基于AOS格式的扩展Mumford-Shah模型图像分割算法

An Extended Image Segmentation Algorithm of Mumford-Shah Model Based on AOS Scheme

在Chan-Vese模型的基础上,给出一种基于AOS格式的扩展Mumford-Shah模型图像分割算法.扩展的Mumford-Shah模型将图像分解为几何和纹理两部分,实现图像分割的同时有效避免了纹理和噪声的影响.数值求解采用AOS格式,不仅扩大了时间步长的调节范围,还解决了参数难以选择的问题,提高了算法稳定性.实验结果表明,本文算法分割效果良好,运算效率有了较大提高.

Founded on the Chan-Vese Model, this paper presents an extended image segmentation algorithm of Mumford-Shah based on AOS scheme. The extended model divides image into geometry and texture part with the realization of a texture and noise free image segmentation. With the application of AOS scheme, the numerical solution enlarges the adjusting range of time step, and also works out the difficulty in parameter decision, finally enhances the stability of algorithm. The experiment manifests that the segmentation effect of the algorithm is good, and the efficiency is highly improved, which proves to be a highly practical significance.