Unsupervised Change-Detection in Color Fundus Images of the Human Retina

The aim of this paper is to develop an automatic method for the detection of the changes that occurred in multitemporal digital images of the fundus of the human retina, in terms of white and red spots. The images are acquired from the same patient at different times by a color fundus camera. The proposed approach is unsupervised and is based on a minimum-error thresholding technique. This technique is applied both to separate the "change" and the "no-change" classes in a suitably defined difference image, and to distinguish among different typologies of change. The algorithm is tested on 10 multitemporal pairs of images. A quantitative assessment of the change detection performances suggests that the method is able to provide accurate change maps, although possibly affected by misregistration errors or calibration/acquisition artifacts