A two-phase connectionist approach to invariant picture interpretation

Kontoravdis, D; Kollias, S; Stafylopatis, A

dc.contributor.author	Kontoravdis, D	en
dc.contributor.author	Kollias, S	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T01:11:38Z
dc.date.available	2014-03-01T01:11:38Z
dc.date.issued	1996	en
dc.identifier.issn	0378-4754	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/11757
dc.subject	Individual Object	en
dc.subject	Learning Automata	en
dc.subject	Neural Network Classifier	en
dc.subject	Parallel Implementation	en
dc.subject	Relaxation Scheme	en
dc.subject	Simulation Experiment	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Computer Science, Software Engineering	en
dc.subject.classification	Mathematics, Applied	en
dc.subject.other	Automata theory	en
dc.subject.other	Computer simulation	en
dc.subject.other	Computer vision	en
dc.subject.other	Correlation theory	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Object recognition	en
dc.subject.other	Parallel processing systems	en
dc.subject.other	Random processes	en
dc.subject.other	Relaxation processes	en
dc.subject.other	Invariant picture representation	en
dc.subject.other	Neural network classifiers	en
dc.subject.other	Probabilistic assignment	en
dc.subject.other	Stochastic learning automata	en
dc.subject.other	Third order image correlations	en
dc.subject.other	Two phase connectionist techniques	en
dc.subject.other	Image analysis	en
dc.title	A two-phase connectionist approach to invariant picture interpretation	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/0378-4754(95)00009-7	en
heal.identifier.secondary	http://dx.doi.org/10.1016/0378-4754(95)00009-7	en
heal.language	English	en
heal.publicationDate	1996	en
heal.abstract	The paper presents an efficient two-phase approach to picture interpretation based on original connectionist techniques. During the first phase invariant representations of individual objects are obtained based on third-order image correlations and appropriate neural network classifiers are used to provide a probabilistic assignment of labels to objects. The second phase uses relationships between objects to reduce or eliminate ambiguity by means of a relaxation scheme based on stochastic learning automata. Both phases are particularly suited to parallel implementation. Simulation experiments revealed the effectiveness of our approach in solving several problems of small and medium sizes.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Mathematics and Computers in Simulation	en
dc.identifier.doi	10.1016/0378-4754(95)00009-7	en
dc.identifier.isi	ISI:A1996UR67100008	en
dc.identifier.volume	40	en
dc.identifier.issue	5-6 SPEC. ISS.	en
dc.identifier.spage	597	en
dc.identifier.epage	613	en