Research Topic

Indexing of high dimensional data in Image Database Systems.

Summary

Indexing techniques are essential for efficient search and retrieval of information from Image database systems. Existing indexing techniques, though they perform satisfactorily in low dimensions, are not suitable for indexing higher dimensional data encountered in Image database systems. This research project will investigate novel indexing techniques for image database systems, that are faster and more accurate than existing techniques. 

Publications

  1. Performance analysis of a hierarchical index structure for multimedia databases.  In Proceedings of the International Conference of Information Technology, Bubaneshwar, India, December 2003.
  2. Design of a CBIR system supporting high-level concepts. Chapter 16 of Interactive Multimedia Systems. Editor: Syed M. Rahman. IRM Press,  259-268, 2002.
  3. CHILMA: An efficient high dimensional indexing structure for image databases. In Proceedings of the First IEEE Pacific-Rim Conference on Multimedia, pages 76 - 79, December 2000.

  4. Linear Mapping Functions for High-dimensional Indexing in Image Databases. In Proceedings of the SPIE International Conference on Internet Multimedia Management Systems, Vol 4210, pages 246 - 255, November 2000.

  5. Analysis of Image Feature Mapping Functions using Statistical Parameters. In Proceedings of RMIT Computer Science Postgraduate Students Conference, pages 161 - 168, December 1998 .

  6. Indexing Spatial Data Using a Class of Mapping Functions. In Proceedings of the International Conference of Information Technology, Bubaneshwar, India, December 1998.
    Also appeared in Proceedings of RMIT Computer Science Postgraduate Students Conference, pages 47 - 56, December 1997 (Best Paper Award in CSPSC'97).