臺灣博碩士論文加值系統

由於建構工具的日益提升，製作三維模型的效率明顯有很大的提升。無論是在電影、電玩、建築等領域中都經常使用數量龐大的三維模型，因而三維模型檢索的相關技術自然成為目前一個熱門的研究議題。由於骨架是三維模型本質上的特徵，不易受形變因素所影響，與人類判斷物體外觀十分相符。因此在此一研究中，我們將探討以三維模型骨架為基礎的特徵擷取與資料檢索等議題，並且在滿足不變的拓樸性質下對於非剛體模型的運動形變仍能保持高度穩定的檢索結果。在論文中，首先介紹一個求取三角網格模型骨架的方法，主要透過對理想或非理想的三維模型進行體素化工作、計算關鍵點、向量場，進而讓關鍵點依照向量場方向連通起來而得到三維模型骨架。接著，以骨架結構取代原本以多邊形表面當作特徵的擷取對象，從模型骨架中擷取出拓樸性特徵來進行模型的檢索。我們以普林斯頓大學三維模型資料庫為例，測試與分析其執行成效。

As the effective development of modeling and rendering technology, the World Wide Web is enabling access to 3D models more and more by people. Retrieval by content of 3D models is becoming an important issue in the past few years. In this thesis, we present a new method, referred to as Curve-Skeleton of 3D models, that develops on the topological feature approach, with adaptations to support effective retrieval by content. According to the proposed method, a skeleton is computed for each model to obtain an invariant feature of deformable 3D models like human and animals. The skeletonization is based upon computing a so-called repulsive force field over a discretization of the 3D models and tracing the medial axis on the defined vector field. Then, we extract invariant features from the deformable 3D skeleton. Experimental results are presented to show the effectiveness of the Curve-Skeleton based retrieval method and its sensitivity to model deformations.

目錄

摘 要
Abstract
目錄
圖目錄
Chapter 1簡介
Chapter 2三維模型檢索技術之相關研究
2.1以主軸為基礎的相似度比對
2.1.1方位校正
2.1.2以主軸外形分佈為基礎的相似度比對
2.1.3以主軸切片為基礎的相似度比對
2.2以外形分佈為基礎的相似度比對
2.3以實心模型為基礎的相似度比對
2.4以轉換域為基礎的相似度比對
2.4.1 Radon轉換
2.4.2 二維傅利葉轉換
Chapter 3三維模型骨架化演算法
3.1 中軸轉換法
3.2 可控制參數實體細線法
3.2.1距離轉換(The Distance Transform)
3.2.2距離轉換的演算法
3.2.3 萃取關鍵點
3.3 使用一般性電位場骨架化三維物件
Chapter 4以骨架為基礎的三維特徵與模型檢索方法
4.1 體素化的步驟
4.2三維模型特徵擷取演算法
4.2.1 D2、D1、A3外型統計方法
4.2.2測地線演算法
4.3 特徵比對方式
Chapter 5實驗結果
5.1 骨架化前後分析
5.2 GD與A3特徵法
5.3 檢索結果
Chapter 6結論
參考文獻

[1]J. W.H. Tangelder and R. C. Veltkamp, “A Survey of Content Based 3D Shape Retrieval Methods,” Proceedings of the Shape Modeling International, 2004.
[2]T. Funkhouser, P. Min, M. Kazhdan, J. Chen, A. Halderman, and D. Dobkin, “A Search Engine for 3D Models,” ACM Transactions on Graphics, vol. 22, no. 1, pp. 83-105, January 2003.
[3]R. Ohbuchi, T. Minamitani and T. Takei, “Shape-Similarity Search of 3D Models by using Enhanced Shape Functions,” Theory and Practice of Computer Graphics 2003, Birmingham, U.K, pp. 97-104, June 2003.
[4]P. Jiantao, L. Yi, X. Guyu, Z. Hongbin, L. Weibin and Y. Uehara, “3D Model Retrieval Based on 2D Slice Similarity Measurements,” Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, 2004.
[5]R. Ohbuchi, T. Otagiri, M. Ibato and T. Takei, “Shape-Similarity Search of Three-Dimensional Models Using Parameterized Statistics,” Proceedings of the Pacific Graphics, Beijing, China, October 9-11, 2002.
[6]R. Osada, T. Funkhouser, B. Chazelle and D. Dobkin, “Matching 3D Models with Shape Distributions,” Int. Conf. on Shape Modeling and Applications (SMI 2001), pp. 154-166, 2001.
[7]J.H. Chuang, C.H. Tsai and M.C. Ko, “Skeletonzation of Three-Dimensional Object using Generalized Potential Field,” Pattern Analysis and Machine Intelligence, IEEE Transactions, vol. 22, Issue. 11, pp. 1241-1251, Nov. 2000.
[8]N.D. Cornea, M.F. Demirci, D. Silver, Ali Shokoufandeh, S.J. Dickinson and P.B Kantor, “3D object retrieval using many-to-many matching of curve skeletons,” 2005 International Conference, Shape Modeling and Applications, June 13-17, 2005.
[9]N.D Cornea, D. Silver, X. Yuan and R. Balasubramanian, “Computing hierarchical curve-skeletons of 3D objects,” The Visual Computer, vol. 21 no.11 pp. 945-955, October, 2005.
[10]J.-L. Shin, C.-H. Lee and J.T. Wang, “3D object retrieval system based on grid D2,” Electronics letters 17th, vol. 41 no. 4, February 2005.
[11]N. Gagvani and D. Silver, “Parameter controlled volume thinning,” Manuscript for Graphical Models and Image, May 1999.
[12]H. Sundar, D. Silver, N. Gagvani amd S. Dickinson, “Skeleton based shape matching and retrieval,” Proceeding of the Shape Modeling International, 2003.
[13]Y. Keselman, A. Shokoufandeh, M.F. Demirci and S. Dickinson, “Many-to-many graph matching via metric embedding,” Proceedings of the IEEE computer society conference on computer vision and pattern recognition, 2003.
[14]M.T. Suzuki, T. Kato and H. Tsukune, “A Statistical Method for Subjective Retrieval of 3D Objects,” Trans. IEICE, DI, vol. j82-DI, pp. 184-192, 1999.
[15]Y. Liu, J. Pu, G. Xin and H. Zha, “A robust method for shape-based 3D model retrieval,” Proceedings of the 12th Pacific conference, computer graphics and applications, 2004.
[16]J. P. Vandeborre, V. Couillet and M. Daoudi, “A practical approach for 3D model indexing by combining local and global invariants,” Proceedings of the First International Symposium on 3D Data Processing Visualization and Transmission, 2002.
[17]P.-C. Liu, F.-C. Wu, W.-C. Ma, R.-H. Liang and M. Ouhyoung, “Automatic animation skeleton construction using repulsive force field,” Proceedings of the 11th Pacific Conference on Computer Graphics and Applications, 2003.
[18]N. Ahuja and J.-H. Chuang, “Shape representation using a generalized potential field model,” IEEE transactions on pattern analysis and machine intelligence, vol. 19, no. 2, pp. 169-176, February 1997.
[19]H. Dutağc, B. Sankur and Y. Yemez, “Transform-based methods for indexing and retrieval of 3D objects,” Proceedings of the fifth international conference on 3D digital imaging and modeling, 2005.
[20]P. Daras, D. Zarpalas, D. Tzovaras and M. G. Strintzis, “Efficient 3-D model search and retrieval using generalized 3-D radon transforms,” IEEE Transactions on Multimedia, vol. 8, no. 1, pp. 101-114, February 2006.
[21]T. Itoh, Y. Yamaguchi and K. Koyamada, “Fast isosurface generation using the volume thinning algorithm,” IEEE Transactions on Visualization and Computer Graphics, vol. 7, no. 1, pp. 32-46, 2001.
[22]N. Vajramushti, I.A. Kakadaris, T. Theoharis and G. Papaioannou, “Efficient 3D object retrieval using depth images,” Proc. ACM, MIR’04, New York, USA, October 15-16, 2004.
[23]R. Ohbuchi, M. Nakazawa and T. Takei, “Retrieving 3D Shapes based on their appearance,” Proc. ACM, MIR’03, Berkeley, California, USA, November 7, 2003.
[24]K. Kaku, Y. Okada and K. Niijima, “Similarity measure based on ObbTree for 3D model search,” Proceedings of the international conference on computer graphics, imaging and visualization, 2004.
[25]Princeton University, Princeton Shape Retrieval and Analysis Group, 3D Models Search Engine, http://shape.cs.princeton.edu/search.html.
[26]R. Osada, T. Funkhouser, B. Chazelle and D. Dobki, “Shape Distribution,” ACM Transactions on Graphics, vol. 21, no. 4, pp. 807-832, 2002.
[27]D. Parikh, R.Sukthankar, T. Chen and M. Chen, “Feature-based Part Retrieval for Interactive 3D Reassembly,” Proceeding of the IEEE Workshop on applications of computer vision, 2007.
[28]J. Assfalg, M. Bertini, A.D. Bimbo and P. Pala, “Content-Based Retrieval of 3-D Objects Using Spin Image Signatures,” Proceedings of the Multimedia, IEEE transaction, vol. 9, Issue 3, pp. 589-599, April, 2007.