Creating and sharing knowledge for telecommunications

Feature Vector Binarization: A Quantization-Based Approach to a Secure Biometric System

Ramalho, M. ; Correia, P.L. ; Soares, L. D.

Feature Vector Binarization: A Quantization-Based Approach to a Secure Biometric System, Proc Portuguese Conf. on Pattern Recognition - RecPad, Vila Real, Portugal, Vol. ., pp. . - ., October, 2010.

Digital Object Identifier:

Abstract
In this paper, a biometric template protection scheme is proposed. The scheme can be described by three essential modules: binarization, error-correcting code (ECC) and cryptographic hash function. Both ECC and cryptographic hash function require a binary representation of the biometric template. If the templates contain real-valued features, an additional step of binarization is necessary. The proposed Feature Vector Binarization (FVB) scheme relies on a quantizer that is applied to each real-valued feature in a biometric template, to convert into a binary string. All binary strings are then concatenated to form a fixed-length binary template that can be processed by an ECC and hashed to guarantee its privacy. A palmprint identification system is implemented for testing purposes, using the UST hand image database, with promising results.