Fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination)

A feature selection and detection method technology, applied in the field of true and false detection of fingerprint images, can solve problems such as poor reliability, and achieve the effect of improving reliability and short training time

Active Publication Date: 2015-02-18
HANGZHOU JINGLIANWEN TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To overcome the disadvantages of poor reliability of the existing false fingerprint detection method, the present invention

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
  • Fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination)
  • Fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination)
  • Fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] refer to figure 1 , a kind of false fingerprint detection method based on SVM-RFE feature selection, described false fingerprint detection method comprises the following steps:

[0048] 1) Image cutting:

[0049] F(X,h,w)

[0050] Among them, F represents the cutting function, and X, h, and w are the independent variables of F. The respective meanings are: X is the original fingerprint image, and h, w are the height and width of the fingerprint image after cutting.

[0051] The cutting function F is for the training and testing library, and it cuts off the background blank area with the fingerprint area as the center. If most of the fingerprint background areas in a fingerprint library are too large (over 50% is considered to be too large), the fingerprint image of this library is cut, otherwise it is not cut. The cutting size h and w can be estimated in adv...

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

A fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination) includes the following steps: 1), segmenting an image; 2), extracting features; 2.1), performing discrete wavelet transform, 2.2), denoising by a hyperbolic shrinkage method; 2.3), performing wavelet reconstruction to acquire a denoised image; 2.4), differencing the original image with the denoised image to acquire a noise image; 2.5), respectively performing block-based LBP (local binary pattern) feature extraction on the denoised image and the noise image; 2.6), normalizing block features, and connecting the block features in series to acquire final fingerprint features; 3), selecting the features; 4), training to acquire a classifier. Compared with conventional methods of detecting fake fingerprints only by image noises, the fake fingerprint detection method has the advantages that the denoised image is utilized, an LBP method substitutes for a standard deviation method to extract the features, and an SVM-RFE feature selection method is introduced, ineffective and redundant features are eliminated effectively, and accordingly, reliability in fake fingerprint detection is improved.

Description

technical field [0001] The invention relates to technical fields such as image processing, machine learning, pattern recognition, and feature selection, in particular to a method for authenticity detection of fingerprint images. Background technique [0002] Image processing, feature extraction, feature selection, classifier training, and image classification are important links in fake fingerprint detection methods. [0003] With the development of automatic fingerprint identification technology, fingerprints, as the most reliable way of identity authentication, have been widely used in criminal investigation, border inspection, household registration management, medical and health care, access control, and in various fields such as banking, finance, and social insurance. However, some criminals use cheap materials to forge fingerprints to easily deceive many current fingerprint identification systems, obtain illegal benefits, disrupt the investigation line of sight, and br...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/1347G06V40/1365
Inventor 张永良谢瑜方珊珊
Owner HANGZHOU JINGLIANWEN 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