Retinal Blood Vessel Extraction using image enhancement and Fuzzy C-means Clustering


YAVUZ Z., KÖSE C.

The 4th International Fuzzy Systems Symposium, İstanbul, Turkey, 5 - 06 November 2015, vol.1, no.1, pp.255-259

  • Publication Type: Conference Paper / Full Text
  • Volume: 1
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.255-259

Abstract

 Retinal blood vessel segmentation is an important step  for  diagnosis  of  retinal  diseases.  An  automatic  vessel  extraction technique can help specialist for this purpose. In this paper a new method is developed to extract vessel structures in retinal  fundus  images.  Firstly,  an  enhancement  procedure including  Gabor  Filter  is  performed  to  increase  contrast  between  vessels  and  background  after  a  preprocessing  step.  Afterward, top-hat transform is applied to gabor filter response 
in order to make blood vessels more accurate. The output of the transformations is converted to binary image with a  modified Fuzzy C-means clustering  method.  The  images  obtained  from STARE and DRIVE databases which are available  online are 
used in order to test the developed system. A promising result is finally reached which are 95.63% and 95.80% of accuracy for STARE and DRIVE database respectively.