SEGMENTASI CITRA RETINA MENGGUNAKAN PENDEKATAN METODE SEGMENTASI SEMANTIK

HANSEN, FRISKA ARDHANA and Erwin, Erwin (2022) SEGMENTASI CITRA RETINA MENGGUNAKAN PENDEKATAN METODE SEGMENTASI SEMANTIK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181823001.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011181823001_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
Preview	Text RAMA_56201_09011181823001_0029017101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011181823001_0029017101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (795kB) | Request a copy
	Text RAMA_56201_09011181823001_0029017101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (544kB) | Request a copy
	Text RAMA_56201_09011181823001_0029017101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181823001_0029017101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (148kB) | Request a copy
	Text RAMA_56201_09011181823001_0029017101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (104kB) | Request a copy
	Text RAMA_56201_09011181823001_0029017101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (560kB) | Request a copy

Abstract

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%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	segmentasi retina
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Friska Ardhana Hansen
Date Deposited:	21 Sep 2022 05:35
Last Modified:	21 Sep 2022 05:35
URI:	http://repository.unsri.ac.id/id/eprint/79254

Actions (login required)

View Item