IRIS - a system for image and video retrieval

  • Authors:

  • P. Alshuth;Th. Hermes;Ch. Klauck;J. Kreyß;M. Röper

  • Affiliations:

  • Artificial Intelligence Group, Center for Computing Technology, University of Bremen, Germany and P. O. Box 330 440, D-28334 Bremen;Artificial Intelligence Group, Center for Computing Technology, University of Bremen, Germany and P. O. Box 330 440, D-28334 Bremen;Artificial Intelligence Group, Center for Computing Technology, University of Bremen, Germany and P. O. Box 330 440, D-28334 Bremen;Artificial Intelligence Group, Center for Computing Technology, University of Bremen, Germany and P. O. Box 330 440, D-28334 Bremen;Artificial Intelligence Group, Center for Computing Technology, University of Bremen, Germany and P. O. Box 330 440, D-28334 Bremen

  • Venue:
  • CASCON '96 Proceedings of the 1996 conference of the Centre for Advanced Studies on Collaborative research
  • Year:
  • 1996

Quantified Score

Hi-index 0.00

Visualization

Abstract

The abundance of available multimedia information (e.g.videos, audio, images) requires efficient and effective annotation and retrieval methods. The IRIS system is designed for content-based retrieval of single images. Techniques and methods from computer vision and AI are combined in a new way within IRIS. The system has been tested with single images on several domains (e.g. landscape images, technical drawings) covering a wide range of applications As videos become a more important role in the frame of multimedia, we want to include them into the IRIS system. This paper describes the methods to divide the video into shots (scenes with a common content) and to create still images for each scene with the mosaicing technique. These images can be analyzed with the IRIS system. The first results of this approach are also shown in this paper.