Scene classification for content-based image retrieval
2008 IEEE 16th Signal Processing, Communication and Applications Conference, SIU
Item Usage Stats
MetadataShow full item record
Content-based image indexing and retrieval have become important research problems with the use of large databases in a wide range of areas. In this study, a content-based image retrieval system that is based on scene classification for image indexing is proposed. Instead of using low-level features directly, semantic class information that is obtained as a result of scene classification is used during indexing. The traditional "bag of words" approach is modified for classifying the scenes. In order to minimize the semantic gap, a relevance feedback approach that is based on one-class classification is also integrated. The support vector data description is used for learning during feedback iterations. The experiments using the Corel data set show good results for both classification and retrieval. ©2008 IEEE.
KeywordsBag of words
Content-based image retrieval systems
Content-based image retrievals
Image indexing and retrievals
Support vector data descriptions
Content based retrieval
Indexing (of information)
Published Version (Please cite this version)http://dx.doi.org/10.1109/SIU.2008.4632723
Showing items related by title, author, creator and subject.
Sener F.; Ikizler-Cinbis, N. (Elsevier Ltd, 2014)Text-based image retrieval may perform poorly due to the irrelevant and/or incomplete text surrounding the images in the web pages. In such situations, visual content of the images can be leveraged to improve the image ...
Gürkök H.; Karamuftuoglu, M.; Schaal, M. (2008)Traditionally, information retrieval systems rank documents according to the query terms they contain. However, even if a document may contain all query terms, this does not guarantee that it is relevant to the query. The ...
Can, F.; Altingövde I.S.; Demir, E. (Elsevier, 2004)Our research shows that for large databases, without considerable additional storage overhead, cluster-based retrieval (CBR) can compete with the time efficiency and effectiveness of the inverted index-based full search ...