Iris features segmentation for arabian horses identification
Aya Salama, Aboul Ella Hassanien, Aly Fahmy · 2017
This paper introduces a new approach for segmentation of the found significant features in the iris of Arabian horses. It was found that the most significant features are as follows; the retina cogina, the pupil shape and the pupil size. Accordingly; a new technique that depends on segmentation of the pupil region with the retina cogina in the iris is proposed. Circular hough transform, canny edge detection, and k-mean clustering are applied. For noise removal, connected component labeling and morphological analysis take place. The presented study surveys the application of the proposed technique on collected data set of iris images for different 145 Arabian horses, For testing the effectiveness and the success of such newly applied technique, Jaccard similarity coefficient was evaluated and it was found in the range 80% to 95%. Hence; such technique may represent a new contribution in the iris identification as it hasnfit been applied in any previous study.