基于活动轮廓模型的图像分割算法综述  

A Review of Active Contour Model Based Image Segmentation Algorithms

作　　者：段丁娜 张欢[1] 邱陈辉 夏顺仁[1,2] 

机构地区：[1]浙江大学生物医学工程教育部重点实验室,杭州310027 [2]浙江省心脑血管检测技术与药效评价重点实验室,杭州310027

出　　处：《中国生物医学工程学报》2015年第4期445-454,共10页Chinese Journal of Biomedical Engineering

基　　金：国家"十二五"科技支撑计划资助项目(2012BAI10B04);国家自然科学基金(81101903)

摘　　要：活动轮廓模型是一种重要的图像分割技术,它利用底层信息,并结合高层先验知识,实现对复杂目标轮廓的自动分割。自Kass等提出该思想以来的20多年中,活动轮廓模型在理论研究和应用方面均取得长足发展。首先,介绍活动轮廓模型的发展历程,重点阐述并分析典型的参数活动轮廓模型和几何活动轮廓模型,进而扼要介绍混合活动轮廓模型和快速求解算法;随后,从理论基础、分割效果、算法效率以及应用等方面,比较两类模型之间的区别与联系;最后,对活动轮廓模型未来的发展趋势进行展望。Active contour model is an important method for image segmentation. It combines underlying information with high-level prior knowledge to achieve automatic segmentation for complex objects. Active contour model has been developed greatly in theory research and application,since it was proposed twenty years ago. This paper reviewed the development process of active contour model at first and describes the classical parametric active contour models and geometric active contour models,and presents briefly new hybrid active contour models as well as fast solution algorithms. After that,the relationship between these two kinds of models through theory basis,performance,efficiency and applications were introduced. The future prospect of active contour model was discussed as well.

关 键 词：活动轮廓模型 图像分割 参数活动轮廓模型 几何活动轮廓模 混合活动轮廓模型 

分 类 号：R318[医药卫生—生物医学工程]