Combining MPEG-7 based visual experts for reaching semantics


Soysal M., Alatan A.

VISUAL CONTENT PROCESSING AND REPRESENTATION, PROCEEDINGS, vol.2849, pp.66-75, 2003 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 2849
  • Publication Date: 2003
  • Journal Name: VISUAL CONTENT PROCESSING AND REPRESENTATION, PROCEEDINGS
  • Journal Indexes: Science Citation Index Expanded, Scopus, Compendex, EMBASE, MathSciNet, Philosopher's Index, zbMATH
  • Page Numbers: pp.66-75

Abstract

Semantic classification of images using low-level features is a challenging problem. Combining experts with different classifier structures, trained by MPEG-7 low-level color and texture descriptors is examined as a solution alternative. For combining different classifiers and features, two advanced decision mechanisms are proposed, one of which enjoys a significant classification performance improvement. Simulations are conducted on 8 different visual semantic classes, resulting in accuracy improvements between 3.5-6.5%, when they are compared with the best performance of single classifier systems.