A visual pathway for shape-based invariant classification of gray scale images

Raftopoulos, KA; Papadakis, N; Ntalianis, K; Kollias, S

dc.contributor.author	Raftopoulos, KA	en
dc.contributor.author	Papadakis, N	en
dc.contributor.author	Ntalianis, K	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T02:44:25Z
dc.date.available	2014-03-01T02:44:25Z
dc.date.issued	2007	en
dc.identifier.issn	1069-2509	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31811
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-34547736001&partnerID=40&md5=17091824af2c043402262f83c1cd98a7	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Engineering, Multidisciplinary	en
dc.subject.other	Image analysis	en
dc.subject.other	Image coding	en
dc.subject.other	Neural networks	en
dc.subject.other	Neurons	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Vision	en
dc.subject.other	Gray scale images	en
dc.subject.other	Orientation specific receptive fields	en
dc.subject.other	Shape-based invariant classification	en
dc.subject.other	Underlying contour	en
dc.subject.other	Classification (of information)	en
dc.title	A visual pathway for shape-based invariant classification of gray scale images	en
heal.type	conferenceItem	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	Inspired by the rotated orientation specific receptive fields of the simple neurons that were discovered by Hubel and Wiesel we describe a multi-layered neural architecture for calculating the local curvature at each point of a planar shape without extracting the underlying contour. Our architecture resembles the visual pathway of primates as we demonstrate how the rotated orientation specific receptive fields of the simple neurons can perform local curvature calculation of the planar shape that is projected on the retina of the eye. We then use the same method to encode planar curvature into the intensity of gray scale images and we demonstrate the effectiveness of this encoding by proposing a shape-based triple correlation invariant image classification scheme. We present experimental results illustrating that by encoding planar curvature into the intensity values we improve the recognition capability of multi layered neural network classifiers without imposing additional complexity to the learning process. © 2007 - IOS Press and the author(s). All rights reserved.	en
heal.publisher	IOS PRESS	en
heal.journalName	Integrated Computer-Aided Engineering	en
dc.identifier.isi	ISI:000248835600007	en
dc.identifier.volume	14	en
dc.identifier.issue	4	en
dc.identifier.spage	365	en
dc.identifier.epage	378	en