Feature and Rank Level Fusion for Privacy Preserved Multi-Biometric System

Feature and Rank Level Fusion for Privacy Preserved Multi-Biometric System

Padma Polash Paul, Marina Gavrilova
DOI: 10.4018/IJSSCI.2015010101
(Individual Articles)
No Current Special Offers


Privacy protection in biometric system is a newly emerging biometric technology that can provide the protection against various attacks by intruders. In this paper, the authors have presented a multi-level of random projection method based on face and ear biometric traits. Privacy preserved templates are used in the proposed system. The main idea behind the privacy preserve computation is the random projection algorithm. Multiple random projection matrixes are used to generate multiple templates for biometric authentication. Newly introduced random fusion method is used in the proposed system; therefore, proposed method can provide better template security, privacy and feature quality. Multiple randomly fused templates are used for recognition purpose and finally decision fusion is applied to generate the final classification result. The proposed method works in a similar way human cognition for face recognition works, furthermore it preserve privacy and multimodality of the system.
Article Preview

1. Introduction

In the recent years, the link between the cognitive informatics community and biometric security has grown stronger. It is evident from the number of publications that span both domains that deal with issues of applying intelligent techniques to biometric processing, and with developing new cognition methods for biometric and security applications and research (P. Paul & Gavrilova, 2012; Wang & Berwick, 2012; Patel et al., 2013; P. P. Paul & Gavrilova, 2012). Computational intelligence and algorithm finds its many uses in biometric domain (P. P. Paul, Gavrilova, & Alhajj, 2014; P. P. Paul, Gavrilova, & Klimenko, 2014; Perlovsky & Kuvich, 2013; Wang, 2007; Gavrilova & Monwar, 2013; P. Paul & Gavrilova, 2014). In addition, virtual reality also benefits from novel biometric methods (Gavrilova & Yampolskiy, 2010). The concept of cancelable biometric or cancelability has become popular very recently (P. P. Paul & Gavrilova, 2013; Feng, Yuen, & Jain, 2010). This new trend focuses on how to transform a biometric data or feature into a new one so that users can change their single biometric template in a biometric security system. Up until now, multimodal system cancelability has not been considered. However, this can be argued that template protection is even more crucial in such systems. Multimodal biometric system uses a numbers of biometric credentials, so it is cooperative to the attackers to get more evidence if they manage to break the system. Once templates from the multimodal system are compromised, individual loses all the sensitive data stored in the current security system, and all other systems related to that individual. This is why it is crucial for a multi-biometric system to provide the template security and cancelability. It can be claimed that using cancelability for each biometric trait separately in multimodal biometric system can solve the problem. However, this is not as easy as it looks; the solution may be costly in term of computation efforts and performance. If one trait is compromised, similar method can be used to break other traits. Another concern can be key protection and storage; system needs to issue key for each biometric trait. In this paper, we tackle the above problems and present a novel solution for cancelable biometrics in a multimodal system. We develop a new cancelable biometric template generation algorithm using random cross folding of multiple biometric traits, 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. Specifically, algorithm security is validated by issuing different original and fake keys for different subjects of the database. Algorithm discriminability remains high because of the similar cross fold indices and random projection matrix (vectors) for a class. Similarly, revocability and diversity are ensured by issuing different sets of keys for training and testing process.

Complete Article List

Search this Journal:
Volume 16: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
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