DETEKSI PENYAKIT DIABETIC RETINOPATHY MENGGUNAKAN FASTER RCNN DENGAN BACKBONE RESNET 101

RUMERE, ORISAM LORENSONE and Erwin, Erwin (2022) DETEKSI PENYAKIT DIABETIC RETINOPATHY MENGGUNAKAN FASTER RCNN DENGAN BACKBONE RESNET 101. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011981722131.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011981722131_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_09011981722131_0029017101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011981722131_0029017101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (422kB) | Request a copy
	Text RAMA_56201_09011981722131_0029017101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (623kB) | Request a copy
	Text RAMA_56201_09011981722131_0029017101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (811kB) | Request a copy
	Text RAMA_56201_09011981722131_0029017101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (183kB) | Request a copy
	Text RAMA_56201_09011981722131_0029017101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (299kB) | Request a copy
	Text RAMA_56201_09011981722131_0029017101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (644kB) | Request a copy

Abstract

The retina is the most important part of the human eye. Diabetic retinopathy is an eye disorder that can cause complications that trigger blockages in the blood vessels in the retina of the eye. This study presents a disease detection method on retinal images. The first step is to convert the original 700 x 605 pixels image to 400 x 300 pixels. The second stage is nonlinear digital filtering which is commonly used to remove noise in the image called median blur. The next step is to multiply the dataset with the augmented data because the data used is still small. After that, the data annotation process is carried out to identify the characteristics of the disease in the retinal image using a labeling application. In addition, disease on retinal images was detected using the resnet-101 architecture with the STARE dataset. The proposed method with the STARE dataset obtained an average value with a precision of 70.22%, an average precision of 86.58% and an over-union intersection of 86.6%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Diabetic Retinopathy (DR), Resnet-101, Citra retina, Deteksi dan Augmentasi Data.
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics > TA1632.A48 Image processing.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Orisam Lorensone Rumere
Date Deposited:	02 Nov 2022 02:07
Last Modified:	02 Nov 2022 02:07
URI:	http://repository.unsri.ac.id/id/eprint/81188

Actions (login required)

View Item