Share Email Print

Journal of Electronic Imaging

Feature integration and relevance feedback analysis in image similarity evaluation
Author(s): Augusto Celentano; Eugenio Di Sciascio
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

In this article we describe the results of a study on similarity evaluation in image retrieval using color, object orientation, and relative position as content features, in a framework oriented to image repositories where the semantics of stored images are limited to a specific domain. The focus is not on a complete description of image content, which is supposed to be known to some extent, but on the extraction of simple and immediate features that can assure, through their combination, automated image analysis and efficient retrieval. Relevance feedback is introduced as an effective way to improve retrieval accuracy. A simple prototype system is also introduced that computes feature descriptors and allows users to enter queries, browse the retrieved images, and refine the results through relevance feedback analysis.

Paper Details

Date Published: 1 April 1998
PDF: 10 pages
J. Electron. Imag. 7(2) doi: 10.1117/1.482646
Published in: Journal of Electronic Imaging Volume 7, Issue 2
Show Author Affiliations
Augusto Celentano, Univ. Ca' Foscari di Venezia (Italy)
Eugenio Di Sciascio, Univ. di Bari (Italy)

© SPIE. Terms of Use
Back to Top