Poor digital iris images prove to be a challenge when iris features have to be recognised and extracted for use in iris classification. To ensure the accuracy of a typical iris recognition system, acquired
iris images have to undergo a process called pre-processing by employing enhancement algorithms. The purpose of this work is:
(a) to be able to extricate the best suited enhancement technique that will display the articulated iris features and patterns for efficient extraction; and (b) to use the best enhanced images as a directive towards the development of an algorithm that will simulate the change of the different patterns and features by measuring the boundaries between them. This work explores image enhancement in the spatial domain by using three enhancement techniques namely: (i) local histogram equalisation, (ii) global histogram equalisation and (iii) partial contrast, to improve the quality of iris images from three different iris databases.
Reference:
Mabuza, GP and Nelwamondo, FV. Iris image enhancement for feature recognition and extraction. 4th CSIR Biennial Conference: Real problems relevant solutions, CSIR, Pretoria, 9-10 October 2012
Mabuza, G., & Nelwamondo, F. V. (2012). Iris image enhancement for feature recognition and extraction. http://hdl.handle.net/10204/6230
Mabuza, GP, and Fulufhelo V Nelwamondo. "Iris image enhancement for feature recognition and extraction." (2012): http://hdl.handle.net/10204/6230
Mabuza G, Nelwamondo FV, Iris image enhancement for feature recognition and extraction; 2012. http://hdl.handle.net/10204/6230 .