Retinal image analysis aimed at extraction of vascular structure using linear discriminant classifier

Fraz, M.M., Remagnino, P., Hoppe, A. and Barman, S. (2013) Retinal image analysis aimed at extraction of vascular structure using linear discriminant classifier. In: IEEE International Conference on Computer Medical Applications (ICCMA); 20-22 Jan. 2013, Sousse, Tunisia. ISBN 9781467352130

Full text not available from this archive.

Abstract

Automatic segmentation of the retinal vasculature is considered as a first step in computer assisted medical applications related to diagnosis and treatment planning. This paper describes a pixel classification based method of segmenting retinal blood vessels using linear discriminant analysis. The vessel-ness measure of a pixel is defined by the feature vector comprised of a modified multiscale line operator and Gabor filter responses. The sequential forward feature selection scheme is used to identify the optimal scales for the line operator and Gabor filter. The linear discriminant classifier utilizes only two features for pixel classification. The feature vector encodes information to reliably handle normal vessels in addition to vessels with strong light reflexes along their centerline, which is more apparent on retinal arteriolars than venules. The method is evaluated on the three publicly available DRIVE, STARE and MESSIDOR datasets. The method is computationally fast and its performance approximates the 2<sup>nd</sup> human observer as well as other existing methodologies available in the literature, thus making it a suitable tool for automated retinal image analysis.

Item Type: Conference or Workshop Item (Paper)
Event Title: IEEE International Conference on Computer Medical Applications (ICCMA)
Organising Body: IEEE
Uncontrolled Keywords: Image analysis Linear discriminant analysis Medical Imaging Pixel classification Retinal blood vessels segmentation
Research Area: Computer science and informatics
Faculty, School or Research Centre: Faculty of Science, Engineering and Computing > Digital Imaging Research Centre (DIRC)
Faculty of Science, Engineering and Computing > School of Computing and Information Systems
Faculty of Science, Engineering and Computing
Depositing User: Moazam Fraz
Date Deposited: 14 Feb 2014 11:12
Last Modified: 14 Feb 2014 11:12
URI: http://eprints.kingston.ac.uk/id/eprint/27938

Actions (Repository Editors)

Item Control Page Item Control Page