Medical image denoising using multi-resolution wavelet transform and diffusion filter

• Main Author: Abdalrahman M. M. Albishti
• Other Authors: Dr. Ruzelita Ngadiran
• Format: Thesis
• Language: English
• Published: Universiti Malaysia Perlis (UniMAP) 2019
• Subjects: Diagnostic imaging; Medical image denoised; Wavelet transform; Diffusion filter
• Online Access: http://dspace.unimap.edu.my:80/xmlui/handle/123456789/61520

In this project medical image denoised by using proposed filter, multi-resolution wavelet transform and diffusion filter. Medical images denoised from Gaussian noise by applying the algorithms of wavelet transform and diffusion filter and both filter on Matlab and evaluate the performance of the three filters by measuring the difference between signal to noise ratio , peak-signal-to-noise ratio, root mean square error and structural similarity index. The output from wavelet filter is very close to the high quality image and there is no blurring in the output image and the output from diffusion filter was very clean from the added noise. However, the output from the proposed filter more clear than other filters and the result has the best result. From the results it can be deduced that for Gaussian noise, proposed filter always gives better quality result, where it obtained high structural similarity index compared to wavelet transform and diffusion filters.