基于特征融合的三维模型检索技术的研究
摘要
特征提取是基于内容的三维模型检索的研究重点，针对小型、专业模型库中模型数量少、相似度大、复杂度不高的特点，本文运用基于视图的和基于法向面的两种特征提取方式进行特征提取，并与其它检索方式加以实验对比。最后使用特征融合将两种基于内容的检索方式融合在一起，进一步加强了检索效果，并通过大量实验证明了检索的有效性。
本文介绍了基于内容的三维模型检索技术的框架，举例说明了坐标标准化及预处理，列举出了在三维模型相似性匹配中常用的几种方法，介绍了目前三维检索系统的几种查询方式，主要研究了以下内容：
首先、在分析基于视图的模型检索方式的优缺点的基础上，提出了基于三视图的模型检索方法。提取三维模型在外包围立方体的三个方向上投影的视图，通过实验逐步改进每次检索对比的视图数，在一定的检索时间下，有效地提高了检索精度。
其次、针对现有模型库中三维模型模型结构简单、数量小的特点，本文提取模型的法线向量、面（简称为法向面）特征，并与实例模型的法线向量、面加以对比，相对于基于视图的检索方式，此方法能较快速的进行三维模型检索。
最后、结合德国CCCC小组的特征融合(Feature Combination)方式，提出将基于视图的模型特征和基于法向面特征结合起来，增强对三维模型的描述能力。至于融合后特征值之间比例和特征值总量，通过实验进行了求取，并应用在钻井模型库中，进一步提高了模型检索效果。
The key to study content-based retrieval of3D models is feature extraction.Due to small specialized model library has characteristics of high similarities, low complexity,this paper use the view and NVM to extract the feature, and then compare with other methods.At last, using the feature combination combine the two retrieval method to enhance the effectand to validate the effectiveness of the method with a lot of experimental data.
This paper introduces the framework of3D model retrieving based on content, takes thestandardization of the coordinate and preprocessing as the examples, gives several kinds ofapproximate matching methods, introduces the feature extraction and3D model query ofretrieval system, some main points are as follows:
Firstly, on basis of analyzing the advantage and disadvantage of view-based retrievalmethods, this paper presents a new method: three views-based retrieving that extract the threeviews projection from3D model surrounded by the cube, experiments emphasis on improvingthe number of retrieved views, and raise the accuracy under the constant retrieved time.
Secondly, according to the simple structure, small number of3D model in the modellibrary, this paper extracts the normal vector and mesh (Referred to as NVM) as the feature,and compares with the case model. This method can retrieve3D model rapidly.
Finally, combined with the technology of feature combination which put forward byCCCC group in Germany, the paper combines the view-based with NVM-based to reinforcethe description ability. And the proportion and gross of the combined feature have beenproved by experiment. All of these can be applied to the drilling model library, and makefurther improvement of retrieval results.
本文介绍了基于内容的三维模型检索技术的框架，举例说明了坐标标准化及预处理，列举出了在三维模型相似性匹配中常用的几种方法，介绍了目前三维检索系统的几种查询方式，主要研究了以下内容：
首先、在分析基于视图的模型检索方式的优缺点的基础上，提出了基于三视图的模型检索方法。提取三维模型在外包围立方体的三个方向上投影的视图，通过实验逐步改进每次检索对比的视图数，在一定的检索时间下，有效地提高了检索精度。
其次、针对现有模型库中三维模型模型结构简单、数量小的特点，本文提取模型的法线向量、面（简称为法向面）特征，并与实例模型的法线向量、面加以对比，相对于基于视图的检索方式，此方法能较快速的进行三维模型检索。
最后、结合德国CCCC小组的特征融合(Feature Combination)方式，提出将基于视图的模型特征和基于法向面特征结合起来，增强对三维模型的描述能力。至于融合后特征值之间比例和特征值总量，通过实验进行了求取，并应用在钻井模型库中，进一步提高了模型检索效果。
The key to study content-based retrieval of3D models is feature extraction.Due to small specialized model library has characteristics of high similarities, low complexity,this paper use the view and NVM to extract the feature, and then compare with other methods.At last, using the feature combination combine the two retrieval method to enhance the effectand to validate the effectiveness of the method with a lot of experimental data.
This paper introduces the framework of3D model retrieving based on content, takes thestandardization of the coordinate and preprocessing as the examples, gives several kinds ofapproximate matching methods, introduces the feature extraction and3D model query ofretrieval system, some main points are as follows:
Firstly, on basis of analyzing the advantage and disadvantage of view-based retrievalmethods, this paper presents a new method: three views-based retrieving that extract the threeviews projection from3D model surrounded by the cube, experiments emphasis on improvingthe number of retrieved views, and raise the accuracy under the constant retrieved time.
Secondly, according to the simple structure, small number of3D model in the modellibrary, this paper extracts the normal vector and mesh (Referred to as NVM) as the feature,and compares with the case model. This method can retrieve3D model rapidly.
Finally, combined with the technology of feature combination which put forward byCCCC group in Germany, the paper combines the view-based with NVM-based to reinforcethe description ability. And the proportion and gross of the combined feature have beenproved by experiment. All of these can be applied to the drilling model library, and makefurther improvement of retrieval results.
引文
[1] Wellisch,H. information science to informatics:A terminological investigation[J]. Journalof Librarianship.1972,4(3):159.
[2]刘威，孔英蕾，肖宏涛．基于形状特征的图像检索技术[J]．兰州理工大学学报，2011，(01))：16-18．
[3]杨育彬．基于内容的图像检索关键技术及其应用研究[D]．南京大学计算机科学与技术系，南京，2003．
[4] Min P., Halderman A., Kazhdan M., Funkhouser A.. Early experiences with a3d modelsearch engine[C]. In: Proceedings of Web3D Symposium, Saint Malo, France,2003:7-18.
[5]赵鹏飞，金峰．基于面积分布的三维模型检索算法[J]．计算机科学，2009，(07)：176-178．
[6]侯鑫，张旭堂，金天国．基于网格特征临界点的三维工程模型检索算法[J]．计算机集成制造系统，2009，(01)：234-237．
[7] Moustakas,K.,etc.. Masterpiece:physical interaction and3D content-based search in VRapplications[J].IEEE MultiMedia,July2006,13(3)：92-100．
[8]郭竞，冯筠，叶豪盛．相对角度直方图聚类在3维模型检索中的应用[J]．中国图象图形学报,2010,(11)：67-68．
[9] Funkhouser T, Min P, Kazhdan M.et al. A search engine for3d models[J]. ACMTransactions on Graphics,2003,22(1):83~105.
[10]程言志，吕天阳，王钲旋．基于表面属性颜色分布的三维模型检索[J]．仪器仪表学报，2009，(08)：34-37．
[11] Neal J., Shapiro G.. A symbolic representation for3d object feature detection[J]. In:Proceedings of International Conference on Pattern Recognition, Barcelona, Spain,2000:1221-1224.
[12] Cyr C., Kimia B..3d object recognition using shape similarity based aspect graph[C]. In:Proceedings of IEEE International Conference on Computer Vision, Vancouver, Canada,2001:254-261.
[13]刘晓静．一种改进的三维模型特征提取算法[J]．青海大学学报(自然科学版)，2009，(03)：56-57．
[14]潘翔，张三元，叶修梓．三维模型语义检索研究进展[J]．计算机学报，2009，(06)：23-24．
[15]高岩，陈敏刚，王长波．二维动画关键帧的层次约束插值算法[A]．第十五届全国图象图形学学术会议论文集[C]，2010，(06)：678-680．
[16]申伟，苗振江，万丽莉．三维模型检索和逼真显示功能在可视媒体平台的实现
[A]．第18届全国多媒体学术会议（NCMT2009）、第5届全国人机交互学术会议（CHCI2009）、第5届全国普适计算学术会议（PCC2009）论文集[C],2009(07)：345-346．
[17] Liangliang Cao,Jianzhuang Liu,Xiaoou Tang.3D object retrieval using2D line drawingand graph based relevance feedback.International Multimedia Conference[C].2006:105-108.
[18] Atmosukarto I.,et al. Feature Combination and Relevance Feedback for3D ModelRetrieval[C]. Proceedings of the11th International Multimedia Modeling Conference.2005:334-339.
[19] G.Leifman et al. Semantic oriented3d shape retrieval using relevance feedback[J]. VisualComputing(2005).The Visual Computer(Pacific Graphics),October2005,21(8-10):865-875.
[20]杨育彬，林珲，朱庆．基于内容的三维模型检索综述[J]．计算机学报，2004，27(10)：1298-1310．
[21]郑伯川，彭维，张引．3D模型检索技术综述[J]．计算机辅助设计与图形学学报，July2004，16(7)：873-881．
[22] Vranic D., Saupe D..3d model retrieval. In: Proceedings of Spring Conference onComputer Graphics, Budmerice, Slovakia,2000:89-93.
[23] Heczko M., Keim D., Saupe D.. Amethod for similarity search of3d objects. In:Proceedings of German Database Conference(BTW), Oldenburg, Germany,2001,384~401.
[24]郑燕玲．基于视觉面距离的三维模型检索[J]．计算机仿真，2010，27(5)：43-36．
[25] Tangelder J., Veltkamp R.. Polyhedral model retrieval using weighted point sets.International Journal of Image and Graphics,2003:3(1):1~21.
[26] Binford T.. Generalized cylinder representation. In: Shapiro S.ed.. Encyclopedia ofArtificial Intelligence. New York: John Wiley&Sons,1987;321~323.
[27] Elmustapha Ait Lmaati, Ahmed El Oirrak, Mohamaed Najid Kaddioui, Abdellah AitOuahman, and Mohammed Sadgal Model Retrieval Based on3D Discrete CosineTransform The International Arab Journal of Information Technology, Vol.7, No.3, July2010:34-37.
[28] Cicirello V., Regli W.. Machining feature-based comparisons of mechanical parts. In:Proceedings of International Conference on Shape Modeling and Applications, Genoa,Italy,2001:176~185.
[29]郑伯川，张征．特征间互补性结合使用的3D模型检索技术[J]．重庆邮电学院学报(自然科学版)，2006，(01)：54-56．
[30] Zhang D., Hebert M.. Harmonic shape images: A3d free-form surface representation andits applications in surface matching. In:Proceedings of International Workshop on EnergyMinimization Methods in Computer Vision and Pattern Recognition, Sophia Antipolis,France,1999:30~43.
[31] Vranic D., Saupe D.. Description of3d-shape using a complex function on the sphere. In:Proceedings of IEEE InternationalConference on Multimedia and Expo, Lausanne,Switzerland,2002:177~180.
[32] Vranic D., Saupe D..3d shape descriptor based on3d Fourier transform. In: Proceedingsof IEEE EURASIP Conference on Digital Signal Processing for MultimediaCommunications and Services, Budapest, Hungary,2001:271~274.
[33] Ami Kim, Oubong Gwun, and Juwhan Song3D Model Retrieval based on NormalVector Interpolation Method Worl Acdemy of Science Engineering and Technology572009.
[34] Sharir M., Schorr A.. On shortest paths in polyhedral spaces.SIAM Journal onComputing,1986,15(1):193~215.
[35]章志勇，潘志庚，李黎．累进三维模型相似匹配算法[J]．计算机辅助设计与图形学学报,2005,(08)：23-33．
[36] Bardinet E., Vidal S., Arroyo S., Malandain G., Capilla N.. Structural object matching.Department of Computer Science and AI, University of Granada, Spain: TechnicalReport DECSAI000303,2000:1222-1223.
[37]徐敬华，张树有．基于形态分布图与BP神经网络的三维模型检索方法[J]．浙江大学学报(工学版)，2009，43(5)：48-49．
[38] Leymarie F., Kimia B.. The shock scaffold for representing3d shape. In: Proceedings ofInternational Workshop on Visual Form,Capri, Italy,2001:216-228.
[39] Zhang Y., Koschan A., Abidi M.. Superquadrics based3d object representation ofautomotive parts utilizing part decomposition. In: Proceedings of InternationalConference on Quality Control by Artificial Vision Gatlinburg, USA,2003:241-251.
[40]刘玉杰，张晓冬，李华．正交样条矩与三维模型检索[J]．计算机辅助设计与图形学学报，2009，(07)：78-80．
[41] Sundar H., Silver D., Gagvani N., Dickinson S.. Skeleton based shape matching andretrieval. In: Proceedings of International Conference on Shape Modeling andApplications, Seoul, Korea,2003:130~139.
[42]崔晨旸，石教英.三维模型检索中的特征提取技术综述[J]．计算机辅助设计与图形学学报，2004，(07)：90-91．
[43] Shokoufandeh A., Dickinson S., Jonsson C., Bretzner L., Lindeberg T.. Therepresentation and matching of qualitative shape atmultiple scales. In: Proceedings ofEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,759~775.
[44] Chen H., Huang T.. A survey of construction and manipulation of octrees. ComputerVision, Graphics, and Image Processing,1988,43(3):409-431.
[45]李山，石源，刘红军．基于ART2网络的三维模型聚类分析方法[J]．计算机集成制造系统，2011，(09)：23-24．
[46] Kitamura Y., Kishino F.. A parallel algorithm for octree generation from polyhedral shaperepresentation. In: Proceedings of International Conference on Pattern Recognition,Vienna, Austria,1996:303-309.
[47] Little J.. Extended Gaussian images, mixed volumes, shape reconstruction. In:Proceedings of Annual Symposium on Computational Geometry, Baltimore, USA,1985:15-23.
[48] Delingette H., Hebert H., Ikeuchi K.. A spherical representation for the recognition ofcurved objects. In: Proceedings of IEEE International Conference on Computer Vision,Berlin, Germany,1993:103-112.
[49]谭晓．一种基于球面调和分析的三维模型检索算法[J]．计算机工程与应用，2011，(19)：20-21．
[50] Johnson A., Hebert M.. Using spin-images for efficient multiple model recognition incluttered3-d scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):433-449.
[51] Mohamed Chaouch, Anne Verroust Blondet..Content-based3D model retrieval[J].INRIARocquencourt Domaine de Voluceau, B.P.10578153Le Chesnay Cedex,FRANCE2009:2312-2320.
[52]周旭，白深模．基于灰度共生矩阵的遥感图像纹理库设计[J]．海洋测绘，2010，(05)：56-57．
[53]陈怀友．大规模作战仿真平台可视化关键技术研究[D]．哈尔滨工程大学,2010．
[54]白静，唐韦华，刘玉生等．面向实体模型相似评价的层次图生成与高效匹配[J]．计算机辅助设计与图形学学报，2009，(07)：4-5．
[55] Canterakis N.. Fast3d zernike moments and invariants[J]. Institute for Computer Science,University of Freiburg, Freiburg, Germany: Technical Report,1997,(12):23-24.
[56]徐敬华．面向变异设计的移植单元检索与融合过程进化技术[D]．浙江大学,2009．
[57]郑赢，周明全，耿国华．多特征动态融合的三维模型检索方法[J]．计算机科学，2010,(37)7：23-25．
[58] Suzuki M.. A web-based retrieval system for3d polygonal models[C]. In: Proceedings ofJoint9th IFSA World Congress and20th NAFIPS International Conference, Vancouver,Canada,2001,2271-2276.
[59] Benjamin Bustos,etc.Automatic Selection and Combination of Descriptors for Effective3D Similarity Search[C].IEEE Sixth International Symposium on Multimedia SoftwareEngineering.2004:2345-2346.
[60]汤进，陈展展，罗斌.基于复杂网络和最优子序列双射的形状描述与匹配[J]．电子学报,2011,(08)：56-57．
[61] Atmosukarto I.,et al.Feature Combination and Relevance Feedback for3D ModelRetrieval[C].Proceedings of the11th International Multimedia ModelingConference.,2005:334-339.
[62] Aβfalg J, Borgwardt K M, Kriegel H P.3DString: a feature string kernel for3D objectclassification on oxelized data[C] Proceedings of the15th ACM InternationalConference on Information and Knowledge Management, Arlington,2006:198-207.
[63]普建涛，刘一，辛谷雨等．一种基于2维多边形集相似性的三维模型检索方法[J]．中国图象图形学报：A版，2004，9(12)：1437-1442．
[64]万丽莉，刘美琴．基于评价指标组合特征的三维模型检索方法[J]．计算机辅助设计与图形学学报，2009，(11)：34-35．
[65]韩丽,楚秉智．关节特征约束的3维模型骨架提取算法[J]．中国图象图形学报，2011，(04)3：45-46．
[66] Mihael Ankerst,etc.3D Shape Histograms for Similarity Search and Classification inSpatial Databases[C]. Proc.6th International Symposium on SpatialDatabases(SSD’99).July99,pp.207-226.
[67] Benjamin Bustos,etc.. An Experimental Effectiveness Comparison of Methods for3DSimilarity Search[J]. International Journal on Digital Libraries,2006,6(1),pp.39-54.
[68] Philip Shilane, Patrick Min, Michael Kazhdan. The Princeton Shape Benchmark[J].Proceedings Shape Modeling Applications.2004:167-388.
[69] D. Saupe and D. V. Vranic.3D model retrieval with spherical harmonics and moments[J].In B. Radig and S. Florczyk,editors, DAGM2001:392–397.
[70] Mohamed Chaouch and Anne Verroust Blondet. New Descriptor for2D Depth ImageIndexing and3D Model Retrieval[C]. INRIA Rocquencourt Domaine de Voluceau, B.P.10578153Le Chesnay Cedex, FRANCE2007:1546-1548.
[71] M. Chaouch and A. Verroust-Blondet.3D model retrieval based on depth linedescriptor[C]. in IEEE International Conference on Multimedia&Expo (ICME07),Beijing, China, July2007:1223-1224.
[72]王大千．基于语义的三维模型检索[D]．中国石油大学，2010．
[2]刘威，孔英蕾，肖宏涛．基于形状特征的图像检索技术[J]．兰州理工大学学报，2011，(01))：16-18．
[3]杨育彬．基于内容的图像检索关键技术及其应用研究[D]．南京大学计算机科学与技术系，南京，2003．
[4] Min P., Halderman A., Kazhdan M., Funkhouser A.. Early experiences with a3d modelsearch engine[C]. In: Proceedings of Web3D Symposium, Saint Malo, France,2003:7-18.
[5]赵鹏飞，金峰．基于面积分布的三维模型检索算法[J]．计算机科学，2009，(07)：176-178．
[6]侯鑫，张旭堂，金天国．基于网格特征临界点的三维工程模型检索算法[J]．计算机集成制造系统，2009，(01)：234-237．
[7] Moustakas,K.,etc.. Masterpiece:physical interaction and3D content-based search in VRapplications[J].IEEE MultiMedia,July2006,13(3)：92-100．
[8]郭竞，冯筠，叶豪盛．相对角度直方图聚类在3维模型检索中的应用[J]．中国图象图形学报,2010,(11)：67-68．
[9] Funkhouser T, Min P, Kazhdan M.et al. A search engine for3d models[J]. ACMTransactions on Graphics,2003,22(1):83~105.
[10]程言志，吕天阳，王钲旋．基于表面属性颜色分布的三维模型检索[J]．仪器仪表学报，2009，(08)：34-37．
[11] Neal J., Shapiro G.. A symbolic representation for3d object feature detection[J]. In:Proceedings of International Conference on Pattern Recognition, Barcelona, Spain,2000:1221-1224.
[12] Cyr C., Kimia B..3d object recognition using shape similarity based aspect graph[C]. In:Proceedings of IEEE International Conference on Computer Vision, Vancouver, Canada,2001:254-261.
[13]刘晓静．一种改进的三维模型特征提取算法[J]．青海大学学报(自然科学版)，2009，(03)：56-57．
[14]潘翔，张三元，叶修梓．三维模型语义检索研究进展[J]．计算机学报，2009，(06)：23-24．
[15]高岩，陈敏刚，王长波．二维动画关键帧的层次约束插值算法[A]．第十五届全国图象图形学学术会议论文集[C]，2010，(06)：678-680．
[16]申伟，苗振江，万丽莉．三维模型检索和逼真显示功能在可视媒体平台的实现
[A]．第18届全国多媒体学术会议（NCMT2009）、第5届全国人机交互学术会议（CHCI2009）、第5届全国普适计算学术会议（PCC2009）论文集[C],2009(07)：345-346．
[17] Liangliang Cao,Jianzhuang Liu,Xiaoou Tang.3D object retrieval using2D line drawingand graph based relevance feedback.International Multimedia Conference[C].2006:105-108.
[18] Atmosukarto I.,et al. Feature Combination and Relevance Feedback for3D ModelRetrieval[C]. Proceedings of the11th International Multimedia Modeling Conference.2005:334-339.
[19] G.Leifman et al. Semantic oriented3d shape retrieval using relevance feedback[J]. VisualComputing(2005).The Visual Computer(Pacific Graphics),October2005,21(8-10):865-875.
[20]杨育彬，林珲，朱庆．基于内容的三维模型检索综述[J]．计算机学报，2004，27(10)：1298-1310．
[21]郑伯川，彭维，张引．3D模型检索技术综述[J]．计算机辅助设计与图形学学报，July2004，16(7)：873-881．
[22] Vranic D., Saupe D..3d model retrieval. In: Proceedings of Spring Conference onComputer Graphics, Budmerice, Slovakia,2000:89-93.
[23] Heczko M., Keim D., Saupe D.. Amethod for similarity search of3d objects. In:Proceedings of German Database Conference(BTW), Oldenburg, Germany,2001,384~401.
[24]郑燕玲．基于视觉面距离的三维模型检索[J]．计算机仿真，2010，27(5)：43-36．
[25] Tangelder J., Veltkamp R.. Polyhedral model retrieval using weighted point sets.International Journal of Image and Graphics,2003:3(1):1~21.
[26] Binford T.. Generalized cylinder representation. In: Shapiro S.ed.. Encyclopedia ofArtificial Intelligence. New York: John Wiley&Sons,1987;321~323.
[27] Elmustapha Ait Lmaati, Ahmed El Oirrak, Mohamaed Najid Kaddioui, Abdellah AitOuahman, and Mohammed Sadgal Model Retrieval Based on3D Discrete CosineTransform The International Arab Journal of Information Technology, Vol.7, No.3, July2010:34-37.
[28] Cicirello V., Regli W.. Machining feature-based comparisons of mechanical parts. In:Proceedings of International Conference on Shape Modeling and Applications, Genoa,Italy,2001:176~185.
[29]郑伯川，张征．特征间互补性结合使用的3D模型检索技术[J]．重庆邮电学院学报(自然科学版)，2006，(01)：54-56．
[30] Zhang D., Hebert M.. Harmonic shape images: A3d free-form surface representation andits applications in surface matching. In:Proceedings of International Workshop on EnergyMinimization Methods in Computer Vision and Pattern Recognition, Sophia Antipolis,France,1999:30~43.
[31] Vranic D., Saupe D.. Description of3d-shape using a complex function on the sphere. In:Proceedings of IEEE InternationalConference on Multimedia and Expo, Lausanne,Switzerland,2002:177~180.
[32] Vranic D., Saupe D..3d shape descriptor based on3d Fourier transform. In: Proceedingsof IEEE EURASIP Conference on Digital Signal Processing for MultimediaCommunications and Services, Budapest, Hungary,2001:271~274.
[33] Ami Kim, Oubong Gwun, and Juwhan Song3D Model Retrieval based on NormalVector Interpolation Method Worl Acdemy of Science Engineering and Technology572009.
[34] Sharir M., Schorr A.. On shortest paths in polyhedral spaces.SIAM Journal onComputing,1986,15(1):193~215.
[35]章志勇，潘志庚，李黎．累进三维模型相似匹配算法[J]．计算机辅助设计与图形学学报,2005,(08)：23-33．
[36] Bardinet E., Vidal S., Arroyo S., Malandain G., Capilla N.. Structural object matching.Department of Computer Science and AI, University of Granada, Spain: TechnicalReport DECSAI000303,2000:1222-1223.
[37]徐敬华，张树有．基于形态分布图与BP神经网络的三维模型检索方法[J]．浙江大学学报(工学版)，2009，43(5)：48-49．
[38] Leymarie F., Kimia B.. The shock scaffold for representing3d shape. In: Proceedings ofInternational Workshop on Visual Form,Capri, Italy,2001:216-228.
[39] Zhang Y., Koschan A., Abidi M.. Superquadrics based3d object representation ofautomotive parts utilizing part decomposition. In: Proceedings of InternationalConference on Quality Control by Artificial Vision Gatlinburg, USA,2003:241-251.
[40]刘玉杰，张晓冬，李华．正交样条矩与三维模型检索[J]．计算机辅助设计与图形学学报，2009，(07)：78-80．
[41] Sundar H., Silver D., Gagvani N., Dickinson S.. Skeleton based shape matching andretrieval. In: Proceedings of International Conference on Shape Modeling andApplications, Seoul, Korea,2003:130~139.
[42]崔晨旸，石教英.三维模型检索中的特征提取技术综述[J]．计算机辅助设计与图形学学报，2004，(07)：90-91．
[43] Shokoufandeh A., Dickinson S., Jonsson C., Bretzner L., Lindeberg T.. Therepresentation and matching of qualitative shape atmultiple scales. In: Proceedings ofEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,759~775.
[44] Chen H., Huang T.. A survey of construction and manipulation of octrees. ComputerVision, Graphics, and Image Processing,1988,43(3):409-431.
[45]李山，石源，刘红军．基于ART2网络的三维模型聚类分析方法[J]．计算机集成制造系统，2011，(09)：23-24．
[46] Kitamura Y., Kishino F.. A parallel algorithm for octree generation from polyhedral shaperepresentation. In: Proceedings of International Conference on Pattern Recognition,Vienna, Austria,1996:303-309.
[47] Little J.. Extended Gaussian images, mixed volumes, shape reconstruction. In:Proceedings of Annual Symposium on Computational Geometry, Baltimore, USA,1985:15-23.
[48] Delingette H., Hebert H., Ikeuchi K.. A spherical representation for the recognition ofcurved objects. In: Proceedings of IEEE International Conference on Computer Vision,Berlin, Germany,1993:103-112.
[49]谭晓．一种基于球面调和分析的三维模型检索算法[J]．计算机工程与应用，2011，(19)：20-21．
[50] Johnson A., Hebert M.. Using spin-images for efficient multiple model recognition incluttered3-d scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(5):433-449.
[51] Mohamed Chaouch, Anne Verroust Blondet..Content-based3D model retrieval[J].INRIARocquencourt Domaine de Voluceau, B.P.10578153Le Chesnay Cedex,FRANCE2009:2312-2320.
[52]周旭，白深模．基于灰度共生矩阵的遥感图像纹理库设计[J]．海洋测绘，2010，(05)：56-57．
[53]陈怀友．大规模作战仿真平台可视化关键技术研究[D]．哈尔滨工程大学,2010．
[54]白静，唐韦华，刘玉生等．面向实体模型相似评价的层次图生成与高效匹配[J]．计算机辅助设计与图形学学报，2009，(07)：4-5．
[55] Canterakis N.. Fast3d zernike moments and invariants[J]. Institute for Computer Science,University of Freiburg, Freiburg, Germany: Technical Report,1997,(12):23-24.
[56]徐敬华．面向变异设计的移植单元检索与融合过程进化技术[D]．浙江大学,2009．
[57]郑赢，周明全，耿国华．多特征动态融合的三维模型检索方法[J]．计算机科学，2010,(37)7：23-25．
[58] Suzuki M.. A web-based retrieval system for3d polygonal models[C]. In: Proceedings ofJoint9th IFSA World Congress and20th NAFIPS International Conference, Vancouver,Canada,2001,2271-2276.
[59] Benjamin Bustos,etc.Automatic Selection and Combination of Descriptors for Effective3D Similarity Search[C].IEEE Sixth International Symposium on Multimedia SoftwareEngineering.2004:2345-2346.
[60]汤进，陈展展，罗斌.基于复杂网络和最优子序列双射的形状描述与匹配[J]．电子学报,2011,(08)：56-57．
[61] Atmosukarto I.,et al.Feature Combination and Relevance Feedback for3D ModelRetrieval[C].Proceedings of the11th International Multimedia ModelingConference.,2005:334-339.
[62] Aβfalg J, Borgwardt K M, Kriegel H P.3DString: a feature string kernel for3D objectclassification on oxelized data[C] Proceedings of the15th ACM InternationalConference on Information and Knowledge Management, Arlington,2006:198-207.
[63]普建涛，刘一，辛谷雨等．一种基于2维多边形集相似性的三维模型检索方法[J]．中国图象图形学报：A版，2004，9(12)：1437-1442．
[64]万丽莉，刘美琴．基于评价指标组合特征的三维模型检索方法[J]．计算机辅助设计与图形学学报，2009，(11)：34-35．
[65]韩丽,楚秉智．关节特征约束的3维模型骨架提取算法[J]．中国图象图形学报，2011，(04)3：45-46．
[66] Mihael Ankerst,etc.3D Shape Histograms for Similarity Search and Classification inSpatial Databases[C]. Proc.6th International Symposium on SpatialDatabases(SSD’99).July99,pp.207-226.
[67] Benjamin Bustos,etc.. An Experimental Effectiveness Comparison of Methods for3DSimilarity Search[J]. International Journal on Digital Libraries,2006,6(1),pp.39-54.
[68] Philip Shilane, Patrick Min, Michael Kazhdan. The Princeton Shape Benchmark[J].Proceedings Shape Modeling Applications.2004:167-388.
[69] D. Saupe and D. V. Vranic.3D model retrieval with spherical harmonics and moments[J].In B. Radig and S. Florczyk,editors, DAGM2001:392–397.
[70] Mohamed Chaouch and Anne Verroust Blondet. New Descriptor for2D Depth ImageIndexing and3D Model Retrieval[C]. INRIA Rocquencourt Domaine de Voluceau, B.P.10578153Le Chesnay Cedex, FRANCE2007:1546-1548.
[71] M. Chaouch and A. Verroust-Blondet.3D model retrieval based on depth linedescriptor[C]. in IEEE International Conference on Multimedia&Expo (ICME07),Beijing, China, July2007:1223-1224.
[72]王大千．基于语义的三维模型检索[D]．中国石油大学，2010．