Identifying the best periocular region for biometric recognition

Periocular images contain iris as well as other near-by regions such as eyelids and eyebrows. It is useful to know which regions of ocular images are important for achieving good recognition performance. This chapter will present observations from experiments with regard to the effect of changing the size or selection of the periocular region on biometric recognition performance. One can use a single definition of the periocular region to identify areas that contain significant discriminative textural information in an attempt to identify such regions. In this chapter, we investigate sub-region effects over varying cropping sizes to determine an appropriate periocular image representation.