Two different multi-kernels integration with spatial information in fuzzy C-means algorithm for medical image segmentation

This paper proposes a new procedure for medical image segmentation using the integration of two different multi-kernels with spatial information in fuzzy c-means algorithm. In literature, it has proved that the multi-kernels outperform the single kernels. In this paper, the integration of two hyperbolic tangent kernels and two Gaussian kernels are used in the proposed algorithm for clustering of images. The performance of the proposed algorithm is tested on OASISMRI image dataset. The performance is tested in terms of V_pc, V_pe and Silhouette Value on OASIS-MRI dataset. The results after investigation, the proposed method shows a significant improvement as compared to other existing methods in terms of score, NI and TM under different Gaussian noises on OASIS-MRI dataset.