The fuzzy C-means(FCM) clustering algorithm has been proven to be effective for image segmentation.However,the standard FCM algorithm is sensitive to noise and gray inhomogeneity.An improved FCM-based algorithm is proposed in this paper,which firstly modeled the noise of an image as a slowly varying additive or multiplicative noise and iteratively approximate the gray inhomogeneity and noise areas by using the spatial neighborhood information.In this process,the threshold values of up and down c...