Three Models Based Data Fusion Approach for the Segmentation of MR Images : A Comparative Study

In this paper, we propose an automatic segmentation technique of multispectral magnetic resonance image (MRI) of the brain using three models based data fusion approach through the framework of the possibility theory. The fusion process is decomposed into three fundamental phases. Firstly, we modeling information extracted from the various images in a common framework, in this step the retained formalism is FPCM algorithm . in the second phase an operator of fusion is used to combine then this information by taking account redundancies and complementarities of data. We build a Synthetic information to exploit the fusion results in the last phase. Some results are presented and discussed.