IMPLEMENTATION OF FRACTAL DIMENSIONS BOX COUNTING AND K-MEANS IN THE CLASSIFICATION OF EYE DISEASES BASED ON RETINAL FUNDUS IMAGES

Abstract

The eyes are one part of the body that has an important role in human life. Like vision, the eye has parts that have their respective functions, both the outer parts such as the eyelids and eyebrows, and the inner parts of the eye such as the cornea, retina, and pupil. Visual impairment refers to any condition that affects the eye's ability to see clearly or function optimally. Visual impairment can affect various aspects of daily life and requires appropriate care and treatment. To differentiate between various types of eye disease, you can take pictures of the fundus of the retina. In this study, an introduction to the characteristics of each eye disease was carried out, namely Diabetic Retinopathy, Pathological Myopia, Hypertension Retinopathy, and Macular Degeneration. A total of 100 retinal fundus images were used in this research. The first step was to convert the image into RGB form and then carry out several image segmentation processes on the retinal fundus, namely green channel, CLAHE, morphological opening, and complement image (negative image). The image is then used to identify eye disease using edge detection using the Canny method. Furthermore, by using the
fractal dimension box-counting method, the resulting dimensional values are used in the clustering process. The resulting dimension values will be classified using the K-means grouping method with five clusters with an accuracy of 89%.
Keywords: Diabetic Retinopathy, Pathological Myopia, Hypertension Retinopathy, Age-related Macular Degeneration, Box Counting, K-Means.