A Novel Cross Folding Algorithm for Multimodal Cancelable Biometrics

A Novel Cross Folding Algorithm for Multimodal Cancelable Biometrics

Padma P. Paul (University of Calgary, Canada) and Marina L. Gavrilova (University of Calgary, Canada)
DOI: 10.4018/jssci.2012070102
OnDemand PDF Download:
No Current Special Offers


Multimodal biometric systems have emerged as 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. However, one major issue pertinent to unimodal system remains, which has to do with actual biometric characteristics of users being permanent and their number being limited. Thus, if a user’s biometric is compromised, it might be impossible or highly difficult to replace it in a particular system. The concept of 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. In this paper, the authors present a novel solution for cancelable biometrics in a multimodal system. They develop a new cancelable biometric template generation algorithm using random projection and transformation-based feature extraction and selection. Performance of the proposed algorithm is validated on a virtual multi-modal face and ear database.
Article Preview

1. Introduction

Secure access to information, databases and networks can be ensured by using several types of credentials. Passwords and tokens are traditionally used to authenticate the users. Complexities of the credentials ensure the system security level (Feng, Yuen, & Jain, 2010). However, a password-based system may not be efficient or reliable for several reasons, mainly rooted in the need for legitimate users to memorize the passwords, more sophisticated methods of password break-in, and availability of spyware used by hackers to steal the passwords. Thus, the use of biometric technologies in physical and logical access control system is one of the most rapidly developed areas of biometric research and commercial sectors of biometric (Jain, Flynn, & Ross, 2007.). A biometric system has been defined as “a pattern-recognition system that recognizes a person based on a feature vector derived from a specific physiological or behavioral characteristic that the person possesses” (Prabhakar, Pankanti, & Jain, 2003). Commonly used biometric traits include fingerprint, face, signatures, iris, palm-print, fingerprint, hand geometry, ear, voice etc. A typical biometric system usually consists of four basic components, a) acquisition of biometric data, b) feature extraction, c) feature matching, and d) decision-making. Figure 1 shows the general architecture of a biometric authentication system.

Figure 1.

General block diagram of traditional biometric system


In a biometric system, both verification and identification are two important ways of person recognition (Jain et al., 2007). Each is intended to be used under different conditions and in different security applications. In verification mode, the person’s identity is claimed (Jain et.al 2007). On the other hand, an identification system recognizes a person from a template database containing certain number of persons. Identification is a more challenging and computationally expensive problem because it involves finding the correct match between the sample and the template stored in the database. On the other hand, verification is one by one matching (Jain & Flynn 2007). Multimodal Biometric System is a relatively new alternative to Unimodal Biometric System. Multimodality can be achieved in different ways: such as combining multiple biometric traits, selecting different feature sets from the same source of biometric, using different sensors, fusing the decision of individual biometric system etc. (Monwar & Gavrilova, 2008). In our system, we have used different 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 et al., 2006; Jain & Pankanti, 2006). Multimodal biometric systems are more secure compared with unimodal systems in term of authentication accuracy (Down & Sands, 2004).

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 13: 4 Issues (2021): 3 Released, 1 Forthcoming
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing