Image metric-based biometric comparators: a supplement to feature vector-based Hamming distance?

Abstract

In accordance with the ISO/IEC FDIS 19794-6 standard an iris-biometric fusion of image metric-based and Hamming distance (HD) comparison scores is presented. In order to demonstrate the applicability of a knowledge transfer from image quality assessment to iris recognition, Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Local Edge Gradients metric (LEG), Edge Similarity Score (ESS), Local Feature Based Visual Security (LFBVS), and Visual Information Fidelity (VIF) are applied to iris textures, i.e. query textures are interpreted as noisy representations of registered ones. Obtained scores are fused with traditional HD scores obtained from iris-codes generated by different feature extraction algorithms. Experimental evaluations on the CASIA-v3 iris database confirm the soundness of the proposed approach.