On the use of multispectral conjunctival vasculature as a soft biometric

Abstract

Ocular biometrics has made significant progress over the past decade primarily due to advances in iris recognition. Initial research in the field of iris recognition focused on the acquisition and processing of frontal irides which may require considerable subject cooperation. However, when the iris is off-angle with respect to the acquisition device, the sclera (the white part of the eye) is exposed. The sclera is covered by a thin transparent layer called conjunctiva. Both the episclera and conjunctiva contain blood vessels that are observable from the outside. In this work, these blood vessels are referred to as conjunctival vasculature. Iris patterns are better observed in the near infrared spectrum while conjunctival vasculature is better seen in the visible spectrum. Therefore, multispectral (i.e., color-infrared) images of the eye are acquired to allow for the combination of the iris biometric with the conjunctival vasculature. The paper focuses on conjunctival vasculature enhancement, registration and matching. Initial results are promising and suggest the need for further investigation of this biometric in a bimodal configuration with iris.