期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2014
卷号：3
期号：3
页码：679-682
出版社：Shri Pannalal Research Institute of Technolgy
摘要：While detecting tumor in Magnetic Resonance Image (MRI) segmentation plays crucial role, because of complexity of MRI segmentation task is not flexible. 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 images (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.
