Abstract
In this work the problem of content-based information retrieval is approached from a new perspective. We look at a probabilistic approach in CBIR from the angle of Bayesian networks. Our data structure serves to break two bottlenecks of retrieval performance: (1) high dimensionality of feature vectors and (2) poor mapping of raw features into highlevel content that a human understands (the semantic gap). We use the network structure instead of the feature space, and propose updating the higherlevel content description by utilising the relevance feedback obtained from the user. Strategies for display update for the next iteration are studied. A new approach for selecting the next display set is tied to our data structure.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Third Dutch-Belgian Information Retrieval Workshop (DIR-2002) |
| Subtitle of host publication | Katholieke Universiteit Leuven December 6, 2002 |
| Editors | Marie-Francine Moens, Rik De Busser, Djoerd Hiemstra, Wessel Kraaij |
| Place of Publication | Leuven |
| Publisher | Katholieke Universiteit Leuven |
| Pages | 28-37 |
| Number of pages | 10 |
| Publication status | Published - 6 Dec 2002 |
| Event | 3rd Dutch-Belgian Information Retrieval Workshop, DIR 2002 - Leuven , Belgium Duration: 6 Dec 2002 → 6 Dec 2002 Conference number: 3 |
Workshop
| Workshop | 3rd Dutch-Belgian Information Retrieval Workshop, DIR 2002 |
|---|---|
| Abbreviated title | DIR |
| Country/Territory | Belgium |
| City | Leuven |
| Period | 6/12/02 → 6/12/02 |
Keywords
- DB-IR: INFORMATION RETRIEVAL
Fingerprint
Dive into the research topics of 'A scalable and efficient content-based multimedia retrieval system'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver