关键词: 遗传算法, 形态学, 医学图像, 信噪比

Abstract: Filtering is a very important preprocessing procedure for medical image.For the limitation of morphology filtering,the paper proposes genetic algorithm-based morphology filtering.First constructs appropriate fitness function and learned sample noise image,then adjusts adaptively the size and shape of structure elements and the median filtering window by genetic algorithm,the optimized combination of median filtering windows and structure elements is found,which can filter the medical image efficiently.The experimental result shows that the signal noise ratio of filtered medical image increases more by the proposed novel method than by morphology filtering and median filtering.

Key words: genetic algorithm, morphology, medical image, signal noise ratio