DEVELOPMENT OF VISUAL CRYPTOGRAPHIC SYSTEM FOR EAR BIOMETRIC TEMPLATE SECURITY

Abstract

Identity theft is a growing concern in this age of digital technology and applications. Traditional authentication methods such as passwords, passphrases, identity documents and the like are not sufficient to combat this menace. Biometrics lends itself as a better and alternative security measure to fight this problem. However, a major challenge to biometric system is the insecurity of biometric templates stored in the database. As a panacea to the vulnerability of templates stored in the database, a secret sharing scheme for images known as visual cryptography is proposed. A wavelet compression scheme known as set partitioning in hierarchical tree (SPIHT) was applied in order to compress the captured biometric data and, principal component analysis was then applied in order to extract the essential biometric features before splitting using a 2-out-of-2 visual cryptographic scheme. The subject whose biometric data is being processed also hold a noise like portion of the template. Compromise through attacks on the database becomes difficult without the cooperation of the subject under investigations. A series of experiments are carried out using different wavelet families upon cropped ear patterns and sample faces of selected students of Federal Polytechnic, Offa. The Daubechies (db) wavelet gave the best results with an average mean square error (MSE) of 1.47 and peak signal to noise ratio (PSNR) of 46.46. A robust visual cryptographic scheme that is fast, secured with minimal loss of resolution was developed.