In this paper, a new rule-based region growing fuzzy segmentation system, capable to segment computed tomography (CT) grayscale images into physiologically and pathologically meaningful regions for display and measurement, is presented. The proposed segmentation approach uses the Mamdani fuzzy control model and can be considered as a general CT segmentation technique. It can be used as a support tool for recognition of different kinds of brain pathologies. The system considered emulates the complexity of the standard radiological and neurological recognition, by defining appropriate linguistic variables in accordance with a priori introduced fuzzy rule base.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.