YUNINGSIH, TETY and Erwin, Erwin (2020) DETEKSI PEMBULUH DARAH RETINA PADA OPTIK DISK DENGAN MAXIMUM PRINCIPAL CURVATURE DAN CIRCULAR HOUGH TRANSFORM. Undergraduate thesis, Sriwijaya University.
Text
RAMA_56201_09011181621117.PDF - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy |
|
Text
RAMA_56201_09011181621117_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (19MB) | Request a copy |
|
Preview |
Text
RAMA_56201_09011181621117_0029017101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview |
Text
RAMA_56201_09011181621117_0029017101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (370kB) | Request a copy |
|
Text
RAMA_56201_09011181621117_0029017101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (465kB) | Request a copy |
|
Text
RAMA_56201_09011181621117_0029017101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy |
|
Text
RAMA_56201_09011181621117_0029017101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (86kB) | Request a copy |
|
Text
RAMA_56201_09011181621117_0029017101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy |
|
Text
RAMA_56201_09011181621117_0029017101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (90kB) | Request a copy |
Abstract
The retina is the part of the eye that protects parts of light-sensitive cells. The retina consists of four main parts namely the blood vessel system, Fovea, Macula and Optical Disks. Blood vessels become one of the characteristics that can help in the diagnosis of various retinal diseases. This research discusses about application of algorithms for detection blood vessels in optic disc. Segmentation of blood vessels using the Maximum Principal Curvature algorithm to detect lines in blood vessels that were previously filtered using input Gaussian filters, remove optical disks by reducing the gaussian filter with the result of Maximum Principal Curvature, segmentation of blood vessels uses wolf thresholding to convert images into binary images, Remove Small Object and erosi morphology to remove fine lines that are not blood vessels. Detection optic disc using Sobel edge detection and circular hough transform. In optic disc detection the input image is converted to grayscale and then complemented and improved contrast using Contrast-Limited Adaptive Histogram Equalization. Then the opening morphology and median filter were performed. After that, the Sobel edge and circular hough transform methods are applied to detect the location of the optic disc. After getting the blood vessel segmentation and detection optic disc last stage is combining the results of blood vessel segmentation with optic disc. The methods applied are quite efficient in detecting blood vessels and detection optic disc.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Maximum principal curvature . Wolf thresholding . Blood vessel . Sobel edge detection. Circular hough transform. |
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: | Users 6918 not found. |
Date Deposited: | 06 Aug 2020 03:08 |
Last Modified: | 06 Aug 2020 03:08 |
URI: | http://repository.unsri.ac.id/id/eprint/32232 |
Actions (login required)
View Item |