计算机科学 ›› 2018, Vol. 45 ›› Issue (5): 266-272.doi: 10.11896/j.issn.1002-137X.2018.05.046
洪汉玉,马尔威,黄丽坤
HONG Han-yu, MA Er-wei and HUANG Li-kun
摘要： 现有的基于简单点判断的三维细化算法不能保证提取骨架的连续性,容易产生断裂。针对该问题,提出了一组各向同性模板,该模板能够使得算法具有90°旋转不变性；在此基础上,进一步提出了一种新的重新检测的方法,通过判断被删除的目标点的26邻域的连通性,来决定该目标点是否应该被还原,从而逐点检测3D物体的连通性,达到 保持整体连通性的目的。该方法可以应用于大多数基于模板的三维细化算法,能够修复断裂,保证其拓扑结构,避免产生空洞；同时,与同类算法相比,本算法由于利用了各向同性模板,在物体旋转的情况下亦能得到最佳的细化结果。
| [1] HONG H Y.Modern image graphics processing and analysis [M].Wuhan:China University of Geosciences Press,2011. [2] PALAGYI K,KUBA A.A Thinning algorithm to extract medial lines from 3D medical images[J].Information Processing in Medical Imaging,1997,0:411-416. [3] GENG H,YANG J Z,ZHAO D Z,et al.Three-dimensional ske-leton extraction algorithm for human tubular tissue [J].Journal of Instrumentation,2014,5(4):754-761. [4] CHUANG J H,TSAI C H,KO M C.Skeletonization of three-dimensional object using generalized potential field[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,2(11):1241-1251. [5] CHEN G D,LI J H,MAO Y,et al.Skeleton Extraction Algorithm for 3D Human Body Model [C]∥The 14th National Conference on Graphic Graphics.Fuzhou:Fujian,China. [6] CHEN G,LV X,WANG Z C,et al.Vascular skeletonization of lung CT images [J].Computer Science,2013,40(5):274-278. [7] MA C M,SONKA M.A fully parallel 3D Thinning algorithmand its applications[J].Computer Vision and Image Understanding,1996,64(3):420-433. [8] WANG T,BASU A.A note on A fully parallel 3D Thinning algorithm and its applications[J].Pattern Recognition Letters,2007,8(4):501-506. [9] PALAGYI K,KUBA A.A 3D 6-subiteration thinning algorithm for extracting medial lines[J].Pattern Recognition Letter,1998,9(7),613-627. [10] LOHOU C,BERTRAND G.A 3D 12-subiteration thinning algorithm based on P-simple points[J].Discrete Applied Mathematics,2004,139(1-3):171-195. [11] SAHA P,CHANDA B,MAJUMDER D.A new shape-preserving parallel thinning algorithm for 3D digital images[J].Pattern Recognition,1997,0(12):1939-1955. [12] BERTRAND G,AKTOUF Z.A 3D thinning algorithm using subfields[C]∥SPIE Proc.of Conf.on Vision Geometry.San Die-go,CA,USA,1994:113-124. [13] HALL R W.Connectivity preserving parallel operators in 2D and 3D images[C]∥SPIE Proc.of Conference on Vision Geome-try.Boston,MA,USA,1992:172-183. [14] SAHA P,CHANDA B,MAJUMDER D.Principles and Algorithms for 2D and 3D Shrinking:Technical Report TR/KBCS/2/91[R].N.C.K.B.C.S.Library,Indian Statistical Institute,Calcutta,India,1991. [15] KONG T Y.On the problem of determining whether a parallel reduction operator for n-dimensional binary images always preserves topology [C]∥ SPRE Conference on Vision Geometry.Boston,MA,1993:69-77. [16] CHEISTOPHE L,JULIEN D.Automatic correction of Ma and Sonka’s thinning algorithm using P-simple point[J].IEEE,2010,32(6):1148-1152. [17] BERTRAND G,COUPRIE M.Powerful Parallel and Symmetric 3D Thinning Schemes Based on Critical Kernels[J].Journal of Mathematical Imaging and Vision,2014,48(1):134-148. |
| No related articles found! |
|
||
首页