Privacy Preserving using Primary Biometrics and Softbiometrics

Arun Jain, Sukhdev Singh, Anish Soni

Abstract


In many applications, unimodal biometric systems often face significant limitations due to sensitivity to noise, intra class variability, data quality, pressure, dirt, dryness and other factors. Multimodal biometric authentication systems aim to fuse two or more physical or behavioral traits to provide optimal Genuine Acceptance Rate (GAR) Vs Imposter Acceptance Rate (IAR) curve i.e. Receiver‘s Operating Characteristic (ROC). Soft biometrics can be used to improve the performance of traditional biometrics. The equipment used for softbiometric is low in cost and methods are easy to understand. The aim of this paper is to examine whether easily measurable characteristics such as weight, gender etc with the finger geometry and knuckle print can improve the verification process in biometrics. Each biometric trait produces a varied range of scores i.e. heterogeneous scores. Various scores normalization techniques have been developed for fusion of such scores. Whereas this paper presents a technique for producing compatible scores (homogeneous). Decision level AND rule can be used to show the improvement of the combined scheme. This approach is useful for low security requirements. Also use of softbiometrics such as body weight with primary can reduce the Total Error Rate.

 

Keywords: Biometrics verification, fusion, multimodal, softbiometrics, knuckle print.


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v4i10.1883

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science