Semantic image segmentation and object labeling

Athanasiadis, T; Mylonas, P; Avrithis, Y; Kollias, S

dc.contributor.author	Athanasiadis, T	en
dc.contributor.author	Mylonas, P	en
dc.contributor.author	Avrithis, Y	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T01:27:14Z
dc.date.available	2014-03-01T01:27:14Z
dc.date.issued	2007	en
dc.identifier.issn	1051-8215	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/18355
dc.subject	Fuzzy region labeling	en
dc.subject	Semantic region growing	en
dc.subject	Semantic segmentation	en
dc.subject	Visual context	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Fuzzy region labeling	en
dc.subject.other	Image annotation	en
dc.subject.other	Semantic region growing	en
dc.subject.other	Semantic segmentation	en
dc.subject.other	Visual context	en
dc.subject.other	Algebra	en
dc.subject.other	Algorithms	en
dc.subject.other	Fuzzy sets	en
dc.subject.other	Multimedia services	en
dc.subject.other	Ontology	en
dc.subject.other	Recursive functions	en
dc.subject.other	Semantics	en
dc.subject.other	Vision	en
dc.subject.other	Image segmentation	en
dc.title	Semantic image segmentation and object labeling	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TCSVT.2007.890636	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TCSVT.2007.890636	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	In this paper, we present a framework for simultaneous image segmentation and object labeling leading to automatic image annotation. Focusing on semantic analysis of images, it contributes to knowledge-assisted multimedia analysis and bridging the gap between semantics and low level visual features. The proposed framework operates at semantic level using possible semantic labels, formally represented as fuzzy sets, to make decisions on handling image regions instead of visual features used traditionally. In order to stress its independence of a specific image segmentation approach we have modified two well known region growing algorithms, i.e., watershed and recursive shortest spanning tree, and compared them to their traditional counterparts. Additionally, a visual context representation and analysis approach is presented, blending global knowledge in interpreting each object locally. Contextual information is based on a novel semantic processing methodology, employing fuzzy algebra and ontological taxonomic knowledge representation. In this process, utilization of contextual knowledge re-adjusts labeling results of semantic region growing, by means of fine-tuning membership degrees of detected concepts. The performance of the overall methodology is evaluated on a real-life still image dataset from two popular domains. © 2007 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Circuits and Systems for Video Technology	en
dc.identifier.doi	10.1109/TCSVT.2007.890636	en
dc.identifier.isi	ISI:000245227000005	en
dc.identifier.volume	17	en
dc.identifier.issue	3	en
dc.identifier.spage	298	en
dc.identifier.epage	311	en