SIGIR'98 posters: Using Global Colour Features for General Photographic Image Indexing and Retrieval

Using Global Colour Features for General Photographic Image Indexing and Retrieval


Ting-Sheng Lai
School of Computing and Information Systems, The University of Sunderland, Sunderland SR6 0DD, U.K.

John Tait
School of Computing and Information Systems, The University of Sunderland, Sunderland SR6 0DD, U.K.


Abstract

At the present time there is a growing demand for the development of content-based image retrieval. This paper attempts to address the problems of indexing and retrieval of general photographic images. An indexing and retrieval scheme is introduced which models human colour perception. An initial evaluation of an implementation of the scheme reveals reasonable classification effectiveness, and a refinement method is proposed to overcome the problem of intrinsic colour appearance encountered with the implementation.


SIGIR'98
24-28 August 1998
Melbourne, Australia.
sigir98@cs.mu.oz.au.