Enhanced Retinal Biometric System for the Diabetic Population using Modified Discrete Grey Wolf Optimization Algorithm

Abstract

Biometric system is the most widely used technology for automatic recognition and authentication of an individual in this modern world. Retina based identification is one such robust and reliable form of biometric solution. As the blood vascular patterns of retina are unique for individuals, these are used as features for developing a retinal biometric system. However, in diabetic persons, retinal complications such as exudates and hemorrhages may obscure these vascular patterns, cause mismatch in the authentication process. This paper proposes an enhanced retinal biometric system, where retinal vasculatures are extracted by an automatic segmentation technique using Modified Discrete Grey Wolf Optimizer (MDGWO). This algorithm is a population-based meta-heuristic swarm intelligence method to find optimal solutions of threshold values in Kapur’s Multilevel Thresholding (KMLT). A post processing step is included before the authentication both in the enrollment and verification process. In this step, findings due to diabetes seen in the segmented image are removed by a morphological processing method before the matching process. This retinal biometric system shows improved matching accuracy of 97.5%. Hence, MDGWO based enhanced retinal biometric system is optimal for building robust biometric systems for the entire population.