图像扭曲变换中高斯基函数的最优参数分析  

Parameter Choosing of Gaussian Function in Elastic Image Deformation

作　　者：张智雄[1] 周平[1] 杨烜[1] 

机构地区：[1]深圳大学信息工程学院,深圳518060

出　　处：《中国图象图形学报》2009年第2期334-339,共6页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60572101)

摘　　要：薄板样条插值TPS是基于标记点的医学图像弹性配准中常用的插值方法,但该方法的扭曲作用是全局的,对于局部扭曲配准会导致匹配精度下降。基于径向基函数的图像变换方法可以解决局部扭曲配准问题,但如何选取径向基函数的参数还没有很好地解决。本文针对以高斯基函数为径向基函数的局部弹性变换问题,讨论了双标志点情况下高斯径向基函数的参数选取方法,该方法可以使双标志点之间的扭曲影响范围最局部化。本文结论用于多标志点的图像配准时可以解决图像局部弹性变换问题,实验结果验证了本文的结论。Common tools based on landmarks in medical image elastic registration are the thin plate spline （TPS）.However, in real application, such scheme would deform the image globally when the deformation desired is local. Although radial basic functions can limit the effect of the deformation locally, how to choose its parameter is still a problem. This paper used Gaussian function to compute the local elastic registration, purposed a method to choose Gaussianparameter to localize the deformation between two landmarks. Using this method in local image elastic registration base on landmarks, deformation of image could be reduced. Finally, this paper provides lots of experiments to support our conclusion.

关 键 词：图像配准 紧支撑 弹性扭曲 标志点 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]