Volume 7 Issue 1 - May 2016

  • 1. Diagnosis of diabetic retinopathy by blood vessel segmentation and exudate detection

    Authors : Lekshmi Shyam, Kumar G.s

    Pages : 208-213

    DOI : http://dx.doi.org/10.21172/1.71.029

    Keywords : ExudatesHighpassfilteringMorphologicalreconstructionHoughTransform,Imtool operator

    Abstract :

    Blindness is a growing problem all over the world. The major diseases that lead to blindness are glaucoma and diabetic retinopathy. Even though these diseases lead to irreversible blindness, it can be controlled to certain extent if detected earlier. Diabetic Retinopathy can be detected by the presence of exudates. The paper proposes a method for vessel segmentation based on high pass filtering and morphological reconstruction methods. The blood vessel segmentation is an important task in Diabetic Retinopathy detection. Optic disc in the fundus image is detected by Hough transform. After the segmentation the vessels and optic disc are removed from the original image. Diabetic Retinopathy is characterized by the presence of exudates. The exudates are detected by means of imtool operator in the matlab. The simulations are performed on matlab 2011 and the data are collected from DIARETDB1 and HRF databases.

    Citing this Journal Article :

    Lekshmi Shyam, Kumar G.s, "Diagnosis of diabetic retinopathy by blood vessel segmentation and exudate detection", Volume 7 Issue 1 - May 2016, 208-213