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

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...

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 utilizes the image after denoising, and uses the LBP method to replace the standard deviation method for extracting image features

Images