Abstract
Image retrieval has great potential for a variety of tasks in medicine but is currently underdeveloped. For the ImageCLEF 2005 medical task, we developed a context-based retrieval system. We then conducted our experiment using an automatic query, a manual query, and a manual/visual query. The best results were obtained from manual modification of queries, while combining those results with data from content-based image retrieval had a detrimental effect.
Original language | English (US) |
---|---|
Journal | CEUR Workshop Proceedings |
Volume | 1171 |
State | Published - 2005 |
Event | 2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005 - Wien, Austria Duration: Sep 21 2005 → Sep 22 2005 |
Keywords
- Question answering
- Questions beyond factoids
ASJC Scopus subject areas
- Computer Science(all)