Rank level fusion of multimodal cancelable biometrics

Abstract

Cancelable biometrics is newly emerged biometric technology that can provide the protection over different attacks to a biometric system. In this paper, we have presented a multilevel random projection on face and ear biometric traits. The multiple random projections are conducted using multiple random projection matrixes. From multiple random projections, we have generated multiple templates for biometric authentication. Therefore, proposed method can provide better template security and better feature quality. Multiple cancelable templates are used for recognition purpose and rank level fusion is applied to generate final decision from multiple ranks. As per our knowledge, we have applied rank level fusion on cancelable multimodal biometric system for the first time. A detailed validation and the performance analysis of the proposed algorithm on a virtual multimodal cancelable face and ear database are presented.

Cancelable bimodal shell using fingerprint and iris

“…Paul et al 10 proposed a multimodal system using face and ear biometrics. First, multiple blocks of the same size are created for each trait.…”

Hand-based multibiometric systems: state-of-the-art and future challenges

“…The authors have validated the cancelable property of the proposed method, while giving good authentication results in a multibiometric setting. Furthermore, the authors improved the results by proposing a methodology in which both Gram-Schmidt transformation and PCA were used followed by a rank level fusion for performing final authentication of the users (Paul & Gavrilova, 2014). Chin et al (2014)…”

“…Paul & Gavrilova (2014) Multibiometric template protection using Gram-Schmidt transform, PCA and rank level fusion 2017Gomez-Barrero et al (2017) Homomorphic probabilistic encryption for cancelable biometric template generation…”