Improved Image Quality Retinal Fundus with Contrast Limited Adaptive Histogram Equalization and Filter Variation

Erwin, Erwin (2020) Improved Image Quality Retinal Fundus with Contrast Limited Adaptive Histogram Equalization and Filter Variation. In: 2019 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 24-25 Oct 2019, Jakarta.

This is the latest version of this item.

[thumbnail of PID6134669-Erwin.pdf]
Preview
Text
PID6134669-Erwin.pdf - Accepted Version

Download (1MB) | Preview
[thumbnail of IEEE Xplore Search Results.pdf]
Preview
Text
IEEE Xplore Search Results.pdf

Download (122kB) | Preview

Abstract

The use of retinal fundus images in the detection and initial diagnosis of abnormalities or diseases in the retina at this time has become one of the areas of interest to researchers, but these fundus images sometimes have low quality. Therefore, the quality of the fundus image must be improved first in order to facilitate the next process and obtain accurate results. In this study, we used the Contrast Limited Adaptive Histogram Equalization (CLAHE) method with filter order statistics, median filters, Gaussian filters, and Wiener filters using the STARE dataset to improve the quality of retinal images. In this paper, we use Mean Square Error (MSE) and Peak Signal Noise to Ratio (PSNR) as parameters for comparison between methods. From the several methods used, the lowest MSE value is 12.668 which is the result of the Order Statistical Filter and Gaussian Noise method, while the highest PSNR value is 46.58359 dB which is the result of CLAHE and Median Filter.

Item Type: Conference or Workshop Item (Paper)
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: Dr Erwin Erwin
Date Deposited: 12 Oct 2020 00:42
Last Modified: 12 Oct 2020 00:42
URI: http://repository.unsri.ac.id/id/eprint/36524

Available Versions of this Item

Actions (login required)

View Item View Item