Towards a multimodality ontology image retrieval
Ontology based retrieval is gaining popularity due to the limitation posed by the conventional bag-of-words retrieval system. To semantically search for images, textual descriptions are usually used since low level features provide little meaningful information. As such conventional searching and re...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Berlin Heidelberg
2011
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/30412/ http://irep.iium.edu.my/30412/ http://irep.iium.edu.my/30412/ http://irep.iium.edu.my/30412/1/chp%253A10.1007%252F978-3-642-25200-6_36.pdf |
| Summary: | Ontology based retrieval is gaining popularity due to the limitation posed by the conventional bag-of-words retrieval system. To semantically search for images, textual descriptions are usually used since low level features provide little meaningful information. As such conventional searching and retrieving of images are currently being employed. Complex querying and enhanced semantic search still remain the issues to be solved in image retrieval systems. We proposed an ontology driven framework for supporting image retrieval with particular emphasis on the sport news domain. Furthermore, we look into the possibility how multimodality ontology can be integrated in the framework and shows how open knowledge-bases such as the DBpedia play an important role in this area. |
|---|