Human body vein image feature extraction method

A vein image and feature extraction technology, which is applied in the field of identity recognition, can solve problems such as redundant information, insufficient identification information, and difficult selection of Gabor filter parameters, and achieve the best experimental results and the effect of eliminating noise

Inactive Publication Date: 2014-10-08
GUANGDONG WICROWN INFORMATION TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, filters such as Gabor filters and Gaussian filters will generate more redundant information or insufficient identification information, which will increase the computational complexity and storage burden of the algorithm, and will reduce the recognition efficiency and accuracy of the algorithm. The parameter selection is also difficult

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
  • Human body vein image feature extraction method
  • Human body vein image feature extraction method
  • Human body vein image feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A method for extracting features of a human vein image provided in this embodiment includes collecting and establishing a human vein image into a coordinate system, and then extracting vein direction features through a direction filter. The method of extracting vein direction features through a direction filter is adopted Radon transform performs convolution operation on the image established in the coordinate system to extract vein image features. The overall process of feature extraction is as follows:

[0036] (1) Set the distance function:

[0037] d = round ( ( i - i 0 ) 2 + ( j - j ...

Embodiment 2

[0047] The feature extraction method of a human vein image provided in this embodiment, in order to conform to the neighborhood of the distance function, and ensure that the number of pixels contained in the k direction filter is the same, and use as few directions as possible, ensure that the direction Recognition degree, extract as much direction information as possible to improve the recognition rate, when constructing k directions, select six direction intervals, of which:

[0048] Direction 0 is 0 degrees;

[0049] The angle of direction 1 belongs to the interval [30, 31.875], that is, ((22.5+30) / 2+(30+45) / 2) / 2=31.875;

[0050] Direction 2 is within the interval [58.125, 60], that is, ((45+60) / 2+(60+67.5) / 2) / 2=58.125;

[0051] Direction 3 is 90 degrees;

[0052] Similarly, direction 4 is within the [120, 121.875] degree interval;

[0053] Direction 5 is within the interval [148.125, 150].

[0054] The above scheme meets the following two objectives 1 and 2:

[0055] ...

Embodiment 3

[0067] The feature extraction method of a human vein image provided in this embodiment is to extract more direction information that is more in line with the real structure of the vein, perform a direction index operation on the image after the convolution operation, and generate a response image, that is, the direction map feature matrix , and convert the direction index into log 2 (K) the number of bits; the final pattern feature matrix is ​​used as a database template to construct a vein database.

[0068] The pattern feature matrix is ​​expressed as:

[0069] Energy [ L k ] = Σ ( i , j ) ∈ L k f [ i , j ]

[0070] In the collect...

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 human body vein image feature extraction method which comprises the steps of acquiring a human body vein image and establishing the image in a coordinate system, and then extracting the vein direction features through a directional filter. The method is characterized in that vein direction feature extraction through the directional filter is realized by performing convolution operation on the image established in the coordinate system by use of Radon transform to extract the features of the vein image. The whole feature extraction process comprises the following steps: (1) setting a distance function, which is shown in the description; (2) setting a neighborhood consistent with the distance function and dividing the neighborhood into k directions: Lk={(i, j):j=k(i-i0)+j0, i belongs to Zp}, wherein (i, j) belongs to local(i0, j0); and (3) calculating the energy response of the k directions according to a formula in the description. By adopting the human body vein image feature extraction method of the invention, excessive redundant information is removed, the complexity of calculation and the amount of calculation are reduced, more effective information can be contained, and the effective range of the filter neighborhood is determined through construction of the distance function so as to get a better identification effect.

Description

technical field [0001] The invention relates to an identification technology for identifying the identity of a human body by distinguishing vein features, in particular to a method for extracting features of a human vein image. Background technique [0002] In the field of human identification technology, from single fingerprint identification to biometric identification, from iris technology to palm vein technology in biometric identification, everything is constantly developing and improving. In the process of image feature extraction and processing of palm veins, different extraction and processing methods bring different results, which directly affects the accuracy and singleness of identity recognition. With the research on the characteristics of human veins, it is found that not only the palm veins, but also the distribution of veins in different people have different changes. How to effectively extract the features of the extracted vein images to obtain accurate indiv...

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): G06K9/00G06K9/46
Inventor 周宇佳刘娅琴卢慧莉黄振鹏於巧红聂为清詹恩毅陈志刚
Owner GUANGDONG WICROWN INFORMATION TECH
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