Personal Verification Using Two Level Fusion Schemes Based on Ear and Iris Biometrics

Abstract

Increased threats to conventional personnel verification methods, have given rise to verification methods based on biometrics. This paper presents a novel approach for personal verification based on fusion of two biometric modalities: Ear and Iris. Fusion has been done in two levels. In level one right iris and left iris features have been fused using texture based Grey Level Concurrence Matrix (GLCM) and in level two these features have been fused with AR coefficients taken from ear substructure. It has been found that this two level fusion of features improves the recognition rate of a person to the extent of 100%. The biometric modalities of ear and iris have been chosen on the basis of their desirable properties like uniqueness, universality, permanency and acceptability.