ABSTRACT

In this paper, we analyzed the segmentation of MRI brain image into different tissue types on brain image using Possibilistic fuzzy c-means (PFCM) clustering. Application of this method to MRI brain image gives the better segmentation result in compare with Fuzzy c-mean (FCM) and fuzzy possibilistic c-means (FPCM). The results are verified quantitatively using similarity metrics, false positive volumes function (FPVF) and false negative volume functions (FNVF).These values are shows that PFCM segments the tumor class effectively. This is achieved by effectively utilizing the membership and possibility (typicality) function in the PFCM.