Metaheuristic Optimization Algorithms Based Feature Selection for Fingerprint Image Classification

Abstract

Fingerprint biometric plays a vital role to authenticate a person in a right way. Fingerprint classification is crucial which reduces the search time of a large database while authentication. In this research work, a novel fingerprint image classification system is proposed with the exploit of metaheuristic optimization based feature selection methods. It involves four main tasks: pre-processing, feature extraction, feature selection, and classification. Initially, the fingerprint is denoised using undecimated wavelet transform. Then, a set of rich discriminate Local Binary Pattern (LBP) features are extracted from the enhanced image. Metaheuristic models such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO) are studied for feature selection. Finally, the fingerprint images are classified using Back Propagation Neural Network (BPN). In this research, experiments have been conducted on real-time fingerprint images collected from 150 subjects each with ten orientations using eSSL ZK7500 fingerprint sensor and also on the NIST-4 dataset. The experimental results are compared in terms of Precision, Recall, F-measure, Accuracy, and Error rate with other benchmark classification techniques such as Support Vector Machine (SVM) and Multi Layer Perceptron (MLP), to conclude the efficacy of the proposed approach.