结合FCMS与变分水平集的图像分割模型

Image Segmentation Model Combined with FCMS and Variational Level Set

提出了一个结合融合空间约束的模糊C均值(Fuzzy C means with spatial constraints,FCMS)聚类与变分水平集的图像模糊聚类分割模型.在该模型中引入了一个基于图像局部信息和空间信息的外部模糊聚类能量,从而可以获取精确的局部图像的空间特征,使得本文模型对噪声图像的聚类分割具有较强的鲁棒性.采用不同类型的实验图像,将本文模型与10个不同类型的图像分割模型进行了对比实验,实验结果显示本文模型能克服图像中噪声影响并取得较满意的聚类分割结果.

This paper proposes an image fuzzy clustering segmentation model combined with FCMS clustering and variational level set method. An external fuzzy clustering energy based on local information and spatial information of the image is introduced in the energy functional to enable us to extract the accurate spatial information of the local image. Therefore, the proposed model is robust to noisy image segmentation. The experiment results illustrate that the proposed model, compared with 10 different models, can overcome the influence of noise and obtain better segmentation results for different images.