Dear guest, welcome to this publication database. As an anonymous user, you will probably not have edit rights. Also, the collapse status of the topic tree will not be persistent. If you like to have these and other options enabled, you might ask Admin (Ivan Eggel) for a login account.
 [BibTeX] [RIS]
Multi-modal relevance feedback for medical image retrieval
Type of publication: Inproceedings
Citation:
Booktitle: SIGIR workshop on Medical Information Retrieval
Year: 2014
Location: Gold Coast, Australia
Abstract: Medical image retrieval can assist physicians in finding in- formation supporting their diagnosis. Systems that allow searching for medical images need to provide tools for quick and easy navigation and query refinement as the time for information search is often short. Relevance feedback is a powerful tool in information re- trieval. This study evaluates relevance feedback techniques with regard to the content they use. A novel relevance feed- back technique that uses both text and visual information of the results is proposed. Results show the potential of relevance feedback tech- niques in medical image retrieval and the superiority of the proposed algorithm over commonly used approaches. Future steps include integrating semantics into relevance feedback techniques to benefit of the structure knowledge of ontologies and experimenting on the fusion of text and visual information.
Userfields: A SIGIR 2014 workshop - Gold Coast, Australia - July, 11th 2014
Keywords: Content-based image retrieval, Medical image retrieval, relevance feedback
Authors Markonis, Dimitrios
Schaer, Roger
Müller, Henning
Added by: []
Total mark: 0
Attachments
  • relevance_feedback.pdf
Notes
    Topics