臺灣博碩士論文加值系統

現今電腦科技的蓬勃發展，三維模型掃描與建製的技術也有著顯著的提升，在許多地方都看的到三維模型的應用，如電影特效與電腦遊戲中。而隨著製作三維模型的技術越來越好，如今使用者在製作三維模型相對以往可以較方便的可以製作出各種三維模型。而針對這些多樣化的模型，我們希望可以利用一個較精確的檢索方法來幫助使用者找尋想要的三維模型。
在本論文中提出了以二維極座標頻譜特徵(2D Polar spectral feature)與二維極座標倒頻譜特徵(2D Polar cepstral feature)為基礎之三維模型檢索系統。首先將利用網格主軸分析演算法(Grid-based PCAs, GPCA)，來擺正模型，接著我們將對擺正的三維模型從六個不同的視角作六立面投影，產生六張灰階(gray-level)的投影圖，稱為立面圖。針對這些立面圖，使用二維傅立葉轉換(2D discrete fourier transform)取得其二維頻譜(2D spectral)，並且為了強調低頻部份，將利用極座標轉換(polar transform)將二維頻譜圖轉成二維極座標頻譜圖(2D polar spectral)，之後再對二維極座標頻譜圖利用不同的區塊分解方法，包含均勻區塊分解(uniform subband decomposition)、X軸區塊分解(X-axis overlap subband decomposition)、Y軸區塊分解(Y-axis low-frequency subband decomposition)、低頻部份區塊分解(Low-frequency subband decomposition)和合併區塊分解(combine subband decomposition)，之後計算每個頻譜區塊內的能量總和值，再做反向二維傅立葉轉換進而得到二維倒頻譜特徵。為了使檢索系統更加完善，將X軸與Y軸合併區塊分解的頻譜與倒頻譜特徵進行結合。而在搜尋的部份，可利用特徵向量在資料庫中找出使用者想搜尋的3D模型並回應相似度較高的三維模型給使用者。預計將採用五種資料庫來驗證系統的效能，分別為為普林斯頓 (Princeton Shape Benchmark ) 、Purdue Engineering Shape Benchmark (ESB)、SHREC Watertight (SHREC-W)、National Institute of Standards and Technology (NIST)。

In this paper, 2D polar spectrum and cepstrum features will be proposed for 3D model retrieval. First, the grid-based principal component analysis (GPCA) is used to align 3D models. Then, six projection images representing the elevation (depth) value are generated. 2D polar spectrum and cepstrum features are extracted from each projection image for searching similar 3D models. The performance of the experiments conducted on the four databases will be compared with other state-of-the-art descriptors.

摘 要 i
ABSTRACT ii
致 謝 iii
內 容 iv
表格列表 v
圖片列表 vi
第一章 1
第二章 4
第三章 7
3.1 前處理 8
3.1.1 三維模型正規化 8
3.1.2 六立面投影 9
3.2 二維極座標頻譜特徵擷取 10
3.2.1 傅立葉轉換 11
3.2.2 極座標轉換 11
3.2.3 二維極座標均勻區塊分解頻譜特徵 12
3.2.4 二維極座標X軸區塊分解頻譜特徵 13
3.2.5 二維極座標Y軸區塊分解頻譜特徵 14
3.2.6 二維極座標低頻部份區塊分解頻譜特徵 15
3.2.7 二維極座標合併區塊分解頻譜特徵 16
3.3 二維極座標倒頻譜特徵擷取 17
3.3.1二維極座標均勻區塊分解倒頻譜倒特徵 18
3.3.2二維極座標X軸區塊分解頻譜倒特徵 19
3.3.3二維極座標Y軸區塊分解頻譜倒特徵 20
3.3.4二維極座標低頻部份區塊分解頻譜倒特徵 20
3.3.5二維極座標合併區塊分解頻譜倒特徵 21
3.4 特徵合併 22
3.4.1二維極座標均勻區塊分解倒頻譜倒特徵 23
3.4.2二維極座標均勻區塊分解倒頻譜倒特徵 23
第四章 24
4.1 實驗第一個資料庫，PSB資料庫 24
4.2 實驗第二個資料庫，ESB資料庫 30
4.3 實驗第三個資料庫，SHREC-W資料庫 35
4.4 實驗第四個資料庫，NIST資料庫 39
第五章 45
參考文獻 46

[1] https://www.google.com.tw/webhp?source=search_app
[2] http://sketchup.google.com/3dwarehouse/forum?hl=zh-TW
[3] T. Funkhouser, P. Min, M. Kazhdan, J. Chen, A. Halderman, D. Dobkin, and D. Jacobs, “A Search Engine for 3D Models,” ACM Trans. on Graphics, Vol. 22, pp. 83-105, 2003.
[4] N. Iyer, S. Jayanti, K. Lou, Y. Kalyanaraman, and K. Ramani, “Three-Dimensional Shape Searching: state-of-the-art review and future trends,” Computer-Aided Design, Vol. 37, No. 5, pp. 509-530, 2005.
[5] Y. Guo, F. Sohel, M. Bennamoun, M. Lu and J. Wan, “Rotational Projection Statistics for 3D Local Surface Description and Object Recognition”, International Journal of Computer Vision, Vol 105, Issue 1 , pp 63-86, 2013
[6] X. Pan, Q. You, Z. Liu and Q. H. Chen, “3D shape retrieval by Poisson histogram,” Pattern Recognition Letters, Vol. 32, Issue 6, pp. 787-794, 2011.
[7] M. Ramezani and H. Ebrahimnezhad “3D Models' Retrieval System Design Based on Poisson's Histogram of 2D Selective Views” 21st Iranian Conference on Electrical Engineering (ICEE)”, May 2013
[8] D. V. Vranic and D. Saupe, “3D Model Retrieval,” in Proc. of Spring Conference on Computer Graphics and its Applications (SCCG2000), Budmerice Manor, Slovakia, pp. 89-93, May. 2000
[9] J. L. Shih, Y. H. Liu, and F. C. Tsao, ”Combination of 3D Discrete Fourier Transform and 3D Angular Radial Transform for 3D Model Retrieval”, Journal of Information Technology and Applications, Vol. 7, No. 1, pp. 21-29 2013
[10] C. B. Akgul, B. Sankur, Y. Yemez and F. Schmitt, “3D Model Retrieval Using Probability Density-Based Shape Descriptors,” IEEE Transactions on Pattern Analysis And Machine Intelligence, Vol. 31, No. 6, pp. 1117-1133, June 2009.
[11] P. Papadakis, I. Pratikakis, S. Perantonis and T. Theoharis, “Efficient 3D Shape Matching and Retrieval Using a Concrete Radialized Spherical Projection Representation,” Pattern Recognition, Vol. 40, pp. 2437-2452, 2007.
[12] D. V. Vranic and D. Saupe, “3D Shape Descriptor Based on 3D Fourier Transform,” in Proc. of EURASIP Conf. on Digital Signal Processing for Multimedia Communications and Services (ECMCS 2001) (editor K. Fazekas), Budapest, Hungary, pp. 271-274, Sep 2001.
[13] C. Zou, C. Wang, Y. Wen, L. Zhang and J. Liu, “Viewpoint-Aware Representation for Sketch-Based 3D Model Retrieval”, IEEE Signal Processing Letters, Vol. 21, Issue 8, pp. 966-970, 2014
[14] M. Aono, H. Koyanagi and A. Tatsuma, “3D shape retrieval focused on holes and surface roughness”, Asia-PacificSignal and Information Processing Association Annual Summit and Conference (APSIPA), 2013
[15] J. L. Shih and H. Y. Chen, “A 3D Model Retrieval Approach Using the Interior and Exterior 3D Shape Information,” Multimedia Tools and Applications, Vol. 43, pp. 45-62, 2008.
[16] J. L. Shih, C. H. Lee and J. T. Wang, “A New 3D Model Retrieval Approach Based on the Elevation Descriptor,” Pattern Recognition, Vol. 40, No. 1, pp. 283-295, 2007.
[17] Y. Ohishi and R. Ohbuchi, “Densely sampled local visual features on 3D mesh for retrieval”, International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), 2013
[18] H. Tabiaa, M. Daoudib, J. P. Vandeborreb and O. Colota,” Deformable Shape Retrieval using Bag-of-Feature techniques”, Proc. SPIE 7864, Three-Dimensional Imaging, Interaction, and Measurement, January 27, 2011
[19] C. B. Akgül, B. Sankur, Y. Yemez, and F. Schmitt, “Density-based 3D shape descriptors”, EURASIP Journal on Applied Signal Processing, Vol. 2007, pp. 1-16, 2007
[20] T. Tung and F. Schmitt, “The Augmented Multiresolution Reeb Graph Approach for Content-Based Retrieval of 3D Shapes,” International Journal of Shape Modeling, Vol. 11, No. 1, 2005
[21] J. L. Shih, C. H. Lee and C. H. Chuang, “A 3D Model Retrieval Approach Based on the Combination of PCA Plane Projections,” Journal of Information Technology and Applications, Vol. 5, No. 2, pp. 46-102, 2011.
[22] C. W .Wang, “A 3D Model Retrieval Using Local Spectral and Local Cepstral Feature”
[23] C. B. Akgul, B. Sankur, Y. Yemez and F. Schmitt, “3D Model Retrieval Using Probability Density-Based Shape Descriptors,” IEEE Transactions on Pattern Analysis And Machine Intelligence, Vol. 31, No. 6, pp. 1117-1133, June 2009.
[24] P. Shilane, P. Min, M. Kazhdan and T. Funkhouser, “The Princeton Shape Benchmark,” in Proc. of the Shape Modeling Applicat, pp. 167-178, 2004.
[25] S. Jayanti, K. Kalyanaraman, N. Iyer, and K. Ramani, “Developing an Engineering Shape Benchmark for CAD Models”, Computer-Aided Design, Vol. 38, No. 9, pp. 939-953, 2006.
[26] R. C. Veltkamp and F.B. ter Haar, eds., “SHREC 2007: 3D Shape Retrieval Contest”, Technical Report UUCS-2007-015, pp. 5-10, June 2007.
[27] R. Fang, A. Godill, X. Li, and A. Wagan, “A New Shape Benchmark for 3D Object Retrieval”, Proc. Int. symposium on advances in visual computing, pp. 381-392, 2008.