Sclera Recognition System

Abstract

The vein structure in sclera, a white and an opaque outer protective covering of eye, is anecdotally
stable over time and unique to each person. As a result, it is well suited for an use as a biometric for human
identification. The few researchers have performed sclera vein pattern recognition and have the reported promising,
but an low accuracy, and the initial results. Sclera recognition poses several challenges: the vein structure moves
and then deforms with an movement of the eye and its surrounding tissues; images of sclera patterns are often
defocused and/or saturated; and, a most importantly, an vein structure in the sclera is multi-layered and has
complex non-linear deformation. The previous approaches in a sclera recognition have treated the sclera patterns
as a one-layered vein structure, and, as a result, their sclera recognition accuracy is not high. In this, we propose
a new method for the sclera recognition with the following contributions: First, we developed an color-based sclera
region estimation scheme for the sclera segmentation. Second, we designed an Gabor wavelet based sclera
pattern enhancement method, and an adaptive thresholding method to emphasize and binarize the sclera vein
patterns. Third, we proposed a line descriptor based feature extraction, registration, and matching method that is
scale-, orientation-, and an deformation-invariant, and can mitigate the multi-layered deformation effects and
tolerate a segmentation error. It is empirically verified using UBIRIS and IUPUI multi-wavelength databases that
the proposed method can perform the accurate sclera recognition. In addition, an recognition results are compared
to the iris recognition algorithms, with the very comparable results.