Fingerprint Recognition Using Translation Invariant Scattering Network

TL;DR

This paper introduces a fingerprint recognition method using a scattering transform network combined with PCA and SVM, achieving high accuracy on a standard database.

Contribution

It applies a predefined wavelet-based scattering network for fingerprint feature extraction, enhancing recognition performance over traditional methods.

Findings

Achieved 98% accuracy on a standard fingerprint database

Demonstrated effectiveness of scattering features for fingerprint recognition

Combined scattering transform with PCA and SVM for improved results

Abstract

Fingerprint recognition has drawn a lot of attention during last decades. Different features and algorithms have been used for fingerprint recognition in the past. In this paper, a powerful image representation called scattering transform/network, is used for recognition. Scattering network is a convolutional network where its architecture and filters are predefined wavelet transforms. The first layer of scattering representation is similar to sift descriptors and the higher layers capture higher frequency content of the signal. After extraction of scattering features, their dimensionality is reduced by applying principal component analysis (PCA). At the end, multi-class SVM is used to perform template matching for the recognition task. The proposed scheme is tested on a well-known fingerprint database and has shown promising results with the best accuracy rate of 98\%.