Text

SEGMENTASI CITRA RETINA MENGGUNAKAN PENDEKATAN METODE SEGMENTASI SEMANTIK

---

Penilaian

---

Diabetic retinopathy can be diagnosed with an examination called a funduscopy. Funduscopy itself is an examination of the eye to detect disease accurately. Because diabetic retinopathy is a progressive disease, examinations are performed every six months including analysis and imaging of the retina (fundus). For ophthalmologists, evaluating retinal images is a serious burden because of the increasing number of diabetic retinopathy sufferers and the limited number of health workers. An automated method with the help of a computer is needed to analyze diabetic retinopathy so that it can help the work of ophthalmologists. Computer assistance with digital image processing can be used to analyze diabetic retinopathy, because digital images are multimedia components in the form of visual information, digital images can provide more information. Using existing techniques, the image is processed at a stage commonly known as digital digital image processing. Deep learning is a mechanical science that studies high-level abstract modeling algorithms using non-linear transformation functions. This discussion uses the Convolutional Neural Network (CNN) method with the VGGNet (Visual Geometry Group) architecture. CNN is a method used to detect and recognize objects by separating foreground and background from network image data. From the test results using the VGG method and the U-Net method as a comparison, the model uses parameters epoch 1000 and batch size 64. The VGG method produces the best results with 98.05% accuracy, mean iu/iou 89.62%, precision 90.34%, and sensitivity 87.20%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207003829	T79254	T792542022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T792542022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xv, 48 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Jurusan Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment