Open AccessPERBANDINGAN ALGORITMA CANNY EDGE DETECTION DAN PREWITT PADA DETEKSI STADIUM DIABETIK RETINOPATI
Author(s) -
Vina Ardelia Effendy,
Febri Maspiyanti
Publication year - 2021
Publication title -
jif: jurnal imiah informatika/jurnal ilmiah informatika
Language(s) - English
Resource type - Journals
eISSN - 2615-1049
pISSN - 2337-8379
DOI - 10.33884/jif.v9i02.3762
Subject(s) - prewitt operator , canny edge detector , diabetic retinopathy , blindness , computer science , fundus (uterus) , artificial intelligence , edge detection , diabetes mellitus , retinopathy , medicine , computer vision , image processing , ophthalmology , optometry , image (mathematics) , endocrinology
Diabetes is a serious threat to human health. In 2016, non-communicable diseases including Diabetes accounted for 70% of the total causes of death in the world. Diabetes if left unchecked will cause complications that can attack other organs to cause blindness called Diabetic Retinopathy (DR). Ophthalmologists make a grouping of diabetic characteristics of retinopathy by observing the retinal images of the eye taken using a fundus camera. This method requires a long time in the observation that allows errors in making observations, so image processing is needed to detect and classify the stage of diabetic retinopathy suffered by the patient. Thus, this research aims to help the process of early treatment of patients with diabetic retinopathy so as not to cause blindness. The data used in this study is DB0 Diaret data with a pixel size of 128 x 104 and the amount of data is 131. The methods used in this system include Canny Edge Detection, Prewitt, and stadium readings using Artificial Neural Network Algorithms. In this study the highest accuracy results obtained on the Canny Edge Detection method with a value of 90% while the Prewitt method has a 79% result. So, we get the conclusion that Canny Edge Detection is considered better.