Brain MR Image segmentation using type-2 fuzzy clustering algorithm using global and local entropies

Abstract

In this thesis work, we proposed a segmentation algorithm by which we can segment a noisy 3D brain MR image which also contains high Intensity Inhomogeneity(IIH). Using standard fuzzy clustering algorithm (FCM) we fail to achieve comparable segmentation accuracy. As the segmentation is not so perfect, it becomes hard to find the abnormality or the diseases in the tissue area. To mitigate this problem, we considered so many algorithms that are based on standard FCM algorithm. Among them the entropy based algorithms reduces the uncertainty of a voxel being in a cluster. Those algorithms perform well in some scenarios but appears to fail in majority of cases. In this paper we tried to improve the performance of a particular entropy based clustering algorithm by applying type-2 fuzzy. For this we have considered two types of entropy, one is local entropy and another one is Global entropy. This type-2 fuzzy clustering algorithm gives us a better segmentation result by considering the global and local entropy