期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：5
页码：6089-6093
出版社：TechScience Publications
摘要：An important goal of medical image processing is to transfer images into better form for easy representation and evaluation. An important step in this transformation is image segmentation i.e. based on given homogeneity criteria to partition the image into segments. After this, the exact shape and appearance features of segments can be calculated and they can be used for clinical evaluation. Fuzzy c-means clustering method has been widely used for medical image segmentation. As medical images are frequently corroded by noise and the FCM algorithm is more sensitive to this noise. Thus in this paper, we propose optimization of this algorithm by using hybrid of genetic algorithm and particle swarm optimization algorithm. The results of this method are compared with basic segmentation methods like FCM and KFCM using quality parameters like: Rand index, Global consistency error and Variation. Experiments show that the proposed method is more effective and efficient.
