Share Email Print
cover

Proceedings Paper

Quantitative evaluation of color image segmentation results using fuzzy neural network
Author(s): Didier Coquin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper we consider the problem of the automatic evaluation of the results of color image segmentation. There are supervised evaluation criteria based on the computation of the dissimilarity measure between segmentation result and ground truth. Also, there are unsupervised evaluation criteria that enable the quality of a segmentation result without any a priori knowledge. Here, starting from the criteria, we retained six attributes which are summarized in a performance vector and will be used for an evaluation based on a fuzzy neural network.

Paper Details

Date Published: 17 November 2008
PDF: 8 pages
Proc. SPIE 7266, Optomechatronic Technologies 2008, 72661G (17 November 2008); doi: 10.1117/12.807286
Show Author Affiliations
Didier Coquin, LISTIC, Domaine Univ. (France)


Published in SPIE Proceedings Vol. 7266:
Optomechatronic Technologies 2008

© SPIE. Terms of Use
Back to Top