A Finger Vein Recognition Method Based on Two-dimensional Gaussian Maximum Curvature

A finger vein and maximum curvature technology, applied in the field of biometric identification and information security, can solve the problems of poor accuracy of vein lines and achieve high accuracy

Active Publication Date: 2020-07-24
HANGZHOU DIANZI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] For low-quality finger vein images, in order to solve the problem of poor accuracy of vein lines extracted by the existing Garbor filter, direction group filter and maximum curvature algorithm, the present invention provides a method for identifying finger veins based on two-dimensional Gaussian maximum curvature

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 Based on Two-dimensional Gaussian Maximum Curvature
  • A Finger Vein Recognition Method Based on Two-dimensional Gaussian Maximum Curvature
  • A Finger Vein Recognition Method Based on Two-dimensional Gaussian Maximum Curvature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0059] The finger vein quick identification method of the present embodiment comprises the following steps:

[0060] S1. Construct a two-dimensional Gaussian function template G(x, y) with a window of (2×8+1)×(2×8+1), where x∈[-8,8], y∈[- 8,8], σ=2, w=8.

[0061] S2. According to the Gaussian function G(x, y) constructed in step S1, the first-order derivative G of the two-dimensional Gaussian function in the horizontal direction is respectively obtained x (x,y), the first derivative G in the vertical direction y (x,y), the second-order partial derivative G in the horizontal direction xx (x,y), the second-order partial derivative G in the vertical direction yy (x,y) and the second-order mixed partial derivative G xy (x,y).

[0062] S3, using the results obtained in step S2, to obtain the first-order directional derivative G of the 8 dir...

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 based on two-dimensional Gauss maximum curvature. The present invention first utilizes the maximum curvature algorithm based on the two-dimensional Gaussian function to extract the vein pattern and the curvature space field of the finger vein image, and then utilizes the curvature space field matching recognition of the finger vein image. Experiments show that the accuracy of vein pattern extraction based on the Gaussian curvature space field is higher, and the recognition algorithm based on the curvature space field has significantly higher recognition performance than the traditional MHD recognition algorithm under a certain false recognition rate. For low-quality finger vein images, the present invention proposes to extract vein features from 8 directions, which can extract vein information more clearly than the original maximum curvature method to extract vein features from 4 directions. The performance degradation of the recognition algorithm based on the curvature space field of the vein image proposed by the present invention is not obvious. Information that better characterizes the finger veins.

Description

technical field [0001] The invention belongs to the technical field of biological feature identification and information security, and in particular relates to a finger vein identification method based on two-dimensional Gaussian maximum curvature. Background technique [0002] Finger vein recognition technology is a new biometric recognition technology, which uses finger vein recognition technology as one of the most advanced emerging second-generation biometric technologies, because of its high security level, high stability, strong universality and The convenience of acquisition equipment has become a research hotspot of many scholars at home and abroad. Finger vein recognition technology mainly includes collecting finger vein images, image preprocessing, feature extraction and matching recognition. At present, when collecting finger vein images, the acquisition equipment is unstable, the veins in the fingers shrink in the low temperature environment, and some girls have...

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
CPCG06V40/10G06V40/14
Inventor 沈雷李小刚张严严蓝师伟
Owner HANGZHOU DIANZI 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