Rough sets in identification of cellular automata for medical image processing

摘要: In this paper a method is proposed which enables identification of cellular automata (CA) that extract lowlevel features in medical images. The CA problem includes determination neighbourhood and transition rule on the basis training solution uses data mining techniques based rough sets theory. Neighbourhood detected by reducts calculations rule-learning algorithms are applied to induce rules for CA. Experiments were performed explore possibility boundary detection, convex hull transformation skeletonization binary experimental results show approach allows finding useful extraction specific microscopic images blood specimens.