臺灣博碩士論文加值系統

隨著近年來網際網路以及電腦軟體硬體的快速發展，三維模型在各個工作領域上已被廣泛的使用，三維模型的數量也是與日劇增，如電玩遊戲、電影道具、3D列印、文創產業、工業設計、模具打樣...等等。因此如何建立一個有效的搜尋系統來幫助使用者獲得符合使用者個人期待的三維模型，是一個重要的發展目標。本論文希望以三維模型本身的變化為依據，能夠改善傳統以文字為檢索的缺點，來幫助使用者獲得更好的檢索效果。
在本論中提出了基與球面投影維基礎之三維模型檢索系統。我們使用網格主軸分析演算法(Grid-based PCA，GPCA)將模型擺正後，進行大小的正規化，再透過球型座標系統(Spherical coordinate system)及內差法轉換為球型座標圖，三維模型由內至外，取得模型的形狀變化。並通過一維(Discrete Fourier Transform)及二維傅立葉轉換(2D-Discrete Fourier Transform)的方式將球座標圖轉換為頻譜圖後，擷取頻率域上低頻的特徵，最後利用k-means演算法建立編碼簿，並利用詞袋分析的結果，來進行三維模型檢索。在實驗方面，本論文使用常用的三維模型測試資料庫來測試三維模型檢索系統的效能，分別為：Princeton Shape Benchmark(PSB)、3D Shape Retrieval Contest 2015(SHREC2015)、3D Shape Retrieval Contest Watertight (SHREC-W)

In this thesis, a 3D model retrieval system will be proposed based on the discrete Fourier transform (DFT) feature descriptors extracted from spherical projections. First, the grid-based principal component analysis (GPCA) is used to align 3D models. Based on the spherical coordinate system, spherical projections can be obtained. Then 2D low-frequency feature (2DL), horizontal average low-frequency feature (HAL), overlap horizontal average low-frequency feature (OHAL), vertical average low-frequency feature (VAL), and overlap vertical average low-frequency feature (OVAL) are extracted as feature vector for 3D model retrieval. This thesis applied the bag-of-words paradigm to learn the descriptor. The codebook is learned by applying k-means clustering.
The experiments will be conducted on several well-known 3D model databases, including the Princeton Shape Benchmark (PSB), Shape Retrieval Contest Watertight (SHREC’W), 2015 Range Scans based 3D Shape Retrieval (SHREC’15).

摘要
ABSTRACT
致謝
表目錄
圖目錄
第一章 簡介
第二章 相關文獻
2.1 基於投影圖方式的特徵(view-based methods)
2.2 基於轉換方式特徵(transform-Based Methods)
2.3 統計直方圖的特徵(histogram-Based Methods)
第三章 系統流程
3.1 模型擺正及大小正規化
3.2 球型座標系統
3.3 特徵擷取
3.3.1 二維低頻特徵(2D low-frequency feature)
3.3.2 水平平均低頻特徵(Horizontal Average low-frequency feature)
3.3.3 重疊水平平均低頻特徵(overlap Horizontal Average low-frequency feature)
3.3.4 垂直平均低頻特徵(Vertical Average low-frequency feature)
3.3.5 重疊垂直平均低頻特徵(overlap Vertical Average low-frequency feature)
3.3.6 分群及建立編碼簿
第四章 實驗
4.1 PSB資料庫
4.2 SHREC′W資料庫
4.3 SHREC′15資料庫
第五章 結論
第六章 參考文獻

[1]https://3dwarehouse.sketchup.com/?hl=zh-TW
[2]Xiang Bai, Cong Rao, Xinggang Wang, “Shape Vocabulary: A Robust and Efficient Shape Representation for Shape Matching” in IEEE transactions on image processing, vol. 23, no. 9, september 2014
[3]Xiang Bai, Song Bai, Zhuotun Zhu, Longin Jan Latecki, “3D Shape Matching via Two Layer Coding” in IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 12, December 2015
[4]D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Computer Vision, vol. 60, no. 2, pp. 91–110, 2004.
[5]P. Papadakis, I. Pratikakis, T. Theoharis, and S. J. Perantonis,“Panorama: A 3D shape descriptor based on panoramic views forunsupervised 3D object retrieval” Int. J. Computer Vision, vol. 89,nos. 2/3, pp. 177–192, 2010
[6]K. Sfikas, T. Theoharis and I. Pratikakis “Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval” Eurographics Workshop on 3D Object Retrieval (2017)
[7]Lecun Y., Bottou L., BengioY., Haffner P. “Gradient based learning applied to document recognition” Proceedings of the IEEE 86, 11 (1998), 2278–2324
[8]Zhizhong Han, Zhenbao Liu, Junwei Han,Chi-Man Vong, Shuhui Bu,Xuelong Li“Unsupervised 3D Local Feature Learning by Circle Convolutional Restricted Boltzmann Machine” in IEEE transactions on image processing, vol. 25, no. 11, september 2016
[9]Hideki Sagara, Shigeru Takano, Yoshihiro Okada “3D Model Data Retrieval System Using KAZE Feature for Accepting 2D Image as Query” 2016 10th International Conference on Complex, Intelligent, and Software Intensive Systems
[10]Qionghai Dai, Yue Gao, Nai-Yao Zhang “3D model comparison using spatial structure circular descriptor” Pattern Recognition vol.43 (2010) 1142 -1151
[11]T. Furuya, S. Kurabe, R. Ohbuchi “Randomized Sub-Volume Partitioning for Part-Based 3D Model Retrieval” Eurographics Workshop on 3D Object Retrieval (2015)
[12]Indriyati Atmosukarto and Linda G. Shapiro, “3D object retrieval using salient views”, International Journal of Multimedia Information Retrieval, vol. 2, no. 2, pp. 103-115, Jun. 2013
[13]Bruce Fischl, Martin I. Sereno, Roger B.H. Tootell, Anders M. Dale “High-Resolution Intersubject Averaging and a Coordinate System for the Cortical Surface” Human Brain Mapping ,272–284(1999)
[14]D. V. Vranic and D. Saupe, “3d shape descriptor based on 3d fourier transform”, in Proceedings of EURASIP Conference on Digital Signal Processing for Multimedia Communications and Services (ECMCS 2001), Budapest, pp. 271-274, Sept. 2001
[15]Ceyhun Burak Akgül, Bülent Sankur, Yücel Yemez and Francis Schmitt, “3D Model Retrieval Using Probability Density-Based Shape Descriptors”, in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 6, June. 2009
[16]P. Shilane, p. Min, M. Kazhdan and T. Funkhouser, “The Princeton Shape Benchmark”, in Reoceedings of the Shape Modeling Application, pp. 167-178, 2004
[17]Daniela Giorgi, Silvia Biasotti and Laura Paraboschi, “SHREC 2007: 3D Shape Retrieval Contest”, in Technical Report UUCS-2007-015, pp. 5-10, June. 2007
[18]Z. Lian, J. Zhang, S. Choi, H. ElNaghy, J. El-Sana, T. Furuya, A. Giachetti, R.A. Guler, L. Isaia, L. Lai, C. Li, H. Li, F.A. Limberger, R. Martin, R.U. Nakanishi, A.P. Neto, L.G. Nonato, R. Ohbuchi, K. Pevzner, D. Pickup, P. Rosin, A. Sharf, L. Sun, X. Sun, S. Tari, G. “SHREC’15 Track: Non-rigid 3D Shape Retrieval”, Eurographics Workshop on 3D Object Retrieval (2015)
[19]B. K. P. Horn, “Extended Gaussian Image”, in Proc. Of IEEE, Vol. 72, No. 12, pp. 1671-1686, Dec. 1984.
[20]T. Zaharia and F. J. Preteux, “Shape-Based Retrieval of 3D Mesh Models”, in IEEE international fonference on Multimedia, Vol. 1, pp. 437-440, 2002
[21]F. Wang, L. Lin* and M. Tang, “sketch-based 3D model retrieval approach by using global and local features”, Graphical Models, Vol. 76, Issue 3, pp. 128-139, 2014.
[22]M. M. Kazhdan, T. A. Funkhouser, and S. Rusinkiewicz, “Rotation invariant spherical harmonic representation of 3D shape descriptors,” in Symposium on Geometry Processing, 2003, pp. 156–164
[23]M. Kazhdan, T. Funkhouser and S. Rusinkiewicz, “Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors”, Symposium on Geometry Processing, 2003.
[24]B. K. P. Horn, “Extended Gaussian Image”, in IEEE, Vol. 72, No. 12, pp. 1671-1686, Dec. 1984.
[25]J. Assfalg, A. D. Bimbo and P. Pala, “Content-based Retrieval of 3D Models Through Curvature Maps: A CBR Approach Exploiting Media Conversion”, in Multimedia Tools and Application, Vol. 31, No. 1, pp. 29-50, 2006.
[26]D. Zarpalas, P. Daras, A. Axenopoulos, D. Tzovaras and M. G. Strintzis, “3D Model Search and Retrieval Using the Spherical Trace Transform”, EURASIP Journal on Applied Signal Processing, Vol. 2007, pp. 207-207, 2007.
[27]T. F. Ansary, M. Daoudi and J. P. Vandeborre, “A Bayesian 3-D Search Engine Using Adaptive Views Clustering”, in IEEE Transactions on Multimedia, Jan. 2007.
[28]H. Laga, H. Takahashi and M. Nakajima, “Spherical Wavelet Descriptors for Content-Based 3D Model Retrieval”, in IEEE international conference on Shape Modeling and Application, 2006.
[29]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.
[30]D. V. Vranic, “3D Model Retrieval”, Ph. D. Thesis, University of Leipzig, 2004.
[31]J. Assfalg, A. D. Bimbo and P. Pala, “Content-based Retrieval of 3D Models Through Curvature Maps: A CBR Approach Exploiting Media Conversion”, in Multimedia Tools and Application, Vol. 31, No. 1, pp. 29-50, 2006.
[32]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.
[33]C. H. Lee, J. L Shih, C. H. Chou, K. M. Yu and C. Y. Hung, “3D Model Retrieval Using 2D Cepstral Features”, in IEEE international conference Acoustics, Speech and Signal Processing (ICASSP), pp. 2365 - 2368, 2012.
[34]Song Bai, Xiang Bai “Sparse Contextual Activation for Efficient Visual Re-Ranking” in IEEE transactions on image processing, VOL. 25, NO. 3, MARCH 2016
[35]H. Tabia, M. Daoudi, J.-P. Vandeborre, and O. Colot, “A new 3D-matching method of nonrigid and partially similar models using curve analysis,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 4, pp. 852–858, Apr. 2011.
[36]H. Tabia, H. Laga, D. Picard, and P.-H. Gosselin, “Covariance descriptors for 3Dshape matching and retrieval” in IEEE Computer Society Conference on Computer Vision Pattern Recognition, 2014, pp. 4185–4192.
[37]Radu Bogdan Rusu, Nico Blodow, Michael Beetz, “Fast Point Feature Histograms (FPFH) for 3D Registration” 2009 IEEE International Conference on Robotics and Automation.
[38]OHBUCHI R., FURUYA T“Scale-weighted dense bag of visual features for 3d model retrieval from a partial view 3d model. ” In Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference, pp. 63–70.
[39]RUSU R. B., BLODOW N., BEETZ M “Fast point feature histograms (fpfh) for 3d registration.” in Robotics and Automation, 2009. ICRA’09. IEEE International Conference on (2009), IEEE, pp. 3212–3217.
[40]JOHNSON A. E., HEBERT M. “Using spin images for efficient object recognition in cluttered 3d scenes.” Pattern Analysis and Machine Intelligence, vol. 21, no. 5 (1999), 433–449
[41]LEIBE B., LEONARDIS A., SCHIELE B “Combined object categorization and segmentation with an implicit shape model. ” in Workshop on statistical learning in computer vision, ECCV (2004), vol. 2, p. 7
[42]DUTAGACI H., GODIL A., AXENOPOULOS A., DARAS P., FURUYA T., OHBUCHI R“Shrec’09 track: Querying with partial models”. in 3DOR (2009).