Localization of hard exudates in retinal fundus image by mathematical morphology operations

Abstract

Diabetic retinopathy is one of the leading causes of blindness in the world. Detection of hard exudates is an important step for early diagnosis in eye diseases such as Macular Edema(ME). If hard exudates were segmented precisely, laser treatments can be applied more effective for patients by surgeons. The possibility of blindness is very high when the hard exudates are very close to Macula region or Optic disc. Therefore, fast and accurate segmentation is one of the most important factors in elimination of hard exudates. In this paper, a method is proposed for segmentation of hard exudates in retinal color image based on morphological operation. In the proposed method, the retinal images preprocessed and optic disc and the blood vessels identified primarily and then they eliminate from the image. Finally, the Hard Exudates (HEs) are segmented by mixture of morphological operation such as Top-hat, Bottom-hat and reconstruction operations. The proposed method was tested on DIARETDB1 database and 78.28% of sensitivity was obtained. Comparing to other recent automatic method available in the literature, our proposed method can obtain acceptable exudates detection result in term of sensitivity.