| Paper: | MP-P1.7 |
| Session: | Image and Video Storage and Retrieval II |
| Time: | Monday, September 17, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
BOOSTING OF MAXIMAL FIGURE OF MERIT CLASSIFIERS FOR AUTOMATIC IMAGE ANNOTATION |
| Authors: |
Filippo Vella; Consiglio Nazionale delle Ricerche | | |
| | Chin-Hui Lee; Georgia Institute of Technology | | |
| | Salvatore Gaglio; Consiglio Nazionale delle Ricerche | | |
| Abstract: |
Visual information contained in a scene is very complex and can be represented with multiple features describing aspects of the entire information. In this paper we propose a boosting approach to automatic image annotation by building strong classifiers based on multiple collections of weak concept classifiers with each collection focused on a single visual feature. The weak classifiers are trained with a maximal figure-of-merit learning approach. By exploiting multiple features the boosting procedure allows to build classifiers able to pick the most discriminative feature for the specific annotation task. |
