Automatic detection of exudates in retinal images based on threshold moving average models

Since exudates diagnostic procedures require the attention of an expert ophthalmologist, as well as regular monitoring of the disease and the workload of expert ophthalmologists will eventually exceed the current screening capabilities. Retinal imaging technology is a current practice screening capability provide a great potential solution. In this paper, a fast and robust automatic detection of exudates based on moving average histogram models of the fuzzy image, and then derives the better histogram. After segmentation of candidate exudates, the true exudates were prune based on Sobel edge detector and automatic Otsu’s thresholding algorithm is presented that results in the accurate location of the exudates in digital retinal images. To compare the performance of exudates detection methods we have constructed a large database of digital retinal images. The method was trained on a set of 200 retinal images, and tested on a completely independent set of 1 220 retinal images. Results show that the exudates detection method performs overall best sensitivity, specificity, and accuracy are 90.42, 94.60, and 93.69%, respectively.