Author : Kushalatha.M.R. and Ambika.D.R.

Biometric crypto systems are being increasingly deployed in many large-scale biometric applications because they have several advantages such as lower error rates, larger population coverage, offers facility, comfort and more security to users. However in biometric Systems where the user database is stored is vulnerable to several type of attacks. As to protect these databases from attacks efficient encryption and decryption methods have to be used. The generation of direct key using these databases is also of importance. In this paper, extraction of features of face images like mouth region, eyes are done using AdaBoost Algorithm and a database is generated out of these segmented features. We also present various methods that monolithically bind a cryptographic key with the biometric templates of a user stored in the database in such a way that the key cannot be revealed without a successful biometric authentication. We illustrate the challenges involved in biometric feature recognition primarily due to drastic acquisition variations in the representation of a biometric identifier and the imperfect nature of biometric feature extraction and matching algorithms.

Keywords: Adaboost, Biometric Cryptosystems, Elliptical Curve Cryptography, K- Means Algorithm

Article published in International Journal of Current  Engineering  and Technology, Vol.4,No.3 (June- 2014)