Quantitative evaluation of image registration techniques in the case of retinal images

Yann Gavet (1, 2, 3, 4) , Mathieu Fernandes (1, 2, 3, 4) , Jean-Charles Pinoli (1, 2, 3, 4)

1 CIS-ENSMSE - Centre Ingénierie et Santé
2 DIM-ENSMSE - Département Imagerie et Morphologie
3 LPMG-EMSE - Laboratoire des Procédés en Milieux Granulaires
4 IFRESIS - Institut Fédératif de Recherche en Sciences et Ingénierie de la Santé

In human retina observation (with non mydriatic optical microscopes), an image registration process is often employed to enlarge the field of view. Analyzing all the images takes a lot of time. Numerous techniques have been proposed to perform the registration process. Its good evaluation is a difficult question that is then raising. This article presents the use of two quantitative criterions to evaluate and compare some classical feature-based image registration techniques. The images are first segmented and the resulting binary images are then registered. The good quality of the registration process is evaluated with a normalized criterion based on the ϵ dissimilarity criterion, and the figure of merit criterion (fom), for 25 pairs of images with a manual selection of control points. These criterions are normalized by the results of the affine method (considered as the most simple method). Then, for each pair, the influence of the number of points used to perform the registration is evaluated.

Mots clés: image registration; human retina; dissimilarity criterion

Domaines: Génie des procédés; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Yann Gavet, Mathieu Fernandes, Jean-Charles Pinoli. Quantitative evaluation of image registration techniques in the case of retinal images. Journal of Electronic Imaging, 2012, 21 (2), pp.21118. ⟨10.1117/1.JEI.21.2.021118⟩. ⟨hal-00700870⟩