基于升序复核的并行三维图像骨架化算法  

Parallel 3D skeletonization algorithm based on sort ascending rechecking

作　　者：滕奇志[1] 康瑕[1] 唐棠[1] 何小海[1] 

机构地区：[1]四川大学电子信息学院图像信息研究所,四川成都610064

出　　处：《光学精密工程》2009年第10期2528-2534,共7页Optics and Precision Engineering

基　　金：四川省科技攻关基金资助项目(No.05GG021-026-03)

摘　　要：为了准确有效地提取三维图像的骨架,提出一种新的并行三维图像骨架化算法。首先对原图像进行距离变换,然后迭代并行细化。每轮迭代分为6个子迭代,每个子迭代处理一类边界点,标记满足初选规则的前景点。在6个子迭代结束后,按距离值升序复核初选标记点,批量删除满足条件的点,完成一轮迭代。重复这一过程直到没有点被删除,得到最终骨架。将该算法应用于二维和三维图像,得到了与人类视觉感知相一致的目标骨架。新算法能够保证得到的骨架的连通性和拓扑结构,通过计算骨架点的距离值验证了其居中性,反映了目标的本质结构特征。In order to accurately and efficiently extract skeletons from 3D images, a new parallel 3D skeletonization algorithm is proposed. The distances of original images are firstly transformed, and then iterative parallel thinning is performed. Each iteration is divided into 6 sub iterations, one sub it- eration is used to process a kind of boundary points,and the foreground points satisfying the primary selection rule are labeled. After 6 sub iterations are completed, labeled points are rechecked in an as- cending distance order, and those who satisfy thinning conditions are deleted. This process is repeated until there is no point deleted. This algorithm is applied to 2D and 3D images, obtained skeletons are consistent with that by the visual apperception. This algorithm guarantees the connectivity and topol- ogy of extracted skeletons, and its median can be validated by caculating the distance values of skele- ton points,which reflects the essence characteristics of the object.

关 键 词：骨架化 8-6树 升序复核 并行算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]