Pupil segmentation using active contour with shape prior

Wang, Yulin, Jiang, Xudong, Zhang, David, Ukpai, Charles, Dlay, Satnam and Woo, Wai Lok (2015) Pupil segmentation using active contour with shape prior. Proceedings of SPIE, 9443. 94432J. ISSN 0277-786X

Full text not available from this repository.

Abstract

Iris segmentation is the process of defining the valid part of the eye image used for further processing (feature extraction, matching and decision making). Segmentation of the iris mostly starts with pupil boundary segmentation. Most pupil segmentation techniques are based on the assumption that the pupil is circular shape. In this paper, we propose a new pupil segmentation technique which combines shape, location and spatial information for accurate and efficient segmentation of the pupil. Initially, the pupil’s position and radius is estimated using a statistical approach and circular Hough transform. In order to segment the irregular boundary of the pupil, an active contour model is initialized close to the estimated boundary using information from the first step and segmentation is achieved using energy minimization based active contour. Pre-processing and post-processing were carried out to remove noise and occlusions respectively. Experimental results on CASIA V1.0 and 4.0 shows that the proposed method is highly effective at segmenting irregular boundaries of the pupil.

Item Type:	Article
Subjects:	G900 Others in Mathematical and Computing Sciences
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Becky Skoyles
Date Deposited:	10 Apr 2019 13:56
Last Modified:	10 Oct 2019 20:15
URI:	http://nrl.northumbria.ac.uk/id/eprint/38902

Downloads