Stereo-Hyperspectral Face Recognition Method Based on Polar Imaging

A face recognition and hyperspectral technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of poor stability of recognition results and low recognition efficiency, achieving high stability and improving efficiency

Active Publication Date: 2019-04-23
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the defects in the above-mentioned prior art, and propose a stereo-hyperspectral face recognition method based on polar imaging, which is used to solve the problems of poor stability of recognition results and problems in existing multispectral face recognition methods. Identify technical issues with low productivity

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
  • Stereo-Hyperspectral Face Recognition Method Based on Polar Imaging
  • Stereo-Hyperspectral Face Recognition Method Based on Polar Imaging
  • Stereo-Hyperspectral Face Recognition Method Based on Polar Imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0028] Reference figure 1 , A stereo-hyperspectral face recognition method based on polar imaging, including the following steps:

[0029] Step 1. Use hyperspectral imaging system to collect face data, such as figure 2 As shown, the two-dimensional polar image of the face in each spectral band and the spectral information corresponding to the pixels on the two-dimensional polar image are obtained. Collecting the face data of each spectral band can more comprehensively reflect the facial features and make the recognition result more accurate;

[0030] Step 2: Filter out the polar images corresponding to the three spectral bands with high quality scores from the acquired two-dimensional polar images of the face, fuse the selected three polar images, and perform affine on the fused polar images Transform, extract the radial lines (polar lines) in the fused polar im...

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 proposes a method for stereo-hyperspectral face recognition based on polar imaging, which is used to solve the technical problems of poor stability of recognition results and low recognition efficiency in existing multi-spectral face recognition methods, including the following steps, 1. Use the polar spectrum system to collect face information; 2. Perform three-dimensional reconstruction of the face according to the two-dimensional polar image in the face information; Face and face spectral information are divided into regional blocks; 4. Extract the comprehensive feature vector of the regional block; 5. Use steps 1 to 4 to obtain sample library data and face data to be recognized for multiple faces and faces to be recognized respectively 6. Obtain a classifier from the data in the training sample database; 7. Input the face data to be recognized into the classifier, and recognize the face. The invention has the characteristics of good stability and high recognition efficiency, and can be used for identity verification in financial transactions, security defense, customs clearance and security inspection, etc.

Description

Technical field [0001] The invention belongs to the technical field of biometric recognition, and relates to a face recognition method, in particular to a stereo-hyperspectral face recognition method based on polar imaging, which can be used for identity identification in financial transactions, security defense, customs clearance, and the like. Background technique [0002] There are 6.7 billion humans with different looks and skin colors inhabited in the world. As an important biological feature, the human face plays an important role in the communication between people. In today's society, human faces have become an important feature for identification. Face recognition systems can be divided into three types according to their functions: security-oriented, management and supervision, and multimedia entertainment. The requirements for recognition accuracy are also reduced. According to reports, hundreds of millions of dollars in government welfare funds are illegally taken in...

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
CPCG06V40/172G06V40/171
Inventor 吴鑫张建奇刘鹏飞杨琛
Owner XIDIAN 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