Content-Based Image and Video Retrieval

Images and video 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 images, so that efficient and effective searching for images and video is an important operation.

The previous Dagstuhl Seminar on Content-Based Image and Video Retrieval was the first one on this topic, and turned out to be a big success, as demonstrated by the following two results:

• During the seminar we collectively discussed the problems of performance evaluation and quality assessment of retrieval systems.
• A selection of the presentations will be published as a book in the Kluwer series on Computational Imaging and Vision. The book will provide a state-of-the-art overview of the field.

This motivates us to organize a follow-up seminar, with the central theme "Object recognition for image retrieval" The emphasis of this second seminar will lie on identifying the principal obstacles that hamper progress in content-based retrieval. Fundamental questions such as whether image 'understanding' is necessary for effective image 'retrieval' and whether 'low' level features are sufficient for 'high' level querying. We strongly believe that image and video retrieval need an integrated approach from fields such as image processing, shape processing, perception, data base indexing, visualization, querying, etc.

Topics to be discussed at the seminar include

• Object recognition
• Semantic-based retrieval
• Indexing schemes
• Shape, texture, color, and lay-out matching
• Relevance feedback
• Visual data modeling
• MPEG7 and JPEG2000 issues
• Retrieval system architectures
• Image and video databases
• Feature recognition
• Visualizing pictorial information
• Video segmentation
• Picture representation
• Query processing
• Perception issues
• Searching the web
• Delivery of visual information
• Benchmarking
• Application areas of image and video retrieval

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 image and video data.