Segmentation and Vein Extraction in Sclera for Human Identification

Abstract

In this paper the main contribution is statistical approaches based image segmentation method, and is able to pointout the circular pupil and sclera area, occluding eyelashes and eyelids, and reflections by a technique Image cropping. Proposed segmentation method is followed with investigation of five feature extraction techniques, viz. Statistical approaches, Glare Area Detection, Wavelet transforms, Lifting wavelet transforms and finally Contour let transform to extract features and to encode and decode the particular parameters of the iris into a bit-wise biometric template. A comparative analysis is done for these techniques with the proposed segmentation method. The green channel extraction measure and Separable Power was employed for classification, finally for classification adopting train iris image deviated output image methods is imported out. The proposed iris recognition method that uses Glare Area Detection and database identification for feature extraction performed with a near-perfect identification in different sclera pictures. This proposed system demonstrates that combination of proposed segmentation approach and feature extraction method in this work helps to improve overall performance and significant increase in the sclera recognition accuracy. The algorithm is robust for noisy conditions such as errors, elliptical pupils, excess eyelash occlusion errors and bad contrast.