Image retrieval and classification using affine invariant B-spline representation and neural networks

Xirouhakis, Y; Avrithis, Y; Kollias, S

dc.contributor.author	Xirouhakis, Y	en
dc.contributor.author	Avrithis, Y	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T01:47:14Z
dc.date.available	2014-03-01T01:47:14Z
dc.date.issued	1998	en
dc.identifier.issn	09633308	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/25180
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0032273179&partnerID=40&md5=ac1bb9ae4c8a976f811006332a9fa9db	en
dc.subject.other	Color image processing	en
dc.subject.other	Database systems	en
dc.subject.other	Feature extraction	en
dc.subject.other	Image analysis	en
dc.subject.other	Image reconstruction	en
dc.subject.other	Image segmentation	en
dc.subject.other	Information retrieval systems	en
dc.subject.other	Invariance	en
dc.subject.other	Object recognition	en
dc.subject.other	Pattern matching	en
dc.subject.other	Video signal processing	en
dc.subject.other	Affine invariant B-spline representations	en
dc.subject.other	Content-based image retrievals	en
dc.subject.other	Neural networks	en
dc.title	Image retrieval and classification using affine invariant B-spline representation and neural networks	en
heal.type	journalArticle	en
heal.publicationDate	1998	en
heal.abstract	In this paper, a system for content-based image retrieval from video databases is introduced, using B-splines for affine invariant object representation. A small number of ""key-frames"" is extracted from each video sequence, which provide sufficient information about the video content. Color and motion segmentation and tracking is then employed for automatic extraction of video objects. A B-spline representation of the object contours is then obtained, which possesses important properties, such as smoothness, continuity and invariance under affine transformation. A neural network approach is used for supervised classification of video objects into prototype object classes. Finally, higher level classes can be constructed combining primary classes, providing the ability to obtain a high level of abstraction in the representation of each video sequence.	en
heal.journalName	IEE Colloquium (Digest)	en
dc.identifier.issue	446	en
dc.identifier.spage	4/1	en
dc.identifier.epage	4/4	en