Registration of retinal images from Public Health by minimising an error between vessels using an affine model with radial distortions

Guillaume Noyel (1, 2, 3) , R Thomas (4) , S Iles (5) , G Bhakta (5) , A Crowder (5) , D. Owens (4) , P. Boyle (1, 2, 3)

1 IPRI - International Prevention Research Institute
2 SIGPH@iPRI - University of Strathclyde Institute of Global Public Health
3 University of Strathclyde [Glasgow]
4 Swansea University
5 DESW - Diabetic Eye Screening Wales

In order to estimate a registration model of eye fundus images made of an affinity and two radial distortions, we introduce an estimation criterion based on an error between the vessels. In [1], we estimated this model by minimising the error between characteristics points. In this paper, the detected vessels are selected using the circle and ellipse equations of the overlap area boundaries deduced from our model. Our method successfully registers 96 % of the 271 pairs in a Public Health dataset acquired mostly with different cameras. This is better than our previous method [1] and better than three other state-of-the-art methods. On a publicly available dataset, ours still better register the images than the reference method.

Mots clés: image registration; public health; vessel error; radial distortion; Diabetic retinopathy; Diabetes; eye fundus images

Domaines: Traitement du signal et de l'image [eess.SP]; Analyse numérique [math.NA]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Santé publique et épidémiologie

Guillaume Noyel, R Thomas, S Iles, G Bhakta, A Crowder, et al.. Registration of retinal images from Public Health by minimising an error between vessels using an affine model with radial distortions. IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), IEEE, Apr 2019, Venice, Italy. pp.561-564, ⟨10.1109/ISBI.2019.8759415⟩. ⟨hal-02099845⟩