A Robust Biometrics System Using Finger Knuckle Print

Abstract

Among various biometric indicators, hand-based biometrics has been widely used and deployed for last two decades. Hand-based biometrics are very popular because of their higher acceptance among the population because of their ease of use, high performance, less expensive, etc. This chapter presents a new hand-based biometric known as finger-knuckle-print (FKP) for a person authentication system. FKP are the images obtained from the one's fingers phalangeal joints and are characterized by internal skin pattern. Like other biometrics discrimination ability, FKP also has the capability of high discrimination. The proposed system consists of four modules: image acquisition, extraction of ROI, selection and extraction of features, and their matching. New features based on information theory are proposed for matching. The performance of the proposed system is evaluated using experiment performed on a database of 7920 images from 660 different fingers. The efficacy of the proposed system is evaluated in terms of matching rate and compromising results are obtained.