Brain image segmentation using fuzzy classifiers

A rule-based approach is proposed here for brain tissue segmentation in magnetic resonance images (MRI). By combining a thresholding method, which is fast and easy to implement, and fuzzy rules, which can deal with uncertain or ambiguous data, the proposed segmentation method outperforms the existing conventional methods. The results of the proposed method have been compared to that obtained with the well-known fuzzy c-means algorithm on a typical MRI brain dataset.<
>