为了更好地改善图像分割效果,提出一种自适应空间信息的模糊聚类算法(adaptive spatial information fuzzy clustering,ASIFC)。算法将图像空间信息与FCM算法相结合,改进了FCM算法的目标函数;使用信息最大化识别噪声数据和消除异常值。在合成图像和核磁共振脑部图像数据库Brainweb上的实验结果表明,该算法能自适应地实现图像分割,有效识别噪声数据,解决了FCM的空间信息缺乏问题,增强了算法的鲁棒性,相比其他几种较新的聚类算法,取得了更好的分割效果。
This paper presented an adaptive spatial information fuzzy clustering algorithm to improve the image segmentation effect. The algorithm combined spatial information of image and FCM algorithm, which improved the objective function of FCM. At the same time,it used information maximization to identify noise data and eliminated outliers. Experiment results on composite images and MRI brain image database Brainweb show that the presented algorithm can segment image adaptively and identify noise data effectively. The algorithm can also solve the lack of spatial information using FCM to segment images, improve algorithm robustness. The proposed algorithm has better image segmentation effect than several advanced clustering algorithms.