Open Science Research Excellence
%0 Journal Article
%A J. Mehena and  M. C. Adhikary
%D 2015 
%J  International Journal of Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering
%B World Academy of Science, Engineering and Technology
%I International Science Index 102, 2015
%T Medical Image Segmentation and Detection of MR Images Based on Spatial Multiple-Kernel Fuzzy C-Means Algorithm
%U http://waset.org/publications/10002499
%V 102
%X In this paper, a spatial multiple-kernel fuzzy C-means (SMKFCM) algorithm is introduced for segmentation problem. A linear combination of multiples kernels with spatial information is used in the kernel FCM (KFCM) and the updating rules for the linear coefficients of the composite kernels are derived as well. Fuzzy cmeans (FCM) based techniques have been widely used in medical image segmentation problem due to their simplicity and fast convergence. The proposed SMKFCM algorithm provides us a new flexible vehicle to fuse different pixel information in medical image segmentation and detection of MR images. To evaluate the robustness of the proposed segmentation algorithm in noisy environment, we add noise in medical brain tumor MR images and calculated the success rate and segmentation accuracy. From the experimental results it is clear that the proposed algorithm has better performance than those of other FCM based techniques for noisy medical MR images.
%P 518 - 522