Detection of Diabetic Retinopathy in Fundus Images using Extreme Learning Machines
Diabetic Retinopathy (DR) is the term used to describe the retinal damage due to diabetes. Initially, diabetic retinopathy may cause none to mild symptoms but sight loss at an advanced stage. Hence detecting lesions automatically in retinal images can assist in diagnosis and screening of DR at an early stage. The detection of the different lesions in fundus images is therefore of interest. This project proposes the pre-processing of the image using a Median Filter and Contrast Limited Adaptive Histogram Equalization(CLAHE), optic disc detection using Hough Transform, feature extraction using Gray-Level Co-Occurrence Matrix (GLCM) and Extreme Learning Machines (ELM) for classification.
Keywords - Contrast Limited Adaptive Histogram Equalization (CLAHE), Diabetic Retinopathy, Gray Level Co-Occurrence Matrix (GLCM), Extreme Learning Machines (ELM), Median Filter.