摘要： 针对局部二值拟合(LBF)模型容易陷入能量泛函局部极小值的问题，提出基于局部与全局拟合的活动轮廓模型。引入一个衡量某点处局部区域内灰度分布是否均匀的特征函数，将LBF模型中的局部拟合项与CV模型中的全局拟合项相结合，同时保留LBF模型分割灰度不均匀图像和CV模型全局收敛性的优点。实验结果表明，该模型能够分割灰度不均匀图像，对初始轮廓的依赖性较弱，并且具有一定的抗噪性。

关键词: 图像分割, 活动轮廓, 局部二值拟合模型, CV模型, 水平集, 偏微分方程

Abstract: The localization property of Local Binary Fitting(LBF) model may introduce many local minimums of the energy functional. In order to overcome this problem, an active contour model based on local and global fitting is proposed. By introducing a characteristic function which measures the intensity distribution in a local region of a certain point, the proposed model combines the global fitting energy in CV model and the local fitting energy in LBF model. The proposed model not only retains the advantages of LBF model in segmentation of intensity inhomogeneity images, but also introduces the advantages of global convergence of CV model. Experimental results demonstrate that the proposed model can segment images with intensity inhomogeneity, while it allows for flexible initialization of the contours, and it is less sensitive to noise.

Key words: image segmentation, active contour, Local Binary Fitting(LBF) model, CV model, level set, Partial Differential Equation(PDE)

中图分类号: 

• TN911.73