Macular Edema severity detection in colour fundus images based on ELM classifier

Abstract

Diabetic Macular Edema is a complication of diabetic retinopathy which is a cause of vision loss. It is assessed by detecting the hard exudates present in the color fundus images. The proposed method has two stages, there are detection of hard exudates and classification of diabetic macular edema severity from color fundus images. A feature extraction technique is used to capture the global features like intensity, color and texture of the fundus images and discriminate the normal from abnormal images. In this, the detection of hard exudates are done by using extreme learning machine classifier. This can be used to improve the detection accuracy. Disease severity classification is assessed by using regional property of the hard exudates in the retinal image. The detection performance has a sensitivity of 99% with specificity between 85% and 98%. The severity classification accuracy is 98% for the abnormal images.