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

Finger vein image feature extraction method combined with sobel and mfrat

An image feature extraction and finger vein technology, which is applied in biometric recognition, character and pattern recognition, instruments, etc., can solve the problems of poor image quality of finger vein database and inability to extract edge information of finger vein images well. Achieve the effect of good time performance, low error rate, and high recognition rate

Active Publication Date: 2021-11-12
ANHUI UNIVERSITY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the poor image quality of the finger vein library used in the experiment, the original differential excitation operator cannot extract the edge information that can best represent the image features in the finger vein image; the original direction operator cannot be very good. Good extraction of discriminative line features in 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 feature extraction method combined with sobel and mfrat
  • Finger vein image feature extraction method combined with sobel and mfrat
  • Finger vein image feature extraction method combined with sobel and mfrat

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0048] The present invention uses finger vein databases respectively from Tianjin Key Laboratory of Intelligent Signal and Image Processing and Malaysian Polytechnic University. The finger vein library (FV-TJ) of the Tianjin experiment contains 64 categories of 15 samples, a total of 64*15 samples, and all samples have been extracted by region of interest (ROI). The finger vein library (FV-USM) of the University of Technology in Malaysia contains 492 categories of 6 samples in total, 492*6 samples, and all samples have been processed by ROI extraction and scale normalization (image size is 300×100pixel).

[0049] We take the samples in the FV-TJ finger vein bank as an example, and follow the figure 1 The flow chart shown is for feature extraction.

[0050] Step 1: Perform scale normalization processing on the input image, and unify the image siz...

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 image feature extraction method combining Sobel and MFRAT. First, Sobel operator combined with Weber's law is used to calculate the differential excitation characteristics of finger vein samples; then MFRAT is used to extract the direction characteristics of samples; finally, SMWLD is obtained by combining the two by constructing a two-dimensional joint distribution histogram. Apply the proposed feature extraction method to finger vein image recognition, and conduct comparative experiments in two public finger vein image databases at home and abroad, and use Euclidean distance for matching. The experimental results show that, compared with other similar methods, this application's The method has higher recognition rate and lower equal error rate, and the highest recognition rate reaches 100% and 99.729% respectively.

Description

technical field [0001] The invention belongs to the field of biological feature recognition, in particular to a finger vein image feature extraction method combining Sobel and MFRAT. Background technique [0002] As personal information security issues are paid more and more attention to, identification technologies based on biometrics, such as fingerprints, faces, and irises, have also received more and more attention. Compared with other biometric-based identification methods, finger vein recognition has gradually become a hot topic in the field of biometrics due to its advantages such as simple collection equipment, safe living body recognition and high recognition rate. [0003] Feature extraction is a key step in vein recognition, and the quality of feature extraction will have a great impact on the recognition effect. At present, there are two main types of feature extraction methods commonly used in finger vein recognition: the first type is based on subspace methods...

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): G06K9/00G06K9/46
CPCG06V40/10G06V10/443
Inventor 王华彬曹伟王东旭朱颜羊代风黄汉文符春兰丁一军陶亮
Owner ANHUI UNIVERSITY