臺灣博碩士論文加值系統

電腦輔助設計與製造(CAD/CAM)技術經過多年的發展已經非常的普遍，但是隨著幾何模型資料量的快速累積，若缺乏有效率的幾何模型比對方法配合，對於累積的幾何模型設計資料提供後續的查詢或取出，將影響整個自動化的推動。雖然運用群組技術(Group Technology)來執行設計產品之模型或加工製程資訊的分類與取出查詢技術已經發展多年，但是僅藉由編碼的方式實在無法描述產品的具體外形，達到精確資料搜尋的效果，因此一套可以進行三維幾何模型比對辨識的方法是需要的。
三維幾何模型之比對由於幾何資料結構的複雜性，發展通用之模型搜尋比對法相當困難。目前STL之模型檔案格式已普遍被使用於逆向工程之資料交換，且STL格式基本上為多面網格模型，可直接支援顯示所需，因此本論文以STL資料格式所描述之物體為對象，利用主軸分析與ICP演算法發展可進行特徵辨識以及兩物體之最佳對準(Registration)與比對(Matching)技術。
本研究以 Visual C++ 發展程式，並結合VTK（The Visualization Toolkit）圖形處理類別函式庫來進行系統整合。

摘 要..................................................I
致 謝.................................................II
目 錄................................................III
圖 索 引.................................................VI
表 索 引.................................................IX
第一章 緒論...............................................1
1.1 前言................................................1
1.2 研究目的............................................3
1.3 研究方法............................................4
1.4 文獻回顧............................................5
1.5 論文結構............................................8
第二章 三維模型資料結構與比對概念.........................9
2.1資料結構種類.........................................9
2.1.1 線框模型.........................................9
2.1.2 表面模型........................................10
2.1.3 實體模型........................................10
2.2 STL檔案格式........................................14
2.3 座標系統轉換.......................................16
2.3.1 座標系統平移....................................17
2.3.2 座標系統旋轉....................................18
2.3.3 齊次式座標系統轉換..............................19
2.2 模型比對概念.......................................21
第三章 3D幾何模型之基本對齊..............................25
3.1 基本對齊之原理與策略...............................25
3.2 動量矩陣...........................................28
3.2.1二維幾何圖形面積.................................29
3.2.2三維幾何模型體積.................................30
3.2.3動量計算.........................................32
3.3 三維幾何模型之主軸對齊.............................32
第四章 校準與相似度評估..................................37
4.1 校準策略...........................................37
4.2 ICP演算法之原理與步驟..............................39
4.3 相似度評估 .......................................47
4.3.1相似度評估函數...................................49
4.3.2相似度量化.......................................50
第五章 應用實例與結果....................................53
5.1 系統簡介與流程.....................................53
5.2 應用實例一.........................................55
5.3 應用實例二.........................................68
5.4 應用實例三.........................................76
第六章 結論與未來展望....................................89
6.1結論................................................89
6.2未來展望............................................89
參考文獻.................................................91

[1] Park,K. and Cannon,D.,“Recognition and localization of
a 3D polyhedral object using neural network”,Proceeding
of the IEEE International Conference on Robotics and
Automation, 1996
[2] Bebis,G.N. and Papadourakis.G.M.,“Object Recongnition
using Invariant Object Boundary Representations and
Neural Network Models”, Pattern Recongnition, Vol.25,
No.1,pp,25-44,1992
[3] Zhang,D. and Hebert,M.“Harmonic Maps and Their
Applications in Surface Matching”,IEEE Conference on
Computer Vision and Pattern Recognition (CVPR'99), Vol.
2, 1999
[4] Hebert,M., Ikeuchi,K. and Delingette,H.,“A Spherical
Representation for Recognition of Free-Form Surfaces”,
IEEE Transactions on Pattern Analysis and Machine
Intelligence July 1995 (Vol. 17, No. 7)
[5] Okada,Y., “3D Model Database System by Hand Sketch Query
and Its Intuitive Interface,” 13th European-Japanese
Conference on Information Modeling and Knowledge Bases
(13EJC), Kitakyushu, Japan, pp. 889-892, June 2003
[6] Tuzikov,A.V, Roerdink, J.B.T.M., and Heijmans, H.J.A.M.,
“Similarity measures for convex polyhedra based on
Minkowski addition,” Pattern Recognition, Vol. 33, No.
6, pp. 979–995 ,2000
[7] Audette,M., Ferrie,F.P., and Peters,T.M., “An
algorithmic overview of surface registration techniques
for medical imaging”, Medical Image Analysis, Vol.4,
2000
[8] Ko,K.H, Maekawa,T.,and Patrikalakis,N.M.,“An algorithm
for optimal free-form object matching”,Computer-Aided
Design 35,(2003)913-923
[9] Huber,D.F. and Hebert,M.,“Fully automatic registration
of multiple 3D data sets,” Image and Vision Computing,
Vol.21, 2003
[10] Zhang,C. and Chen,T.,“Efficient Feature Extraction for
2D/3D Objects in Mesh Representation”,ICIP 2001

[11] Anthony P.R, Prokop,R.J., Susan E.A. and Frank P.K,
“Three-Dimensional Shape Analysis Using Moments and
Fourier Descriptors”,IEEE Trans. Pattern Analysis and
Machine Intelligence,pp. 937-943, Vol. 10, No. 6, Nov.
1988
[12] Vranic,D.V., Saupe,D. and Richter,J.,“Tools for
3D-object retrieval:Karhunen-Loeve Transform and
Spherical harmonics”,Proceedings of the IEEE Workshop
Multimedia Signal Processing, Cannes, France,2001
[13] Sheue-ling Lien and James T. Kajiya,“A Symbolic Method
for Calculating the Integral Properties of Arbitrary
Nonconvex Polyhedra”,IEEE Computer Graphics and
Applications,pp.35-41,Oct.1984
[14] Michael Kazhdan and Thomas Funkhouser.“Harmonic 3D Shape
Matching”,SIGGRAPH 2002 Technical Sketch
[15] Besl,P.J. and Mckay,N.D.,“A Method for Registration of
3-D Shapes”,IEEE Trans. Pattern Anal. Mach. Intell., vol.14,pp.239-256,
1992.

[16] Golub,G.H. and Van Loan,C.F.,“Matrix Computation”,
Baltimore,MD: Johns Hopkins Univ.Press,1983
[17] Schonemann,P.H.,“A generalized solution to the
Orthogonal procrustes problem”,Psychometrika,Vol.31,
No.1,1966
[18] Arun,K.S, Huang,T.S and Blostein,S.D,“Least square
Fitting of two 3-D point sets,”IEEE Trans. Patt. Anal.
Machine Intell. Voi. PAMI-9,No.5,1987
[19] 黃俊宏,“以VRML 物件內容為基礎之3D 模型資訊擷取系統”,
淡江大學資訊工程所碩士班碩士論文,2003
[20] 陳嘉復,“有效率的VRML 資料庫索引暨擷取機制”,真理大學
數理科學研究所碩士班碩士論文,2004
[21] 蘇龍祥,“使用模型表面距離進行三維模型萃取”,國立成功大
學資訊工程學系博士論文,2001
[22] 蔡明倫,“三度空間腦部結構校準”,國立交通大學資訊科學系
碩士論文,2002
[23] 許哲魁,“影像相似度評估函數之分析與比較”,國立交通大學
資訊工程碩士論文,2002
[24] 鐘永彬,“三角網面為基礎之曲面設計系統發展與應用”,國立
中央大學機械研究所碩士論文
[25] http://amp.ece.cmu.edu/projects/3DModelRetrieval/