Detection of Brain Tumor in MRI Images using Mean Shift Algorithm and Normalized Cut Method
Vishal B. Padole1, D. S. Chaudhari2
1Vishal B. Padole Department Of Electronics And Telecommunication, Government college of Engineering ,Amravati Maharashtra, India.
2D. S. Chaudhari Department Of Electronics And Telecommunication, Government college of Engineering ,Amravati Maharashtra, India.
Manuscript received on may 27, 2012. | Revised Manuscript received on June 22, 2012. | Manuscript published on June 30, 2012. | PP: 53-56 | Volume-1 Issue-5, June 2012 | Retrieval Number: E0416051512/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper introduces an efficient method for detection of brain tumor from Magnetic Resonance Images (MRI). In the process of detection of tumor from MRI, segmentation plays vital role for partitioning an image into different subregion with homogeneous properties. The methodology introduced here consist of combination of two conventional algorithms i.e. Mean shift algorithm and Normalized cut (Ncut) Method which provides automatic detection of exact surface area of brain tumor in MRI. By incorporating the advantages of the mean shift segmentation and Ncut method, Magnetic Resonance image (MRI) will be preprocessed first by using the mean shift algorithm to form segmented regions, then Ncut method will be used for region nodes clustering after this connect component extraction analysis is used to locate the exact tumorous area in MRI Images.
Keywords: Mean shift, Normalized cut (NCut), tumor.