Fingerprint Recognition Based on Wavelet Transform and Ensemble Subspace Classifier

Abstract

This paper presents a fingerprint recognition system based on Wavelet transform, multiple domain feature extraction, and Ensemble Subspace Discriminant Classifier. The main contribution of this work is the computation of a set of features that can be used for the classification of fingerprints, and the implementation of an ensemble of discriminant classifiers. First, the review of previous works is presented. Next, a detailed description of the proposed method is elaborated. Finally, it is shown that the proposed system provides the highest accuracy (97.5%) in comparison with other works proposed in the literature using a different type of classifier such as the ensemble subspace discriminant.