FIRE - Flexible Image Retrieval Engine: ImageCLEF 2004 Evaluation

In this paper we present FIRE, a content-based image retrieval system and the methods we used in the ImageCLEF 2004 evaluation. In FIRE, different features are available to represent images. This diversity of available features allows the user to adapt the system to task specific characteristics. A weighted combination of these features admits very flexible query formulations and helps in processing specific queries. For the ImageCLEF 2004 evaluation, we used content-based methods only and the experimental results compare favorably well with other systems that make use of the textual information in addition to the images.

• Type: Conference
• Year: 2004
• Where: CLEF
• Authors: Thomas Deselaers, Daniel Keysers, Hermann Ney
• Keywords: CLEF 2004, Content-based Image Retrieval, ImageCLEF 2004 Evaluation, flexible Query Formulations