Periocular Biometric Recognition Using Supervised Fuzzy Clustering

Abstract

Abtsract-Developing a potential biometrics has been a key focus of research in recent years. Periocular biometrics is a new trait to deal with non-ideal scenarios in face and iris biometrics. It can be used as an alternative to iris recognition, if the iris images are captured at a distance. In forensic applications, this trait can be used individually as well as with other traits (face and iris) for effective and accurate identification. In recent researches, the periocular biometrics is significantly impacting the iris and face based recognition. In this paper, we investigated the efficacy of supervised fuzzy clustering for strict periocular region which does not involve the eyebrows. The fixed initialization is considered in proposed supervised fuzzy clustering instead of random initialization. Then fuzzy clustering motivated with partition index maximization is used to optimize the objective function, hence yield clusters with representative prototype. The fuzzy clustering is further generalized with Minkowski distance matrices to yield variable cluster shape. Recognition is done based on the minimum distance measure between the test patterns and the centroid of the clusters. We use eight hundred periocular region images extracted from AR face dataset of 40 subjects. Performance of the proposed technique has been evaluated in terms of rank-one and rank-two recognition accuracy. Experimental analysis demonstrates the efficacy of presented technique over other variants of fuzzy clustering techniques.Index Terms-Periocular biometrics, fuzzy clustering, supervised initialization, principal component analysis. I. INTRODUCTIONThe periocular biometric is gaining attention as a potential feature for biometric authentication in the recent past. The term periocular refers to the facial region in the immediate vicinity of the eye. It has been evolved as a separate modality in biometric information [1]-[3] which can be independently used for recognition. It has been also observed that it may aid to traditional biometric traits viz face, iris or retina, to identify an individual uniquely and reliably. The acquizistion of the periocular biometric requires less subject cooperation, where as it allows a larger depth of field compared to conventional ocular biometric traits. This trait can be more useful in forensic applications to reduce the search space when only periocular region is provided. One the influential factor for using this region as a separate trait is its non mandatory nature towards the higher resolution as compared to other ocular biometrics such as iris, retina and conjunctiva [4]- [6]. The fundamental requirement of any biometric recognition system is a human trait having several desirable features like universality, distinctiveness, permanence and acceptability. However, a human characteristic possessing all these features has not yet been identified. As a result, none of the single biometric trait can provide perfect recognition. It is also difficult to achieve very high recognition rates using single tr...