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

- M. Ramalho; 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 .

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.