DIAGNOSIS OF RETINAL DISEASE USING ADAPTIVE NEURO FUZZY INFERENCE SYSTEM
C.Vinodhini1, R.Manjula Devi2
1 PG Student, 2 Assistant Professor [SG]
1,2Department of ECE,National Engineering College (Autonomous), Kovilpatti, Tamilnadu, India.
Image processing is a method in order to perform some operations on an image, mainly to get enhanced image. Image segmentation is the process of partitioning a digital image into multiple segments. Retinal images can be viewed using SLO fundus camera which provide detailed views of the different layers inside a human cornea. Some retinal problems and diseases can occur in one or more of the main corneal layers such as the epithelium and endothelium. In this paper, a unique approach to automatically extract the true retinal area from image based on image processing and machine learning approaches is performed.ANN is a parallel distributed information processor made of simple processing units. ANN is not effective to obtain the abnormal image of retina and it provides multilevel performance. Therefore misclassification rate occurs in the system. In order to reduce the error work, feature extraction was performed using texture and then the classification was done. The results obtained with accuracy of 93%.ANFIS provide output linearly. Finally the performance analysis is compared between ANN and ANFIS.
