Automatic retinal vessel profiling using multi-step regression method

Aliahmad, Behzad and Kumar, Dinesh K. and Janghorban, Samira and Che Azemin, Mohd Zulfaezal (2011) Automatic retinal vessel profiling using multi-step regression method. In: 33rd Annual International Conference of the IEEE EMBS, 30 Aug-3 Sept. 2011, Boston, Massachusetts.

PDF (Automatic retinal vessel) - Published Version Restricted to Repository staff only Download (594kB)

Abstract

Caliber of the retinal blood vessel is widely used for risk assessment of cardiovascular diseases. Accurate and automatic caliber measurement requires a precise model to be made for the vessel profile. In this paper, we present a new approach for retinal vessel profiling in which the background noise, uneven illuminations and specular reflections have all been considered. In this method, regression analysis is performed with a series of second-order Gaussians to filter and up-sample the original vessel profile. This is then segmented to identify and represent the vessel edges by two Generalized Gaussian functions. The technique has been applied to retinal images and the results have been verified and compared with the state of the art automatic techniques.

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Additional Information:	/19469
Uncontrolled Keywords:	Gaussian representation , Retinal image , Vessel profile
Subjects:	R Medicine > RC Internal medicine
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Science Kulliyyah of Science > Department of Biomedical Science
Depositing User:	Mrs. Wan Salwati Wan Salleh
Date Deposited:	16 Feb 2012 08:33
Last Modified:	09 Nov 2022 15:47
URI:	http://irep.iium.edu.my/id/eprint/19469

Actions (login required)

View Item