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
%0 Journal Article
%1 Athanasiadis2007
%A Athanasiadis, T.
%A Mylonas, P.
%A Avrithis, Y.
%A Kollias, S.
%D 2007
%J Circuits and Systems for Video Technology, IEEE Transactions on
%K (mathematics)automatic algorithms, analysis, annotation, blending context extraction, feature features, fuzzy global growing image knowledge knowledge, knowledge-assisted labeling, multimedia object ontological recursive region representation, segmentation, semantic set sets, shortest spanning taxonomic theory, tree tree, trees visual watershed
%N 3
%P 298-312
%R 10.1109/TCSVT.2007.890636
%T Semantic Image Segmentation and Object Labeling
%V 17
%X 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
@article{Athanasiadis2007,
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},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Athanasiadis, T. and Mylonas, P. and Avrithis, Y. and Kollias, S.},
biburl = {https://www.bibsonomy.org/bibtex/2fd94df4f1bcdf8927f50ab6a91f74cea/mozaher},
doi = {10.1109/TCSVT.2007.890636},
file = {:Athanasiadis2007.pdf:PDF},
interhash = {c6c4b01ecd6dae4fe95c67a13a5f2453},
intrahash = {fd94df4f1bcdf8927f50ab6a91f74cea},
issn = {1051-8215},
journal = {Circuits and Systems for Video Technology, IEEE Transactions on},
keywords = {(mathematics)automatic algorithms, analysis, annotation, blending context extraction, feature features, fuzzy global growing image knowledge knowledge, knowledge-assisted labeling, multimedia object ontological recursive region representation, segmentation, semantic set sets, shortest spanning taxonomic theory, tree tree, trees visual watershed},
month = {March },
number = 3,
owner = {Mozaherul Hoque},
pages = {298-312},
print = {Y},
timestamp = {2009-09-12T19:19:36.000+0200},
title = {Semantic Image Segmentation and Object Labeling},
volume = 17,
year = 2007
}