Home // SEMAPRO 2011, The Fifth International Conference on Advances in Semantic Processing // View article

Query Expansion for Peculiar Images by Web-extracted Hyponyms

Authors:
Shun Hattori

Keywords: image retrieval; query expansion; peculiar images; hyponymy; concept hierarchy

Abstract:
Most researches on Image Retrieval have aimed at clearing away noisy images and allowing users to retrieve only acceptable images for a target object specified by its object-name. We have become able to get enough acceptable images of a target object just by submitting its object-name to a conventional keyword-based Web image search engine. However, because the search results rarely include its uncommon images, we can often get only its common images and cannot easily get exhaustive knowledge about its appearance. As next steps of Image Retrieval, it is very important to discriminate between "Typical Images" and "Peculiar Images" in the acceptable images, and moreover, to collect many different kinds of peculiar images exhaustively. This paper proposes a novel method to search the Web for peculiar images by expanding or modifying a target object-name with its hyponyms extracted from the Web by text mining techniques, and validates its precision by comparing with Google Image Search.

Pages: 69 to 74

Copyright: Copyright (c) IARIA, 2011

Publication date: November 20, 2011

Published in: conference

ISSN: 2308-4510

ISBN: 978-1-61208-175-5

Location: Lisbon, Portugal

Dates: from November 20, 2011 to November 25, 2011