Open AccessIris Segmentation Based on Black Hole Algorithm for Biometric System
Author(s) -
Tara Othman Qadir,
T. M.
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.b2111.1210220
Subject(s) - hough transform , iris (biosensor) , iris recognition , segmentation , artificial intelligence , biometrics , computer science , computer vision , matlab , boundary (topology) , pupil , pixel , transformation (genetics) , pattern recognition (psychology) , algorithm , image (mathematics) , mathematics , optics , mathematical analysis , biochemistry , chemistry , physics , gene , operating system
Current iris recognition schemes such as IntegroDifferential method, Hough Transform, Watershed Transform Circle Fitting, and Circular Hough Transformation (CHT) are used to find circular parameters between pupil and iris. Segmentation process of an eye image using the circular parameters toextracts the iris region still can be further improved. In this paper, we introduced an optimization method of circular parameters detection for iris segmentation based on Black Hole Algorithm (BHA). The proposed segmentation algorithm utilizes a computational model of the pixels’ value to detect the iris boundary. The BHA searches for center radius of both pupil and iris. The system tests the CASIA Iris Interval V3 database by on MATLAB. The segmented images show an accuracy of 98.3%. In short, the segmentation-based on BHA is efficient to identify the iris for any future access control applications.