Organising and Searching Partially Indexed Image Databases - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2002

Organising and Searching Partially Indexed Image Databases

Abstract

This paper addresses the issue of efficient retrieval from image corpora in which only a little proportion is textually indexed. We propose a hybrid approach integrating textual search with content-based retrieval. We show how a preliminary double clustering of image corpus exploited by an adequate retrieval process constitutes an answer to the pursued objective. The retrieval process takes advantage of user-system interaction via relevance feedback mechanism whose results are integrated in a virtual image. Experimental results on the PICAP prototype are reported ed and discussed to demonstrate the effectiveness of this work.
Not file

Dates and versions

inria-00100734 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100734 , version 1

Cite

Gérald Duffing, Malika Smaïl. Organising and Searching Partially Indexed Image Databases. 24th BCS-IRSG European Colloquium on Information Retrieval Research, 2002, Glasgow, Scotland, UK, 19 p. ⟨inria-00100734⟩
39 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More