Abstract— The performance of iris recognition systems is significantly affected by the segmentation accuracy, especially in non-ideal iris images. This paper proposes a fast and accurate method to segment the pupil regardless of the shape using a combination of morphological operations and snake active contour. The morphological operations are used to determine a rough boundary of the pupil region while the active contour is used to find the precise boundary. The proposed scheme is robust in finding the exact pupil boundary of non-ideal iris image. Experimental results on the CASIA version 4.0 iris databases have indicated a high level of accuracy using the proposed technique.
Index Terms— Active contour, iris recognition, image segmentation, morphological operations, pupil segmentation.
The authors are with the school of Electrical and Electronic Engineering, Newcastle University, England, United Kingdom.
Mohammed A. M. Abdullah is also with the University of Mosul in Nineveh, Iraq (e-mail: mabdul@uomosul.edu.iq).
[PDF]
Cite: Mohammed A. M. Abdullah, S. S. Dlay, and W. L. Woo, " Fast and Accurate Pupil Isolation Based on Morphology and Active Contour," International Journal of Information and Electronics Engineering vol. 4, no. 6, pp. 418-422, 2014.