id: 05867464
dt: a
an: 05867464
au: Kim, Wonpil; Kong, Hyunjang; Oh, Kunseok; Moon, Yoojin; Kim, Pankoo
ti: Concept based image retrieval using the domain ontology.
so: Kumar, Vipin (ed.) et al., Computational science and its applications ‒
    ICCSA 2003. International conference, Montreal, Canada, May 18‒21,
    2003. Proceedings, Part II. Berlin: Springer (ISBN 3-540-40161-X/pbk).
    Lecture Notes in Computer Science 2668, 401-410 (2003).
py: 2003
pu: Berlin: Springer
la: EN
cc: 
ut: 
ci: 
li: doi:10.1007/3-540-44843-8_43
ab: Summary: The recent study has been progressed the research about more
    semantic image indexing and retrieval. In our paper, we represent the
    improved concept-based image retrieval by using domain ontology. We
    analyze the many studies that applied the theory of ontology to
    concept-based image retrieval. Then, we try to solve the problems when
    we apply the huge ontologies in image retrieval system. There are two
    big problems. First, the huge ontologies that have many concepts, is
    out of date and changed the meaning. Secondly, the many new concepts,
    especially in particular domain, cannot express in existing ontologies.
    Therefore, in this paper we try to design and implement the domain
    ontology about the car based on the WordNet, which is one kinds of
    ontologies. The experimental result shows that the semantic distances
    between words are quite close when we test domain ontology than the
    existing WordNet.
rv: