Palmprint Recognition Using Deep Scattering Convolutional Network

TL;DR

This paper introduces a palmprint recognition method using a deep scattering convolutional network that captures invariant features, reducing preprocessing needs and achieving near-perfect accuracy on a standard database.

Contribution

The paper proposes using a scattering network with predefined wavelet filters for palmprint feature extraction, improving invariance and recognition accuracy over traditional transform domain methods.

Findings

Achieved 99.95% accuracy with minimum-distance classifier.

Achieved 100% accuracy with SVM classifier.

Demonstrated robustness and high accuracy on a standard palmprint database.

Abstract

Palmprint recognition has drawn a lot of attention during the recent years. Many algorithms have been proposed for palmprint recognition in the past, majority of them being based on features extracted from the transform domain. Many of these transform domain features are not translation or rotation invariant, and therefore a great deal of preprocessing is needed to align the images. In this paper, a powerful image representation, called scattering network/transform, is used for palmprint recognition. Scattering network is a convolutional network where its architecture and filters are predefined wavelet transforms. The first layer of scattering network captures similar features to SIFT descriptors and the higher-layer features capture higher-frequency content of the signal which are lost in SIFT and other similar descriptors. After extraction of the scattering features, their dimensionality is reduced by applying principal component analysis (PCA) which reduces the computational complexity of the recognition task. Two different classifiers are used for recognition: multi-class SVM and minimum-distance classifier. The proposed scheme has been tested on a well-known palmprint database and achieved accuracy rate of 99.95% and 100% using minimum distance classifier and SVM respectively.