基于算子分裂的图像分割模型及其快速算法  

Image Segmentation and Its Fast Algorithm Based on Operator Splitting

作　　者：宋锦萍[1] 职占江[1] 刘玉霞[1] 

机构地区：[1]河南大学数学与信息科学学院,河南开封475004

出　　处：《河南大学学报（自然科学版）》2013年第2期111-114,共4页Journal of Henan University:Natural Science

基　　金：国家自然科学基金资助项目(11026077);河南省教育厅自然科学基金资助项目(2009B110006)

摘　　要：针对带有纹理和噪声的图像,在Mumford-Shah模型的基础上,提出一种基于算子分裂的图像分割模型.数值求解采用AOS与Newton迭代相结合的方法,不仅解决了参数难以选择的问题,还扩大了时间步长的调节范围,提高了算法稳定性.实验结果表明,本文算法在分割过程中可以很好的处理拓扑结构,有效地避免了纹理(或噪声)对分割效果的影响,并且具有较高的计算效率.Aiming at images with texture and noise, this paper proposes a kind of image segmentation based on additive operator splitting within the Mumford-Shah model. The numerical solution applying the method of connecting AOS with the Newton iteration not only solves the problem difficult to choose parameters, but also expands the range of the time step adjustment to improve the stability of the algorithm. The experimental results show that the algorithm proposed in this paper can process the topology, avoid the effect of the texture （or noise） on the segmentation results and have a high computational efficiency in the segmentation process.

关 键 词：图像分割 加性算子分裂 水平集 MUMFORD-SHAH模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]