Content-Based Retrieval

Motivation

Images, music, video, and 3D scenes play a crucial role in Visual Information Systems and Multimedia. There is an extraordinary number of applications of such systems in entertainment, business, art, engineering, and science. Such applications often involve huge collections of media, so that efficient and effective searching in databases of these media is an important operation.

This seminar is the follow-up of the Dagstuhl Seminars on Content-Based Image and Video Retrieval in December 1999 and January 2002. One of the notable trends was the extension of the retrieval process from images and video, to also 3D scenes and music, often integrated with text. Many of the same algorithmic elements can be seen in the retrieval of these different media. We have therefore decided to broaden the scope of the seminar, and call the seminar "Content-Based Retrieval".

The emphasis of this third seminar will lie on the algorithmic aspects of all kinds of content-based retrieval. Fundamental questions such as feature extraction, pattern similarity rating, indexing large collections, and the role of perception play an important role. We strongly believe that content based retrieval needs an integrated approach from fields such as image processing, shape processing, perception, data base indexing, visualization, querying, etc. The purpose of this seminar is to bring together people from the various fields in order to promote information exchange and interaction among researchers who are interested in various aspects of accessing the content of images, music, video, and 3D data.