Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
|
 |
Using Pseudo-Relevance Feedback to Improve Image Retrieval Results
| |
|
Using Pseudo-Relevance Feedback to Improve Image Retrieval Results
Mouna Torjmen1  , Karen Pinel-Sauvagnat1 and Mohand Boughanem1
| (1) |
IRIT, 118 Route Narbonne, 31062 Toulouse Cedex 4, France |
Abstract
In this paper, we propose a pseudo-relevance feedback method to deal with the photographic retrieval and medical retrieval
tasks of ImageCLEF 2007. The aim of our participation to ImageCLEF is to evaluate a combination method using both english
textual queries and image queries to answer to topics. The approach processes image queries and merges them with textual queries
in order to improve results.
A first set of expirements using only textual information does not allow to obtain good results. To process image queries,
we used the FIRE system to sort similar images using low level features, and we then used associated textual information of the top images
to construct a new textual query. Results showed the interest of low level features to process image queries, as performance
increased compared to textual queries processing.
Finally, best results were obtained combining the results lists of textual queries processing and image queries processing
with a linear function.
Fulltext Preview (Small, Large)
 References secured to subscribers.
|
|
|
|
|
|