Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A finger vein recognition method and device based on deep correlation feature learning

A technology of feature learning and identification method, applied in the field of biometric identification, can solve the problem of inability to accurately identify thin veins, achieve good economic and social benefits, improve identification accuracy, and strong identification performance.

Active Publication Date: 2021-02-02
INSPUR GROUP CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it cannot effectively identify finer veins accurately, establish correlation information between detail points, and ensure strong recognition performance.

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 finger vein recognition method and device based on deep correlation feature learning
  • A finger vein recognition method and device based on deep correlation feature learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] as attached figure 1 As shown, the finger vein recognition method based on deep correlation feature learning of the present invention, the specific steps are as follows:

[0041] S1. Extract minutiae points: extract minutiae points of finger veins; the specific steps are as follows:

[0042] S101. For a pair of finger vein images, segment the lines of the finger veins with a linear tracking method, and perform binarization processing to obtain a binary image;

[0043] S102. Thinning the segmented binary image to obtain a thinned image, and extracting detail points of the entire finger vein based on the thinned image. Wherein, the minutiae points include intersections and endpoints of the finger vein thinning image.

[0044] S2. Construct graph nodes: Construct the graph structure of finger veins according to the minutiae points; the specific content is as follows: extract the features of the minutiae points, and use the relevant feature vectors corresponding to the mi...

Embodiment 2

[0054] as attached figure 2 As shown, the finger vein recognition device based on deep correlation feature learning of the present invention includes,

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 finger vein recognition method and device based on deep correlation feature learning, which belongs to the field of biometrics. The technical problem to be solved by the invention is how to effectively and precisely identify finer veins, and establish the relationship between detail points. Relevance information to ensure strong recognition performance. The technical solution adopted is: ①The steps of the method are as follows: S1. Extract detail points; S2. Build graph nodes; S3. Learn correlation map: correlation based on RankSVM Graph mapping learning method, obtaining the adjacency matrix of the correlation graph, reflecting the correlation information between graph nodes; S4, deep correlation feature learning; S5, matching: combining the obtained effective deep correlation features with the templates stored in the database Perform similarity comparison to complete the matching task. ② The device includes a minutiae point extraction module, a graph node construction module, a correlation map learning module, a deep correlation feature learning module, and a matching module.

Description

technical field [0001] The invention relates to the field of biological identification, in particular to a method and device for identifying finger veins based on deep correlation feature learning. Background technique [0002] With the progress of society, technology in various fields has made great progress. Biometric identification technology uses human biological characteristics or behavioral characteristics for human identity authentication. Among them, human biological characteristics mainly include two categories: external biological characteristics and internal biological characteristics. External biometrics such as fingerprints, iris vision, and face shape. Internal biometrics such as finger veins etc. Finger vein recognition is an emerging biometric technology with great potential. It has the advantages of internal features and living body recognition, and has attracted more and more researchers and developers' attention. Feature extraction is a key part of vein...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/10G06V40/14G06N3/045G06F18/2411
Inventor 于治楼计晓贇袭肖明
Owner INSPUR GROUP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com