DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/6230

Title: Iris image enhancement for feature recognition and extraction
Authors: Mabuza, GP
Nelwamondo, FV
Keywords: Iris
Iris classification
Iris recognition
User authentication
Image enhancement
Feature recognition
Issue Date: Oct-2012
Citation: 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
Abstract: 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.
Description: 4th CSIR Biennial Conference: Real problems relevant solutions, CSIR, Pretoria, 9-10 October 2012
URI: http://hdl.handle.net/10204/6230
Appears in Collections:CSIR Conference 2012
Sensor science and technology
Advanced mathematical modelling and simulation
Digital intelligence
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Mabuza_2012.pdf879.36 kBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback