GDL

Journal from gdlhub / 2019-11-15 10:58:24
Oleh : Anugerah Galang Persada, Ahmad Nasikun, Igi Ardiyanto, Hanung Adi Nugroho, JNTETI
Dibuat : 2018-07-25, dengan 1 file

Keyword : Kompresi citra, diabetic retinopathy, microaneurysms detections, deep learning
Url : http://ejnteti.jteti.ugm.ac.id/index.php/JNTETI/article/view/403
Sumber pengambilan dokumen : WEB

Diabetes is one of the most serious diseases that commonly suffered by people around the world, including Indonesia. Early symptoms of diabetes could be observed from various indicators, one of which is through the retina. Retina conditions is affected by diabetics and when remain unproperly threated could lead to blindness. This retinal disorders due to diabetes is normally called Diabetic Retinopathy (DR). One method that able to distinguish and detect DR is microaneurysm detection. This method requires good quality of retinal images. However, in certain areas such as rural areas, this requirement may difficult to meet due to lack of adequate infrastructure. One solution that may overcome this problem is to compress the images. In this paper, image compression algorithms were applied to the retinal image, and then used to detect microaneuryms through Deep Learning-based systems. The result shows that the most stable and appropriate algorithm is PNG, which is able to correctly classify around 83% in accuracy with 5,5% variance.

Beri Komentar ?#(0) | Bookmark

Properti	Nilai Properti
ID Publisher	gdlhub
Organisasi	JNTETI
Nama Kontak	Herti Yani, S.Kom
Alamat	Jln. Jenderal Sudirman
Kota	Jambi
Daerah	Jambi
Negara	Indonesia
Telepon	0741-35095
Fax	0741-35093
E-mail Administrator	elibrarystikom@gmail.com
E-mail CKO	elibrarystikom@gmail.com