Proceedings of the International Conference
I W S S I P   2005
12th INTERNATIONAL WORKSHOP ON SYSTEMS, SIGNALS & IMAGE PROCESSING

22 - 24 September 2005, Chalkida Greece
 
(from Chapter 1: Invited Addresses and Tutorials on Signals, Coding, Systems and Intelligent Techniques)

 Full Citation and Abstract

0 Title: Object-driven content-based image retrieval
  Author(s): Ioannis Pratikakis, Basilios Gatos, Stavros Perantonis, Iris Vanhamel, Hichem Sahli
  Address: Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research
Demokritos
, 153 10 Athens, Greece
Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research
Demokritos
, 153 10 Athens, Greece
Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research
Demokritos
, 153 10 Athens, Greece
Electronics & Informatics Department Vrije Universiteit Brussel, 1050 Brussels,Belgium
Electronics & Informatics Department Vrije Universiteit Brussel, 1050 Brussels,Belgium
ipratika @ iit.demokritos.gr, bgat @ iit.demokritos.gr, sper @ iit.demokritos.gr, iuvanham @ etro.vub.ac.be, hsahli @ etro.vub.ac.be
  Reference: SSIP-SP1, 2005  pp. 189 - 193
  Abstract/
Summary
This paper presents a novel unsupervised strategy for content-based image retrieval. It is based on a meaningful segmentation procedure that can provide proper distributions for matching via the Earth mover's distance as a similarity metric. The segmentation procedure is based on a hierarchical watershed-driven algorithm that extracts meaningful regions automatically. In this framework, the proposed robust feature extraction and the many-to-many region matching along with the novel region weighting for enhancing feature discrimination play a major role. Experimental results demonstrate the performance of the proposed strategy.
 
PDF  View Full PDF
 only subscribers
 
PDF  Order by phone
 or buy On-line
 

 We welcome your comments about this Article