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.
Medical Image Segmentation and Detection of MR Images Based on Spatial Multiple-Kernel Fuzzy C-Means Algorithm
2015-09-01
oai:zenodo.org:1109073
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Fast automatic medical image segmentation based on spatial kernel fuzzy c-means on level set method
British Library Online Contents | 2014
|An adaptive spatial information-theoretic fuzzy clustering algorithm for image segmentation
British Library Online Contents | 2013
|Genetic algorithm-based interactive segmentation of 3D medical images
British Library Online Contents | 1999
|Fuzzy C-Means Image Segmentation Approach for Axle-Based Vehicle Classification
Transportation Research Record | 2016
|