METODE CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK SEGMENTASI OPTIK DISK PADA CITRA RETINA

SEPRIANTINA, PERSIA and Erwin, Erwin (2021) METODE CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK SEGMENTASI OPTIK DISK PADA CITRA RETINA. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181722074.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011181722074_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
Preview	Text RAMA_56201_09011181722074_0029017101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011181722074_0029017101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (662kB) | Request a copy
	Text RAMA_56201_09011181722074_0029017101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (648kB) | Request a copy
	Text RAMA_56201_09011181722074_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_09011181722074_0029017101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (185kB) | Request a copy
	Text RAMA_56201_09011181722074_0029017101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (306kB) | Request a copy
	Text RAMA_56201_09011181722074_0029017101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

The retina is one of the most important parts of the eye. One part of the retina is the optic disc. The optic disc is the starting point of the optic nerve, where the optics meet and relay information to the center and carry more than one million neurons from the eye to brain. One way to simplify the image structure is by segmenting it. Optic disk segmentation, the outhor uses the Convolutional Neural Network (CNN) method with U-Net architecture. At the pre-processing stage using grayscale, complement, augmentation is also used to increase the amount of data used. In this study using the DRIVE dataset with 99.44% accuracy, 99.88% spesification, 92.08% precision, 99.00% sensitivity and 95.33% f1 score on augmented data. While the data without augmentation result in 98.50% accuracy, 99.74% specification, 84.57% precission, 97.27% sensitivity and 89.22% f1 score.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Optik disk, Convolutional Neural Netwok, DRIVE, Augmentasi, U-Net
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Persia Sepriantina
Date Deposited:	23 Nov 2021 04:12
Last Modified:	23 Nov 2021 04:12
URI:	http://repository.unsri.ac.id/id/eprint/57795

Actions (login required)

View Item