FIRE: Fundus Image Registration Dataset is a retinal fundus image dataset, which has 129 fundus retinal images and is combined into 134 pairs of images according to different features. These image combinations are divided into 3 categories according to the features. The fundus images are collected by Nidek AFC-210 fundus camera with a resolution of 2912 * 2912 and a visual elevation angle of 40 degrees.

This dataset was jointly constructed by Papageorgiou Hospital and Aristotle University of Thessaloniki and released in 2017. The data came from 39 patients at the University of Thessaloniki. The main publishers are C. Hernandez-Matas, X. Zabulis, A. Triantafyllou, P. Anyfanti, S. Douma and AA Argyros. The related paper is "FIRE: Fundus Image Registration Dataset".