Elastic models: A comparative study applied to retinal images

Karali, E; Lambropoulou, S; Koutsouris, D

dc.contributor.author	Karali, E	en
dc.contributor.author	Lambropoulou, S	en
dc.contributor.author	Koutsouris, D	en
dc.date.accessioned	2014-03-01T02:01:58Z
dc.date.available	2014-03-01T02:01:58Z
dc.date.issued	2011	en
dc.identifier.issn	09287329	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29277
dc.subject	GVF snakes	en
dc.subject	Image segmentation	en
dc.subject	self affine mapping system	en
dc.subject	snakes	en
dc.subject	T-snakes	en
dc.subject.other	Serpentes	en
dc.subject.other	algorithm	en
dc.subject.other	article	en
dc.subject.other	biometry	en
dc.subject.other	human	en
dc.subject.other	image processing	en
dc.subject.other	methodology	en
dc.subject.other	retina	en
dc.subject.other	statistical model	en
dc.subject.other	statistics	en
dc.subject.other	Algorithms	en
dc.subject.other	Biometry	en
dc.subject.other	Humans	en
dc.subject.other	Image Processing, Computer-Assisted	en
dc.subject.other	Models, Statistical	en
dc.subject.other	Retina	en
dc.subject.other	Statistics as Topic	en
dc.title	Elastic models: A comparative study applied to retinal images	en
heal.type	journalArticle	en
heal.identifier.primary	10.3233/THC-2011-0636	en
heal.identifier.secondary	http://dx.doi.org/10.3233/THC-2011-0636	en
heal.publicationDate	2011	en
heal.abstract	In this work various methods of parametric elastic models are compared, namely the classical snake, the gradient vector field snake (GVF snake) and the topology-adaptive snake (t-snake), as well as the method of self-affine mapping system as an alternative to elastic models. We also give a brief overview of the methods used. The self-affine mapping system is implemented using an adapting scheme and minimum distance as optimization criterion, which is more suitable for weak edges detection. All methods are applied to glaucomatic retinal images with the purpose of segmenting the optical disk. The methods are compared in terms of segmentation accuracy and speed, as these are derived from cross-correlation coefficients between real and algorithm extracted contours and segmentation time, respectively. As a result, the method of self-affine mapping system presents adequate segmentation time and segmentation accuracy, and significant independence from initialization. © 2011 - IOS Press and the authors. All rights reserved.	en
heal.journalName	Technology and Health Care	en
dc.identifier.doi	10.3233/THC-2011-0636	en
dc.identifier.volume	19	en
dc.identifier.issue	6	en
dc.identifier.spage	401	en
dc.identifier.epage	413	en