The High-Resolution Fundus (HRF) Image Database comprises 45 fundus images: 15 images from healthy individuals, 15 from patients with diabetic retinopathy, and 15 from glaucomatous patients. Each image is accompanied by manually labeled vessel segmentation maps (gold standard) and field of view (FOV) masks.
For further details and to access the dataset, please visit the HRF Image Database.
If you use this resource for your research, please cite:
Budai, Attila; Bock, Rüdiger; Maier, Andreas; Hornegger, Joachim; Michelson, Georg. "Robust Vessel Segmentation in Fundus Images." International Journal of Biomedical Imaging, vol. 2013, 2013.