一种融合曲线演化与模糊C均值聚类算法的快速图像分割模型

Fast Image Segmentation Model Combined with Fuzzy C-means Method and Curve Evolution

针对模糊C均值聚类算法(FCM)分割图像时对噪声敏感和分割边界不封闭问题,该文基于FCM的隶属度矩阵定义伪水平集及演化曲线,提出一个融合曲线演化和FCM的快速图像分割模型。在伪水平集上,通过采用高斯滤波近似曲线演化过程中的弧长正则项,得到封闭光滑的分割边界;通过设计新的边缘停止函数,依据灰度值与隶属度映射关系对噪声点灰度值进行修正,降低了滤波对聚类的影响。聚类和曲线平滑交替进行,提高了模型对图像噪声的鲁棒性。实验结果表明该模型能够较好地克服图像噪声对分割的影响,得到较为理想的分割结果。

To solve the problems about noise sensitivity and unclosed segmentation object boundaries in Fuzzy C-means Method （FCM）, this paper proposes a fast image segmentation model combined with FCM and curve evolution, based on the pseudo level set formulations and object boundary curves, which are defined on the membership matrixes of FCM. To get the smooth and closed segmentation object boundaries, the Gaussian filter is performed on the pseudo level sets to approximate the function of the curve length regularization term. To eliminate the influence of Gaussian filter on the results of FCM, the gray values of the noisy points are corrected, according to a new introduced edge-stop function and the mapping relationship between the gray value and membership degree. The FCM and the smoothing object boundary stage are performed alternately, which improves the robustness of this model. The experimental results show that the proposed model can overcome the influence of noise and get better segmentation results.