基于角点的CT影像轮廓遮挡识别  

Corner-based recognition of contour occlusions in CT images

作　　者：刘浩[1] 张召远 戴宁[1] LIU Hao;ZHANG Zhaoyuan;DAI Ning(College of Mechanical and Electrical Engineering, Nanjing University ofAeronautics and Astronautics, Nanjing 210016, China)

机构地区：[1]南京航空航天大学机电学院,南京210016

出　　处：《计算机工程与应用》2017年第1期213-219,共7页Computer Engineering and Applications

基　　金：国家自然科学基金面上项目(No.51175248/E050603)

摘　　要：针对CT影像中的启发式轮廓提取,提出了一种根据上层轮廓识别的当前轮廓遮挡的算法。使用基于曲线的弧长参数化方法识别遮挡,这种方法能够识别出轮廓的所有遮挡,但是,轮廓中的非遮挡部分也可能被识别为遮挡。利用DCSS(直接曲率尺度空间)在上下轮廓中自动识别和匹配角点,进一步设计基于角点的遮挡收缩技术,通过匹配的角点缩短或者删除被错误识别的遮挡。大量的实验研究表明,该算法可以有效、准确地识别所有轮廓的遮挡。Aiming at heuristic contour extraction in CT images, an occlusion recognition algorithm for the current contouris proposed according to the previous contour. Firstly, it uses a curve-based curve parameterization method to recognizeall occlusions in a contour. However, for some parts of the contour that are not occlusions, the method probably recognizesthem as occlusions. Then, based on automatically recognizing and matching corners between the previous contour and thecurrent contour using the Direct Curvature Scale Space(DCSS), an occlusion-shrinking method is designed. The methodshortens or removes incorrect occlusion using matched corner pairs. Many experiments show that this method can efficientlyand accurately recognize all occlusions in a contour.

关 键 词：CT影像 切片 轮廓提取 角点匹配 遮挡 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]