Cancelable Fusion of Face and Ear for Secure Multi-Biometric Template

Cancelable Fusion of Face and Ear for Secure Multi-Biometric Template

Padma P. Paul (Department of Computer Science, University of Calgary, Calgary, Canada) and Marina L. Gavrilova (Department of Computer Science, University of Calgary, Calgary, Canada)
DOI: 10.4018/ijcini.2013070105
OnDemand PDF Download:
List Price: $37.50


Biometric fusion to achieve multimodality has emerged as a highly successful new approach to combat problems of unimodal biometric system such as intraclass variability, interclass similarity, data quality, non-universality, and sensitivity to noise. The authors have proposed new type of biometric fusion called cancelable fusion. The idea behind the cancelable biometric or cancelability is to transform a biometric data or feature into a new one so that the stored biometric template can be easily changed in a biometric security system. Cancelable fusion does the fusion of multiple biometric trait in addition it preserve the properties of cancelability. In this paper, the authors present a novel architecture for template generation within the context of the cancelable multibiometric fusion. The authors develop a novel cancelable biometric template generation algorithm using cancelable fusion, random projection and transformation-based feature extraction and selection. The authors further validate the performance of the proposed algorithm on a virtual multimodal face and ear database.
Article Preview

1. Introduction

Multimodal Biometric System is a relatively new alternative to Unimodal Biometric System. Multimodality can be achieved in various ways: such as combining multiple biometric traits, selecting distinct feature sets from the same source of biometric, using separate sensors, fusing the decision of individual biometric system, etc. (Jain, Flynn, & Ross, 2007). In our system, we have used diverse feature sets from different biometric traits. From the literature, it is found that multimodal biometric system often outperforms a unimodal biometric system in terms of accuracy and reliability (Ross, Nandakumar, & Jain, 2006). It can solve some common problems of unimodal biometric system such as intra-class variability, interclass similarity, non-universality, sensitivity to noise and other issues. Multimodal biometric system can improve the performance of a biometric system in a number of aspects, including accuracy, circumvention, resistance to errors and spoof attacks (Ross, Nandakumar, & Jain, 2006). Multimodal biometric systems are more secure compared with unimodal systems in terms of authentication accuracy (Down & Sands, 2004).

Individual’s biometric traits are stored on a template database during both the training and the matching. The most important part of the biometric system from the point of view of security and privacy is the template database. Previous, studies (Ross, Shah, & Jain, 2007; Alder, 2003) have shown that the raw image or text can be recovered from the template stored within the database. A first approach to deal with biometric security and privacy was to store the transformed version of original template (Ross, Shah, & Jain, 2007; Alder, 2003). Ross, et., al. (2007) reconstructed fingerprint image from stored minutiae points. In previous research on biometric template protection, authors suggested the dependency of cancelable biometric algorithm on security, discriminability, recoverability, performance and diversity of the system (Jain, Flynn, & Ross, 2007; Maltoni, Maio, Jain, & Prabhakar, 2003; Feng, Yuen, & Jain, 2010). They noted that it should be computationally hard to reconstruct the original template from the transformed template. The discriminability of the original biometric template should not be lost after the cancelable transformation as well as performance. On the other hand, the revocability and diversity are the two most important characteristics of Cancelability.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing