Neural networks retraining for unsupervised video object segmentation of videoconference sequences

Ntalianis, KS; Doulamis, ND; Doulamis, AD; Kollias, SD

dc.contributor.author	Ntalianis, KS	en
dc.contributor.author	Doulamis, ND	en
dc.contributor.author	Doulamis, AD	en
dc.contributor.author	Kollias, SD	en
dc.date.accessioned	2014-03-01T01:18:05Z
dc.date.available	2014-03-01T01:18:05Z
dc.date.issued	2002	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/14795
dc.subject	Adaptive Neural Network	en
dc.subject	Convex Function	en
dc.subject	Linear Constraint	en
dc.subject	Network Performance	en
dc.subject	Neural Network Classifier	en
dc.subject	Shape Constraints	en
dc.subject	Template Matching	en
dc.subject	Video Object Segmentation	en
dc.subject	Neural Network	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.other	IMAGES	en
dc.title	Neural networks retraining for unsupervised video object segmentation of videoconference sequences	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/3-540-46084-5_212	en
heal.identifier.secondary	http://dx.doi.org/10.1007/3-540-46084-5_212	en
heal.language	English	en
heal.publicationDate	2002	en
heal.abstract	In this paper efficient performance generalization of neural network classifiers is accomplished, for unsupervised video object segmentation in videoconference/videophone sequences. Each time conditions change, a retraining phase is activated and the neural network classifier is adapted to the new environment. During retraining both the former and current knowledge are utilized so that good network generalization is achieved. The retraining algorithm results in the minimization of a convex function subject to linear constraints, leading to very fast network weight adaptation. Current knowledge is unsupervisedly extracted using a face-body detector, based on Gaussian p.d.f models. A binary template matching technique is also incorporated, which imposes shape constraints to candidate face regions. Finally the retrained network performs video object segmentation to the new environment. Several experiments on real sequences indicate the promising performance of the proposed adaptive neural network as efficient video object segmentation tool.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	ARTIFICIAL NEURAL NETWORKS - ICANN 2002	en
heal.bookName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/3-540-46084-5_212	en
dc.identifier.isi	ISI:000181441900212	en
dc.identifier.volume	2415	en
dc.identifier.spage	1312	en
dc.identifier.epage	1318	en