer to image 3 , the method includes:

[0112] 301: Perform face detection on the real-time video image according to the scale equalization algorithm and the face detection algorithm to obtain a face area;

[0113] The scale equalization algorithm is an algorithm in which windows of different preset scales are traversed in images with different preset frame numbers.

[0114] For the implementation process of this step, reference may be made to step 201 in the second embodiment, and details are not repeated here.

[0115] 302: Perform human eye detection according to the human eye detection algorithm and the face region to obtain the human eye region;

[0116] For the implementation process of this step, reference...

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 present invention discloses a living body detection method and apparatus based on an active state of a human eye region, and belongs to the computer application field. The method comprises: carrying out human eye detection on real-time video images according to a scale equalization algorithm, a human face detection algorithm and a human eye detection algorithm to obtain a human eye region; carrying out human eye tracking according to an LK tracking algorithm, the human eye region and the real-time video images to obtain human eye characteristic points and real-time coordinate information of the human eye characteristic points; after sending a random eye action instruction to a user, carrying out human eye tracking on the real-time video images according to the LK tracking algorithm, the human eye characteristic points and the real-time coordinate information of the human eye characteristic points to obtain a preset number of frames of real-time human eye regions; and determining whether the user is alive according to the living body detection method and the preset number of frames of real-time human eye regions. According to the living body detection method and apparatus provided by the present invention, by means of the human eye tracking and the random eye action instruction, the living body detection can be performed effectively, thereby preventing an attack caused by a faking video.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to a method and device for detecting a living body based on the activity state of a human eye region. Background technique [0002] With the continuous development of biometric recognition technology, face recognition technology is widely used in identity authentication systems. However, the identity authentication system based on face recognition technology cannot identify non-living information such as photos or videos, and uses photos or videos to substitute real living bodies for counterfeiting and deception, which poses a serious threat to the security of the identity authentication system. Aiming at the problem of counterfeiting and deception in face recognition technology, liveness detection has become an important technology to distinguish whether the current user participating in the authentication is alive or not. [0003] In the prior art, a living body detection tec...

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
CPCG06V40/18
Inventor 徐光柱刘鸣尹潘龙雷帮军李春林
Owner CHINA THREE GORGES 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