The automatic detection of the optic disc location in retinal images using optic disc location regression

The automatic detection of the position of the optic disc is an important step in the automatic analysis of retinal images. A method to detect the approximate position of the optic disc using kNN regression is presented. The method starts by building a regression model of the optic disc position. Using a prior vessel segmentation all vessel pixels are searched for those which are inside the optic disc according to the regression model. The regression output is blurred to handle noise. The point which is closest to the middle of the optic disc is chosen. The method was tested on 1000 screening images and was able to find the correct position in 99.9% of all cases.