Sparsity-Based Iris Classification Using Iris Fiber Structures

As there is a growing demand for biometrics usage in e-Society, the biometric recognition system faces the scalability issue as the number of people to be enrolled into the system runs into billions. In this paper, we propose an approach for iris classification using three different iris classes based on iris fiber structures, namely, stream, flower, jewel and shaker for faster retrieval of identities in large scale biometric system. A sparsity based on-line dictionary learning (ODL) algorithm is used in the proposed classification approach where dictionaries are developed for each class using log-Gabor wavelet features. Also, a method for iris adjudication process is illustrated using the iris classification to reduce the search space. The efficacy of the proposed classification approach is demonstrated on the standard UPOL iris database.