Image denoising using discrete wavelet transform and adaptive thresholding optimised with improved arithmetic optimisation algorithm and guided filter
by M. Mohana Dhas; N. Suresh Singh
International Journal of Computational Intelligence Studies (IJCISTUDIES), Vol. 11, No. 2, 2022

Abstract: The identification and characterisation of blood cells are needed for the diagnosis of blood-related diseases. To identify and classify different types of blood cells, image processing techniques are necessary. However, the medical images are generally corrupted with different types of noises. These noises affect the quality of images and causes impact in image processing. Denoising is a pre-processing method in image processing to acquire clear vision, eliminate noise, and enhance the quality of images. In this paper, a novel approach for medical image denoising based on discrete wavelet transform (DWT) and adaptive thresholding optimised with improved arithmetic optimisation algorithm and guided filter is proposed. Initially, the input image is denoised using DWT. Then, the denoised image is again processed with a guided filter for enhancing and improving the denoising performance. Moreover, from the experimental analysis, it is proven that the proposed approach provides better performance than the existing denoising methods.

Online publication date: Fri, 11-Nov-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Intelligence Studies (IJCISTUDIES):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com