Information selective image retrieval
Author(s) -
Guoping Qiu,
Mai Yang,
Jiwu Huang
Publication year - 2005
Publication title -
citeseer x (the pennsylvania state university)
Language(s) - English
Resource type - Conference proceedings
ISSN - 0537-9989
ISBN - 0-86341-595-4
DOI - 10.1049/ic.2005.0740
Subject(s) - computer science , image retrieval , variety (cybernetics) , image (mathematics) , information retrieval , automatic image annotation , visual word , artificial intelligence , computer vision , human–computer information retrieval , search engine
In this paper, we introduce an information theoretic concept to image retrieval by first developing a novel method to compute the amount of information contained in image parts, and then using the informative-ness of the image parts to develop a flexible information selective image retrieval (ISIR) technology. We present experimental results which show that the new method is effective and is especially useful for retrieving similar objects from a variety of different backgrounds.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom