矢量图像分割的快速C-V模型  

A Fast C-V Model for Vector-valued Image Segmentation

作　　者：赵骥[1,2] 邵富群[1] 张学东[2] 田莹[2] 

机构地区：[1]东北大学信息科学与工程学院,沈阳110004 [2]辽宁科技大学软件学院,鞍山114051

出　　处：《计算机辅助设计与图形学学报》2011年第11期1869-1874,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(60775036);辽宁省教育厅资助项目(L2010194,2010076)

摘　　要：为了实现对矢量图像快速有效的分割,在分析矢量图像颜色、空间信息和水平集函数特性的基础上,对主动轮廓分割模型进行了改进,提出一种免重新初始化的矢量图像分割模型.在C-V(Chan-Vese)模型中引入了非线性热方程的符号距离函数的约束项,通过对非线性热方程传导率的均衡化使水平集函数始终保持符号距离函数的特性,完全取消比较耗时的重新初始化过程;改进了曲线二维梯度和散度算子传统离散化方式,使梯度和散度算子保持空间旋转不变性.实验结果表明,改进模型快速有效,对噪声和弱边缘有很好的鲁棒性.To achieve fast and effective vector-valued image segmentation, an improved active contour model without re-initialization for object segmentation is proposed on the basis of analysis on the image colors, spatial information and characteristics of the level set function. Nonlinear heat equation with balanced diffusion rate is added to the C-V model to maintain the signed distance function property. Therefore the costly re-initialization procedure is completely eliminated. The proposed method employs the two-dimensional spatial rotation-invariance gradient and divergence operator instead of the traditional discretization approach. Experimental results show that the proposed method is fast, efficient and robust with respect to noise and weak object boundaries.

关 键 词：水平集 C—V模型 矢量图像 图像分割 半点离散化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]