Fusing Iris, Palmprint and Fingerprint in a Multi-biometric Recognition System

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin, Babak Nadjar Araabi, Hamid Soltanian-Zadeh

Abstract: This paper presents a trimodal biometric recognition system based on iris, palmprint and fingerprint. Wavelet transform and Gabor filter are used to extract features in different scales and orientations from iris and palmprint. Minutiae extraction and alignment is used for fingerprint matching. Six different fusion algorithms including score-based, rank-based and decision-based methods are used to combine the results of three modules. We also propose a new rank-based fusion algorithm Maximum Inverse Rank (MIR) which is robust with respect to variations in scores and also bad ranking from a module. CASIA datasets for iris, palmprint and fingerprint are used in this study. The experiments show the effectiveness of our fusion method and our trimodal biometric recognition system in comparison to existing multi-modal recognition systems.