On The Power of Joint Wavelet-DCT Features for Multispectral Palmprint Recognition

TL;DR

This paper introduces a novel palmprint recognition method combining wavelet and DCT features, achieving near-perfect accuracy by applying PCA and majority voting on multispectral data.

Contribution

It presents a new feature extraction approach using joint wavelet-DCT features for palmprint recognition, outperforming previous methods.

Findings

Achieved 99.97-100% accuracy on multispectral palmprint database.

Demonstrated the effectiveness of combined wavelet and DCT features.

Outperformed all previous similar-condition methods.

Abstract

Biometric-based identification has drawn a lot of attention in the recent years. Among all biometrics, palmprint is known to possess a rich set of features. In this paper we have proposed to use DCT-based features in parallel with wavelet-based ones for palmprint identification. PCA is applied to the features to reduce their dimensionality and the majority voting algorithm is used to perform classification. The features introduced here result in a near-perfectly accurate identification. This method is tested on a well-known multispectral palmprint database and an accuracy rate of 99.97-100\% is achieved, outperforming all previous methods in similar conditions.