Abstract
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.
Highlights
Diabetes is a serious threat to human health
Ophthalmologists make a grouping of diabetic characteristics of retinopathy
This method requires a long time in observation that allows errors in making observations
Summary
Diabetes merupakan salah satu ancaman serius untuk kesehatan manusia. Pada tahun 2016, penyakit tidak menular termasuk Diabetes Melitus (DM), memiliki angka 70% dari total penyebab kematian didunia dan Indonesia pun menghadapi ancaman diabetes. Tanda-tanda penderita diabetik retinopati akan diproses dengan ekstraksi ciri menggunakan metode Canny Edge Detection dan Prewitt yang diharapkan dapat melakukan pencarian ciri yang dapat digunakan sebagai klasifikasi untuk proses kedepannya. Namun, seiring berjalannya waktu, dibutuhkan pendeteksian yang lebih akurat terutama untuk stadium penderita DR untuk penanganan selanjutnya, sedangkan pada penelitian ini hanya mendeteksi dua kategori yaitu normal dan tidak normal. Berdasarkan pemaparan diatas, baik latar belakang serta metode yang sudah dijelaskan maka dilakukan penelitian yang berjudul Perbandingan Metode Canny Edge Detection dan Prewitt pada Deteksi Stadium Diabetik Retinopati. Penelitian ini memiliki tujuan untuk melakukan perbandingan penggunaan metode Canny Edge Detection dan Prewitt pada proses deteksi stadium diabetik retinopati. Proses penelitian ini dilakukan dua tahap penelitian, yaitu pendeteksian diabetik retinopati serta perbadingan presentase hasil penggunaan metode Canny Edge Detection dan Prewitt. Teknik evaluasi dilakukan dengan cara membandingkan presentase hasil akurasi dengan set data yang dimiliki menggunakan pembagian validasi data K-Fold dan teknik evaluasi akurasi [7]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
