摘要： 利用全局信息的C-V模型对轮廓初始化和噪声不敏感，但不能分割灰度不均的图像；利用局部信息的RSF模型能分割灰度不均的图像，但对轮廓初始化和噪声很敏感。针对该问题，基于C-V模型和RSF模型，提出一个新的水平集正则化项，给出一个用偏微分方程表示的结合全局和局部信息的活动轮廓模型。实验结果表明，该模型能分割灰度不均的图像，且允许灵活的轮廓初始化，抗噪性较强。

关键词: 图像分割, 活动轮廓模型, C-V模型, RSF模型, 偏微分方程

Abstract: The Chan-Vese(C-V) model based on global region information is less sensitive to initialization and noise, but it cannot handle images with intensity inhomogeneity. RSF model based on local region information is able to deal with intensity inhomogeneity, but it is highly sensitive to initialization and noise. In order to address this problem, this paper proposes a novel level set regularization term, and then proposes a new active contour model with a partial differential equation, which integrates both global and local region information. Experimental results show that the proposed model can segment images with intensity inhomogeneity, while it allows for flexible initialization and is less sensitive to noise.

Key words: image segmentation, active contour model, Chan-Vese(C-V) model, RSF model, partial differential equation

中图分类号: 

• TP391