Automatic Optic Disc Detection in Retinal Images Using FKMT‒MOPDF

In recent days, detecting Optic Disc (OD) in retinal images has been challenging and very important to the early diagnosis of eye diseases. The process OD is due diversity color, intensity, brightness shape OD. Moreover, color similarities neighboring organs create difficulties during detection. proposed Fuzzy K‒Means Threshold (FKMT) Morphological Operation with Pixel Density Feature (MOPDF), input are coarsely segmented by fuzzy K‒means clustering thresholding, which classified from its intensity similarities. Then, given as morphological operation pixel density feature calculations, reduce false detection small Finally, area detected applying Sobel edge method, accurately detects images. After optimization, method achieved Sensitivity (SEN), Specificity (SPEC) Accuracy (ACC), 96.74%, 96.78% 96.92% DiaretDB0 (Standard Diabetic Retinopathy Database Calibration level 0), 97.12%, 97.10% 97.75% DiaretDB1 1) 97.19%, 97.47% 97.43% STARE (Structured Analysis Retina) dataset respectively. experimental results demonstrated method’s efficiency for segmenting areas.