A Liveness Detection Method Based on Infrared Camera

A technology of living body detection and infrared camera, which is applied to computer parts, instruments, computing, etc., can solve the problems that the camera cannot obtain pupil images, cannot guarantee the time-consuming of living body detection, and cannot defend against headgear attacks, etc., so as to increase the effective working distance. , the effect of reducing the impact and improving the accuracy

Active Publication Date: 2021-05-07
浙江捷汇鑫数字科技有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the current existing technology, "Method and device for living body recognition based on binocular camera-CN201710160685", use binoculars for living body detection, and only when the face is detected in the common light image and the infrared image, the living body detection is performed. The consumption of living body detection It cannot be guaranteed when the light is poor. As long as there is a face detection performance of a camera, the accuracy of liveness detection will inevitably decrease.
"A Liveness Detection Method Based on Blinking under Infrared Camera Device-CN201711204490", the user needs to blink to cooperate when doing liveness detection, and the user experience is not good
"Liveness detection method based on pupil grayscale-CN201810282799", liveness detection is performed with the help of pupil grayscale, when the person is a little far away from the camera or covered by glasses, the camera cannot obtain a clear pupil image, the feasibility of this method is greatly reduced, and it cannot be defended Headgear attacks, this method has relatively large application limitations

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
  • A Liveness Detection Method Based on Infrared Camera
  • A Liveness Detection Method Based on Infrared Camera
  • A Liveness Detection Method Based on Infrared Camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] 2.1. Input an infrared image containing a face and its face detection result.

[0043] 2.2. Align the faces detected according to the standard template to a size of 200*200.

[0044] 2.3. Live detection with infrared human eyes;

[0045] 2.3.1. After deduction and alignment, the human eyes near the tip of the nose in the face image are scaled to 32*32.

[0046]2.3.2. Input the deducted human eyes into the living body detection model model1 to obtain the living body confidence c1, if c1 is greater than the living body threshold t1=0.85 or less than the non-living body threshold t2=0.2, output the living body or non-living body and end, otherwise execute 2.4 .

[0047] 2.4. Liveness detection with infrared face;

[0048] 2.4.1. Scale the aligned face image to 64*64;

[0049] 2.4.2. Input the scaled picture into the living body detection model model2 to obtain the living body confidence c2. If c2 is greater than the living body threshold t3=0.8 or less than the non-liv...

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 living body detection method based on an infrared camera. The present invention aligns face images, uses deep learning methods to extract infrared human eyes and human face features for human face liveness detection, and combines living and non-living multi-threshold strategies for judgment, ensuring that liveness detection takes milliseconds on the premise In this way, the accuracy of liveness detection is improved, the robustness of liveness detection to face angles is enhanced, the user experience of liveness detection is improved, and the application scenarios of liveness detection are increased.

Description

technical field [0001] The invention belongs to the technical field of video monitoring and relates to a living body detection method based on an infrared camera. Background technique [0002] The function of live face detection is to detect whether there is a live face in a picture or video, and to defend against attacks on face recognition-related applications from photos, videos, masks or headgear. Face recognition has been widely used in security, finance and other fields, and face liveness detection is the prerequisite for the application of face recognition. There are many types of non-living bodies, and the application scenarios of face recognition are complex and changeable, which puts forward requirements for the flexibility and adaptability of face liveness detection. Ensuring the accuracy of liveness detection in complex scenes is one of the difficulties of face liveness detection; The high real-time and good user experience requirements of face recognition deter...

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
CPCG06V40/161
Inventor 尚凌辉张兆生王弘玥梅支礼
Owner 浙江捷汇鑫数字科技有限公司
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

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