A STUDY OF EXUDATE SEGMENTATION TECHNIQUES FOR FUNDUS IMAGES

The major reason behind new blindness and vision defects in working-age people, diabetic retinopathy is really a serious public health problem in developed countries. Automatic identification of diabetic retinopathy lesions, such as for instance exudates, in fundus images can subscribe to early diagnosis. Currently, many studies in the literature have reported on segmenting exudates, but none of the techniques performs as needed. Moreover, segment exudates with a new unsupervised approach on the basis of the ant colony optimization algorithm indicate better results nonetheless it is suffering from the effectation of the noise. In this paper, a survey on various image segmentation techniques has been done. From the survey, it's been discovered that none of the technique performs effectively in most fields. Consequently the paper ends with the long run scope to overcome these issues.