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

Feature extraction method for low-quality finger vein images

A feature extraction, finger vein technology, applied in the field of low-quality finger vein image recognition, can solve the problems of unfavorable matching rate, less feature information, ignoring the effective information of non-vein features of the image, etc., to increase edge information and background information, improve Matching rate, the effect of reducing false matching rate

Active Publication Date: 2022-07-22
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, methods based on vein networks usually rely on finger vein segmentation algorithms, and also ignore some effective information such as non-vein features of the image, such as finger edges and finger thickness.
For low-quality images, less feature information is often extracted, which is not conducive to improving the matching rate

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
  • Feature extraction method for low-quality finger vein images
  • Feature extraction method for low-quality finger vein images
  • Feature extraction method for low-quality finger vein images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings.

[0030] The present invention is a feature extraction method for low-quality finger vein images. In the preprocessing link, in view of the serious displacement of the finger vein image, and the direct cropping of the image will lose part of the information, the present invention introduces the replacement displacement method to displace the image. Considering the insufficiency of the local pattern method and the vein network method, the present invention proposes to extract the PBBM feature by stacking on the basis of extracting the MCM feature of the image. Therefore, clearer finger vein features can be extracted while retaining the full image information, and the recognition accuracy of low-quality images can be effectively improved.

[0031] The main steps of this method are as follows:

[0032] Step 1: Image preprocessing.

[00...

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

In the feature extraction method for low-quality finger vein images, in the preprocessing link, since the finger vein images are seriously shifted, and part of the information will be lost by directly cropping the images, the invention introduces the replacement displacement method to shift the images. Considering the shortcomings of the local pattern method and the vein network method, the present invention proposes to extract the PBBM feature by stacking on the basis of extracting the MCM feature from the image. Therefore, clearer finger vein features can be extracted while retaining the full image information, and the recognition accuracy of low-quality images can be effectively improved.

Description

technical field [0001] The invention is a feature extraction method for low-quality finger vein images, belongs to the field of biological feature identification, and mainly solves the identification problem of low-quality finger vein images. Background technique [0002] Finger vein recognition is a technology that uses images of blood vessels under the skin of a finger for personal identification. The vein pattern structure of fingers is complex, and the vein pattern can only be captured in the living body, and it is not easy to copy or forge veins. In addition, veins are surrounded by skin, and it is difficult for external factors to change the growth structure of veins, such as wet, greasy, and worn fingers. In addition, finger veins have the advantages of uniqueness, universality and measurability. Therefore, finger vein biometrics is a very safe and reliable technology. [0003] In finger vein recognition, there are mainly finger vein image acquisition, preprocessin...

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): G06V40/10G06V10/44G06V10/74G06V10/774G06V10/764G06K9/62
CPCG06V40/10G06V40/14G06V10/443G06F18/24G06F18/214
Inventor 郭剑李蓉刘星利穆恒宇成洋王菁韩崇王娟
Owner NANJING UNIV OF POSTS & TELECOMM
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