摘要
对Chan-Vese提出的基于Mumford-Shah模型的多水平集图像分割算法作了改进.首先,使用AOS算法改进了原模型的差分格式,使得差分格式无条件稳定.其次,在水平集的构造中应用了快速推进法的改进算法,减少了水平集初始化时计算的点数和重复次数.
A new level set approach for image segmentation was proposed based on the piecewise-constant Mumford-Shah model developed by Chan and Vese, The approach used AOS scheme, which is unconditional stable, to discrete the level set function. Besides, extended fast marching method for constructing the signed distance function was introduced to reduce the amount of computation significantly.
出处
《华东师范大学学报(自然科学版)》
CAS
CSCD
北大核心
2006年第3期66-70,140,共6页
Journal of East China Normal University(Natural Science)