Bayesian Approach for Sclera Recognition
Iosr Journals, V. Bharathi · Figshare · 2015
Researchers are trying to find new biometrics to provide more options for human ID. Here, we propose a new approach for human ID: sclera recognition. Sclera patterns can be used for human classification and identification since the blood vessel structure of the sclera is unique to each person. Even twins do not have same sclera patterns. Sclera can be acquired at a distance under visible wavelength illumination. But extracting blood vessel pattern is a challenging research problem because images of sclera vessel patterns are often defocused and/or saturated and, most importantly, the vessel structure in the sclera is multilayered and has complex nonlinear deformations. First, a new method for sclera segmentation which works for colour images is developed. Then, a Gabor wavelet-based sclera pattern enhancement method to emphasize and binarize the sclera vessel patterns is designed. For recognition we go for a probabilistic based classifier such as Bayesian to improve the accuracy. Our experimental results show that sclera recognition can achieve comparable recognition accuracy to iris recognition in the visible wavelengths. Thus, sclera recognition is a promising new biometrics for positive human ID.