PERFORMANCE EVALUATION OF TWO HIGH PROFILE SEGMENTATION ALGORITHMS IN IRIS RECOGNITION SYSTEM
PERFORMANCE EVALUATION OF TWO HIGH PROFILE SEGMENTATION ALGORITHMS IN IRIS RECOGNITION SYSTEM
No Thumbnail Available
Date
2014-11
Authors
ADEPOJU, SUNDAY FEMI
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Iris is an effective biometric application of an individual for security-related applications.
However, the iris segmentation process is challenging due to the presence of eye lashes that
occlude the iris. Iris segmentation is an important phase in the whole iris recognition system, for
it determines the accuracy of matching. To find a fast, effective and exact iris segmentation
algorithm is the key step of iris recognition. This thesis compares the two high profile
segmentation algorithms of Daugman (integro-differential) and Wildes (circular hough).
Simulating the two algorithms with MATLAB 2012 and image datasets from Chinese Academy
of Science Institute of Automation (CASIA) version 4, the evaluation of the algorithms was
carried out using the performance metric False Acceptance Rate (FAR), False Rejection Rate
(FRR) and Recognition Accuracy. The analysis of the result, indicated that the Circular Hough is
more accurate than intego-differential as it shows higher recognition accuracy and lower error
rate
Description
A THESIS SUBMITTED TO THE POSTGRADUATE SCHOOL, AHMADU
BELLO UNIVERSITY, ZARIA
IN PARTIAL FULFILLMENT OF THE REQUIREMENT FOR THE
AWARD OF M.SC. DEGREE IN COMPUTER SCIENCE
DEPARTMENT OF MATHEMATICS, FACULTY OF SCIENCE,
AHMADU BELLO UNIVERSITY, ZARIA
Keywords
PERFORMANCE EVALUATION,, HIGH PROFILE,, SEGMENTATION ALGORITHMS,, IRIS RECOGNITION SYSTEM,