Multi scale multi directional shear operator for personal recognition using Conjunctival vasculature

In this paper, we present the results of a study on utilization of Conjunctival vasculature pattern as a biometric modality for personal identification. The visible red blood vessel patterns on the sclera of the eye is gaining acceptance as a biometric modality due to its proven uniqueness and easy accessibility for imaging in the visible spectrum. After acquisition, the images of Conjunctival vascular patterns are enhanced using the difference of Gaussian (DoG). The feature extraction is performed using a multi-scale, multi-directional shear operator (Shearlet transform). Linear discriminant analysis (LDA), neural networks (NN) and pairwise distance metrics were used for classification. In the study, images of 50 subjects are acquired with a DSLR camera at different gazes and multiple distances (CIBIT-I dataset). Additionally, the performance of the proposed algorithms is tested using different gaze images acquired from 35 subjects using an iPhone (CIBIT-II dataset). ROC AUC analysis is used to test the classification performance. Areas under the curve (AUC) and equal error rates (EER) are reported for all acquisition scenarios and different processing algorithms. The best EER value of 0.29% is obtained for a CIBIT-I dataset using NN and a 2.44% EER value for a CIBIT-II dataset using LDA.