Feature and computational time reduction on hand biometric system

Abstract

In real-time biometric systems, computational time is a critical and important parameter. In order to improve it, simpler systems are necessary but without loosing classification rates. In this present work, we explore how to improve the characteristics of a hand biometric system by reducing the computational time. For this task, neural network-multi layer Perceptron (NN-MLP) are used instead of original Hidden Markov Model (HMM) system and classical Principal Component Analysis (PCA) procedure is combined with MLP in order to obtain better results. As showed in the experiments, the new proposed PCA+MLP system achieves same success rate while computational time is reduced from 247 seconds (HMM case) to 7.3 seconds.