HEAL DSpace

Intelligent action-based image recognition system

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Alexopoulos, Vassilios en
dc.contributor.author Kollias, Stefanos en
dc.date.accessioned 2014-03-01T01:44:45Z
dc.date.available 2014-03-01T01:44:45Z
dc.date.issued 1996 en
dc.identifier.issn 12100552 en
dc.identifier.uri http://hdl.handle.net/123456789/24474
dc.relation.uri http://www.scopus.com/inward/record.url?eid=2-s2.0-0029719145&partnerID=40&md5=d6e3796d9fbc906549df8322cd16677e en
dc.subject.other Feature extraction en
dc.subject.other Fuzzy sets en
dc.subject.other Image processing en
dc.subject.other Pattern recognition en
dc.subject.other Spurious signal noise en
dc.subject.other Vision en
dc.subject.other Fuzzy subsystem en
dc.subject.other Intelligent action based image recognition system en
dc.subject.other Neural network classifier en
dc.subject.other Visual information processing en
dc.subject.other Neural networks en
dc.title Intelligent action-based image recognition system en
heal.type journalArticle en
heal.publicationDate 1996 en
heal.abstract This paper presents a novel intelligent system for recognition of images or scenes, which includes neural network architectures and is inspired by human perception actions. In particular, a recurrent neural network subsystem is used to extract features from the images; these features being associated to the way humans perceive visual information. A neural network classifier, followed by a fuzzy subsystem, is used for interpretation of the extracted features. Results are presented using images of objects, that are deformed and/or corrupted by noise, which illustrate the capabilities of the proposed system. en
heal.publisher IDG, Prague, Czech Republic en
heal.journalName Neural Network World en
dc.identifier.volume 6 en
dc.identifier.issue 3 en
dc.identifier.spage 251 en
dc.identifier.epage 258 en


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record