Share Email Print
cover

Proceedings Paper

Automatic quantitative evaluation of image registration techniques with the ε dissimilarity criterion in the case of retinal images
Author(s): Yann Gavet; Mathieu Fernandes; Jean-Charles Pinoli
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In human retina observation (with non mydriatic optical microscopes), a registration process is often employed to enlarge the field of view. For the ophthalmologist, this is a way to spare time browsing all the images. A lot of techniques have been proposed to perform this registration process, and indeed, its good evaluation is a question that can be raised. This article presents the use of the ε dissimilarity criterion to evaluate and compare some classical featurebased image registration techniques. The problem of retina images registration is employed as an example, but it could also be used in other applications. The images are first segmented and these segmentations are registered. The good quality of this registration is evaluated with the dissimilarity criterion for 25 pairs of images with a manual selection of control points. This study can be useful in order to choose the type of registration method and to evaluate the results of a new one.

Paper Details

Date Published: 12 July 2011
PDF: 8 pages
Proc. SPIE 8000, Tenth International Conference on Quality Control by Artificial Vision, 80000H (12 July 2011); doi: 10.1117/12.890883
Show Author Affiliations
Yann Gavet, CIS-LPMG, CNRS, Ecole Nationale Supérieure des Mines de Saint-Etienne (France)
Mathieu Fernandes, CIS-LPMG, CNRS, Ecole Nationale Supérieure des Mines de Saint-Etienne (France)
Jean-Charles Pinoli, CIS-LPMG, CNRS, Ecole Nationale Supérieure des Mines de Saint-Etienne (France)


Published in SPIE Proceedings Vol. 8000:
Tenth International Conference on Quality Control by Artificial Vision
Jean-Charles Pinoli; Johan Debayle; Yann Gavet; Frédéric Gruy; Claude Lambert, Editor(s)

© SPIE. Terms of Use
Back to Top