UTHM Institutional Repository

Quality assessment on medical image denoising algorithm: diffusion and wavelet transform filters

Abdullah, Zaid Qays (2014) Quality assessment on medical image denoising algorithm: diffusion and wavelet transform filters. Masters thesis, Universiti Tun Hussein Onn Malaysia.

[img]
Preview
Text
ZAID_QAYS_ABDULLAH.pdf

Download (1MB) | Preview

Abstract

An image is often corrupted by noise during its acquisition and transmission process. Removing noise from the original image is still a challenging problem for researchers. Medical image carries very important information about human organs that were used for diagnosis. This project proposed techniques that will remove the noise while keeping the important information or details of the image unaffected. Image enhancement was implemented in this project to improve the quality of the images. The proposed techniques for medical image denoising are diffusion filter and discrete wavelet transform. Image quality after denoising was measured in this project based on Signal-to-Noise Ratio (SNR), Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Metric (SSIM). From the obtained results, the images were enhanced and their quality quietly high. From the measurement parameters of image quality, diffusion filter resulted in high level of image quality as given by structural similarity index metrics. The noise has been totally removed under the proposed algorithm and it can be concluded that diffusion filter resulted in removing the noise and maintaining the important details of the images. The images remained unaffected when increasing the contrast.

Item Type: Thesis (Masters)
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Depositing User: Normajihan Abd. Rahman
Date Deposited: 10 Dec 2014 07:02
Last Modified: 29 Jul 2020 07:07
URI: http://eprints.uthm.edu.my/id/eprint/6155
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year