De-Noising and Segmentation of Brain MR images by Spatial Information and K-Means Clustering

Javed, Arshad and Wang, Yin Cha and Narayanan, Kulathuramaiyer (2013) De-Noising and Segmentation of Brain MR images by Spatial Information and K-Means Clustering. Research Journal of Applied Sciences, Engineering and Technology, 6 (22). pp. 4215-4220. ISSN 2040-7459

[img] PDF
De-Noising.pdf

Download (35kB)
Official URL: http://www.maxwellsci.com/jp/abstract.php?jid=RJAS...

Abstract

Image Segmentation is the process of partitioning a digital image into non-overlapping distinct regions, so that significant information about the image could be retrieved and various analysis could be performed on that segmented image. The aim of this study is to reduce the noise, enhance the image quality by considering the spatial information without losing any important information about the images and perform the segmentation process in noise free environment. K-Means clustering technique is used for the purpose of segmentation of brain tissue classes which is considered more efficient and effective for the segmentation of an image. We tested the proposed technique on different types of brain MR images which generates good results and proved robust against noise. Conclusion had been concluded at the end of this study

Item Type: Article
Uncontrolled Keywords: Cluster validity index, image segmentation, k-means, MRI, spatial information, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak
Subjects: T Technology > T Technology (General)
Divisions: Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Faculties, Institutes, Centres > Faculty of Computer Science and Information Technology
Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Depositing User: Saman
Date Deposited: 30 Mar 2017 08:20
Last Modified: 25 Jan 2022 06:28
URI: http://ir.unimas.my/id/eprint/15750

Actions (For repository members only: login required)

View Item View Item