Data Fusion Approach in the Possibilistic context : Application to the Segmentation of MR Images

The paper presents the evaluation of the segmentation of MR images using the multispectral fusion approach in the possibility theory context. the process of fusion consists of three parts : (1) information extraction, (2) information aggregation, and (3) decision step. Information provided by T2-weighted and PDweighted images is extracted and modeled separately in each one using fuzzy logic, fuzzy maps obtained are combined with an operator which can managing the uncertainty and ambiguity in the images and the final segmented image is constructed in decision step. Some results are presented and discussed. Keywordsfusion; possibility theory; segmentation; MR images.