Unlock instant, AI-driven research and patent intelligence for your innovation.

Finger vein image quality evaluation method and system thereof

A quality evaluation and image quality technology, applied in the field of identity recognition, can solve the problems of inability to comprehensively evaluate the image quality of finger veins, and achieve accurate and reasonable evaluation

Inactive Publication Date: 2018-05-08
SHENZHEN CASTLE SECURITY TECH CO LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Weighting is a linear model and has significant limitations in reflecting nonlinear problems
However, a single feature cannot comprehensively evaluate the quality of finger vein images.

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
  • Finger vein image quality evaluation method and system thereof
  • Finger vein image quality evaluation method and system thereof
  • Finger vein image quality evaluation method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] A method and system for evaluating finger vein image quality of the present invention will be described with reference to the accompanying drawings.

[0066] figure 1 Shown is a flowchart of a finger vein image quality evaluation method of the present invention, the method includes the following steps:

[0067] A1: Read finger vein data and obtain the quality score of the finger vein data image;

[0068] A2: Extract quality evaluation features from finger vein data;

[0069] A3: Based on the quality scores and quality evaluation features obtained in the above steps, an SVR (Support Vector Regress ion) model is obtained, and the SVR model is used to evaluate and screen the image quality.

[0070] Preferably, the quality evaluation features extracted from finger vein data in the step A2 include local features and global features;

[0071] The local features include image contrast, spatial gradient and Gabor-based features;

[0072] The global features include image information capaci...

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 provides a finger vein image quality evaluation method and a system thereof. The method comprises the following steps: A1, finger vein data are read, and the quality score of the fingervein data image is acquired; A2, quality evaluation characteristics are extracted from the finger vein data; and A3, based on the quality score and the quality evaluation characteristics acquired in the above steps, a SVR (Support Vector Regression) model is obtained, and the SVR model is adopted to evaluate and screen the image quality. According to the finger vein image quality evaluation methodand the system thereof, the purpose of accurate recognition is achieved through a new quality score-based finger vein image quality evaluation method.

Description

Technical field [0001] The invention relates to the technical field of identity recognition, in particular a method and system for evaluating the quality of finger vein images. Background technique [0002] With the rapid development of science and technology, people are gradually released from various documents in daily life. The traditional identity authentication method is to use (key, ID card) and password for identity authentication, but these methods are easy to be Forgery or forgetting, compared with traditional identity authentication, each person's biological characteristics are unique, no need to remember, and cannot be forged. [0003] The finger is one of the important organs for humans to perceive the external world. The finger veins under the skin of the finger are the biological characteristics of the living body. Practice shows that no two people in the world have the same finger veins. Compared with the fingerprints of the fingers, Finger veins are difficult to fo...

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 Applications(China)
IPC IPC(8): G06T7/00
Inventor 唐忞旻龙安川曾尧张燕妮
Owner SHENZHEN CASTLE SECURITY TECH CO LTD