This paper presents an automatic method for exudate detection from colour fundus images based on Differential Morphological Profile (DMP).The detection of exudates is important for the identification of eye diseases such as diabetic retinopathy. The method involves of three main phases. In the first phase, pre processing tasks like Gaussian smoothing and contrast enhancement is done. In the second phase, DMP is applied on the pre-processed image. The image obtained from DMP contains highlighted bright regions consisting of exudates and optic disc. In the next phase, feature extraction based on location of optic disc, shape index and area is done to obtain actual exudates. The performance of the proposed method is evaluated by applying it on the DIARETDB1 database. The specificity, sensitivity and PPV of the proposed method were compared with two other methods. The results show that the proposed method gives better results than the other conventional methods.
展开▼
