小橋 昌司

This paper proposes an image segmentation method based on fuzzy if-then rules. It is a derivative of the conventional region growing method. This method represents expert's knowledge using fuzzy if-then rules, and embeds them as the growing criteria. To examine the proposed method, it has been applied to artificially generated images involving white Gaussian noise. In comparison with the conventional region growing method, the proposed method can segment region of interests(ROIs)with high robustness against to white noise. Moreover, it has been applied to dynamic mognetic resonance(MR)images of the Liver. The growing Criteria that represent physician's knowledge of MR images were derivedfrom the illustrated time-density curve of the liver, hepatic arteries, and veins after intravenous bolus injection. The experiments were done on three different normal volunteer with promising results.