Share Email Print

Proceedings Paper

Color image comparison and visual perception: a process for descriptor validation
Author(s): Eric Favier; Eric Dinet; Alain Tremeau
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In some specific problems, a gray scale analysis is unfortunately not sufficient: color is necessarily required. Generally in these kinds of problems it is necessary to be able to quantify the quality of an image in accordance with a reference one and the quality of a process in accordance with another one (for example to evaluate degradations introduced when compressing color images). Such quantifications must provide results correlated with human vision since color image quality is generally evaluated by human observers. In a first time we have developed objective local descriptors for the evaluation of quality of color images. Then we have established a process to validate the accuracy and the correlation of these descriptors with human visual perception. The goal of this paper is to expose how we determine during an experimental process whether retained descriptors are correlated with a visual classification of color images based on their quality. We describe the whole experimental process used to study this correlation. We also expose results obtained through the experimental process.

Paper Details

Date Published: 7 September 1998
PDF: 10 pages
Proc. SPIE 3409, Electronic Imaging: Processing, Printing, and Publishing in Color, (7 September 1998); doi: 10.1117/12.324097
Show Author Affiliations
Eric Favier, Univ. Jean Monnet de Saint-Etienne (France)
Eric Dinet, Univ. Jean Monnet de Saint-Etienne (France)
Alain Tremeau, Univ. Jean Monnet de Saint-Etienne (France)

Published in SPIE Proceedings Vol. 3409:
Electronic Imaging: Processing, Printing, and Publishing in Color
Jan Bares, Editor(s)

© SPIE. Terms of Use
Back to Top