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 r andom 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.