Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Hierarchical image database browsing environment with embedded relevance feedback and threedimensional visualization

: Meiers, T.; Keller, I.; Zimmermann, J.; Sikora, T.


Smith, J.R.:
Internet multimedia management systems III : 31 July - 1 August 2002, Boston
Bellingham, WA: SPIE, 2002 (Proceedings of SPIE 4862)
ISBN: 0-8194-4641-6
Internet Multimedia Management Systems <3, 2002, Boston>
Fraunhofer HHI ()

In recent years, there has been a growing interest in developing effective methods for searching large image databases based on image content. A commonly used method is search-by-query, that is often not satisfactory. Often it is difficult to find or produce good query images or repetitive queries tend to become trapped among a small group of undesirable images. To overcome these problems the user is to be provided with easy and intuitive access to information in image databases. In this paper we present a new browsing environment, which uses the metaphor of maps. Like street maps with different scales, from a world map to a city map, the image space is represented through "image maps" with different scales and user adapted similarity metrics. Beginning with a global view about the whole image database, containing only representative images (key images), the user can enter into any domain of the database by selecting appropriate key frames and iteratively refine the sea rch process. Three different technologies, which in combination guarantee an intuitive browsing environment, are presented. These are: (1) A hierarchical organization of the image database as basis for an efficient iterative retrieval procedure from the global view to the finest scale. (2) A new relevance feedback technique, which computes the appropriate image similarity metric based on the users interaction, and (3) An intuitive three-dimensional visualization of the result images in such a way that the mutual dissimilarity of the images matches their distances in the virtual image space, the "image map".