基于空间信息约束改进的FCM图像分割算法

摘要

Because the standard FCM algorithm ignores the spatial information of pixels in the iterative algorithm, this paper proposes an improved FCM algorithm for image segmentation with pixel spatial information. The new algorithm firstly computes the pixel neighborhood average value, calculate the difference between the average value of the pixel and its neighborhood , which is used as the influence weight of spatial information, construct the new objective function according to the pixel value and its spatial information, and then segment a image. The experiment results show that the new algorithm can better suppress the noise, reduce the noise sensitivity and improve the quality of image segmentation.%针对标准FCM算法在算法迭代中忽略像素的空间信息，提出了一种结合像素空间邻域信息改进的FCM图像分割算法（SAFCM）。新算法首先计算出像素的邻域平均值，然后求出邻域平均值和像素的差异，把该差异值作为空间信息的影响权值，利用像素值和空间信息构造新的目标函数，从而实现图像的分割。仿真实验表明，新算法能够更好的抑制噪声，降低噪声敏感性，提高图像的分割质量。