The invention discloses an FCM diabetic retina image optic disk segmentation method, and belongs to the technical field of image processing. The method mainly comprises the following steps: step 1, acquiring a to-be-processed original fundus image R '(x, y), and carrying out image preprocessing on the image R' (x, y); step 2, carrying out blood vessel processing, including blood vessel segmentation and blood vessel erasing, on the preprocessed image R (x, y), the blood vessel segmentation mainly comprising the following parts: blood vessel enhancement, matched filtering, gray scale adjustmentand contour elimination; step 3, carrying out optic disk positioning on the image R after the blood vessel is erased; and step 4, carrying out optic disk segmentation by utilizing an FCM (fuzzy C-means) algorithm. The problems of large calculation amount, long consumed time, low accuracy and the like are solved by using the FCM algorithm, and the overall efficiency of the optic disk segmentation process is improved.