Semantic image analysis using a symbolic neural architecture

Kollia, I; Simou, N; Stafylopatis, A; Kollias, S

dc.contributor.author	Kollia, I	en
dc.contributor.author	Simou, N	en
dc.contributor.author	Stafylopatis, A	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T01:59:54Z
dc.date.available	2014-03-01T01:59:54Z
dc.date.issued	2010	en
dc.identifier.issn	15803139	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29055
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-78650154882&partnerID=40&md5=aa08bf9c69fc7dd5d64508c47492c0ce	en
dc.subject	Fuzzy description logics	en
dc.subject	Kernel based connectionist systems	en
dc.subject	Machine learning	en
dc.subject	Semantic image analysis	en
dc.title	Semantic image analysis using a symbolic neural architecture	en
heal.type	journalArticle	en
heal.publicationDate	2010	en
heal.abstract	Image segmentation and classification are basic operations in image analysis and multimedia search which have gained great attention over the last few years due to the large increase of digital multimedia content. A recent trend in image analysis aims at incorporating symbolic knowledge representation systems and machine learning techniques. In this paper, we examine interweaving of neural network classifiers and fuzzy description logics for the adaptation of a knowledge base for semantic image analysis. The proposed approach includes a formal knowledge component, which, assisted by a reasoning engine, generates the a-priori knowledge for the image analysis problem. This knowledge is transferred to a kernel based connectionist system, which is then adapted to a specific application field through extraction and use of MPEG-7 image descriptors. Adaptation of the knowledge base can be achieved next. Combined segmentation and classification of images, or video frames, of summer holidays, is the field used to illustrate the good performance of the proposed approach.	en
heal.journalName	Image Analysis and Stereology	en
dc.identifier.volume	29	en
dc.identifier.issue	3	en
dc.identifier.spage	133	en
dc.identifier.epage	141	en