A multiresolution neural network approach to invariant image recognition

Kollias, SD

dc.contributor.author	Kollias, SD	en
dc.date.accessioned	2014-03-01T01:11:36Z
dc.date.available	2014-03-01T01:11:36Z
dc.date.issued	1996	en
dc.identifier.issn	0925-2312	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/11732
dc.subject	autoassociative	en
dc.subject	hierarchical neural networks	en
dc.subject	invariant	en
dc.subject	multiresolution image analysis	en
dc.subject	triple correlations	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.other	Computer architecture	en
dc.subject.other	Computer simulation	en
dc.subject.other	Hierarchical systems	en
dc.subject.other	Image analysis	en
dc.subject.other	Invariance	en
dc.subject.other	Learning systems	en
dc.subject.other	Optical correlation	en
dc.subject.other	Optimization	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Autoassociative linear networks	en
dc.subject.other	Hierarchical neural networks	en
dc.subject.other	Invariant image recognition	en
dc.subject.other	Multiresolution image analysis	en
dc.subject.other	Triple correlations	en
dc.subject.other	Neural networks	en
dc.subject.other	article	en
dc.subject.other	artificial neural network	en
dc.subject.other	image analysis	en
dc.subject.other	mathematical model	en
dc.subject.other	priority journal	en
dc.title	A multiresolution neural network approach to invariant image recognition	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/0925-2312(96)00041-0	en
heal.identifier.secondary	http://dx.doi.org/10.1016/0925-2312(96)00041-0	en
heal.language	English	en
heal.publicationDate	1996	en
heal.abstract	Triple-correlation-based representations of images have recently been combined with neural network architectures to derive invariant, with respect to translation, rotation and dilation, robust classification of images. Multiresolution image analysis is used in this paper to reduce the size of these representations in an optimal way, based on autoassociative linear networks. Hierarchical neural networks are then proposed as an efficient architecture for classification or retrieval of multiresolution invariant image representations. An effective procedure for designing and training such networks is also described and simulation results are presented which illustrate the capabilities of the proposed approach.Triple-correlation-based representations of images have recently been combined with neural network architectures to derive invariant, with respect to translation, rotation and dilation, robust classification of images. Multiresolution image analysis is used in this paper to reduce the size of these representations in an optimal way, based on autoassociative linear networks. Hierarchical neural networks are then proposed as an efficient architecture for classification or retrieval of multiresolution invariant image representations. An effective procedure for designing and training such networks is also described and simulation results are presented which illustrate the capabilities of the proposed approach.	en
heal.publisher	Elsevier Science B.V., Amsterdam, Netherlands	en
heal.journalName	Neurocomputing	en
dc.identifier.doi	10.1016/0925-2312(96)00041-0	en
dc.identifier.isi	ISI:A1996UV61700004	en
dc.identifier.volume	12	en
dc.identifier.issue	1	en
dc.identifier.spage	35	en
dc.identifier.epage	57	en