製鞋業為台灣重要的傳統產業，雖然近幾十年以來不斷有自動化的技術導入到鞋子的生產過程，然而一雙成品鞋仍需經過兩百多個人的手，才能完成。甚至在最重要的鞋面部的設計，需靠有經驗的技師才能完成鞋子的設計。在本論文中，我們實現一套從3D鞋楦模型轉換至2D鞋面布樣轉換系統，提升製鞋技術的自動化。本論文所提出的自動化設備包含：三維掃描平台及四軸裁切機，所提出的系統流程為使用三維掃描平台擷取鞋楦不同角度的3D表面點雲資料，在將多個表面點雲進行對位融合出一個完整三維點雲鞋楦模型。再透過人工選點選取鞋楦模型上的鞋面布分割參考點，並將鞋面布切割，攤平成2D鞋面布圖樣，為了能獲得全尺寸的鞋面布圖樣，針對每一部分依標準尺碼的三維資訊與二維資訊進行分段級放得到全尺寸的鞋楦模型及鞋面布樣板，所提出的系統也整合入一排版演算法，針對鞋面布進行固定面積排版，再由切割機控制程式依排版結果規畫路徑，根據鞋面輪廓進行移動規劃，完成切割。

Shoe making is an important traditional industry in Taiwan. Although automation technology has been introduced into the shoe production process in recent decades, a pair of finished shoes still needs more than 200 hands to complete. Even in the most important shoe face design, it needs experienced technicians to complete the design of shoes. In this paper, we implement a set of conversion system from 3D shoe last model to 2D shoe upper cloth sample, which improves the automation of shoe making technology. The automation equipment proposed in this paper includes three-dimensional scanning platform and four axis cutting machine. The proposed system process is to use the three-dimensional scanning platform to capture the 3D surface point cloud data of shoe last from different angles, and then integrate multiple surface point clouds to form a complete three-dimensional point cloud shoe last model. In order to obtain the full-size vamp pattern, the full-size shoe last model and upper cloth template are obtained by segmenting each part according to the 3D and 2D information of standard size. The proposed system is also integrated into a layout calculation According to the layout results, the cutting machine control program plans the path according to the typesetting results, and carries out the movement planning according to the upper contour to complete the cutting.

摘要 i
Abstract ii
目錄 iii
表目錄 v
圖目錄 vi
第一章 緒論 1
1.1 研究動機 1
1.2 三維物體重建的研究 2
1.3 三維影像轉二維影像 3
1.4 二維排版 ( 2D Nesting ) 3
1.5 論文結構 4
第二章 三維物體重建 6
2.1 點雲擷取平台 6
2.2 擷取點雲 8
2.3 點雲三維對位(Point Cloud Three-dimensional Alignment) 10
2.4 點雲濾波 14
第三章 3D鞋楦模型轉換2D鞋面布 16
3.1 傳統鞋楦攤平鞋面布 16
3.2 程式實際運算結果 17
3.3 鞋面布級放 20
第四章 排版演算法 22
4.1 排版方法 22
4.2裁切機路徑演算 22
第五章 實驗結果與討論 24
5.1 合併對位 24
5.2 鞋面布攤平 26
5.3 級放結果 30
5.4 排版程式 32
5.5 鞋面布裁切 33
第六章 結論 37
參考文獻 38

[1]V. Milenkovic, K. Daniels, and Z. Li, "Placement and Compaction of Nonconvex Polygons for Clothing Manufacture," In Proceedings of Fourth Canadian Conference on Computational Geometry, Newfoundland, pp. 236-243, 1992.
[2]R. N. Rao and M. V. N.K. Talluri, "An overview of recent applications of inductively coupled plasma-mass spectrometry (ICP-MS) in determination of inorganic impurities in drugs and pharmaceuticals", Journal of Pharmaceutical and Biomedical Analysis., vol. 43, no. 1, pp. 1-13, 2007.
[3]D. Beauchemin, "Environmental analysis by inductively coupled plasma mass spectrometry", Mass Spectrom. Rev, vol. 29, no. 4, pp. 560-592, 2010.
[4]Chia-Cheng Liu ,"Mark nesting in clothing industry using Semi-Discrete Representations," International Joint Conference on Computational Sciences and Optimization, vol. 02,pp .908-912, 2009.
[5]Suzuki, S. and Abe, K., "Topological Structural Analysis of Digitized Binary Images by Border Following,"Computer Vision,Graphics,And Image Processing 30 1, pp 32-46, 1985.
[6]How to Make a Shoe Pattern.(2019)from https://reurl.cc/VXpALQ (April 21,2019)
[7]Wade Motawi.(2015). How Shoes are Made.America: Wade's Place
[8]H. Wang, Z. Wu, Y. Zhang, B. Chen, M. He and B. Hu, "Chip-based liquid phase microextraction combined with electrothermal vaporization-inductively coupled plasma mass spectrometry for trace metal determination in cell samples", Journal of Analytical Atomic Spectrometry ., vol. 28, no. 10, pp. 1660-1665, 2013
[9]Satoshi Suzuk, "Topological structural analysis of digitized binary images by border following," Computer Vision, Graphics, and Image Processing Volume 30, Issue 1, pp. 32-46, April 1985.
[10]P.C. Gilmore and R.E. Gomory, "A Linear Programming Approach to the Cutting Stock Program," Operation Research, pp. 848-859, 1961.
[11]P.C. Gilmore, and RE. Gomory, "Multi Stage Cutting Stock Problems of Two and More Dimension ,"Operation Research, pp. 94-120, 1964.
[12]Z. Li, and V. Milenkovic, "Compaction and Separation Algorithms for Nonconvex Polygons and their Applications," European Journal of Operational Research, pp. 539-561, 1995.
[13]S.K. Cheng, and K.P. Rao, "Concepts of Neighbourhood and Universal Compact Yield Towards Achieving Best Pattern Layouts," International Journal of Production Research, pp. 3643-3658, 1999.
[14]H. Ma,and C.C. Liu, "Fast Nesting of 2-D Sheet Parts with Arbitrary Shapes Using a Greedy Method and Semi-discrete Representations," IEEE Transactions on Automation Science and Engineering,pp. 273-282, 2007.
[15]H. Ma,and C.C. Liu, "A 2-D Profile Packing Approach for Multi-Torch Flame Cutting," International Journal of Production Research, pp. 2841-2857, 2007.
[16]M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler and S. Hochreiter, "GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium", Neural Information Processing Systems,pp. 6629-6640, 2017.
[17]Z. Cao, T. Simon, S. Wei and Y. Sheikh, "Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields", Computer Vision and Pattern Recognition,pp. 7291-7299, 2017.
[18]X. Han, Z. Wu, Z. Wu, R. Yu and L. S. Davis, "VITON: An Image-based Virtual Try-on Network", Computer Vision and Pattern Recognition,pp. 7543-7552, 2018.
[19]X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang and S. P. Smolley, "Least Squares Generative Adversarial Networks", International Conference on Computer Vision ,pp. 2794-2802, 2017.
[20]J.-Y. Zhu, T. Park, P. Isola and A. A. Efros, "Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks", International Conference on Computer Vision ,pp. 2223-2232, 2017.
[21]Z. Li, and V. Milenkovic, "Compaction and Separation Algorithms for Nonconvex Polygons and their Applications," European Journal of Operational Research, pp. 539-561, 1995.
[22]V. Milenkovic, "Rotational Polygon Containment and Minimum Enclosure Using Only Robust 2D Constructions," Computational Geometry, Vol. l3, pp. 3-l9, 1999.
[23]Suzuki, S. and Abe, K., "Topological Structural Analysis of Digitized Binary Images by Border Following,"Computer Vision,Graphics,And Image Processing 30 1, pp. 32-46, 1985.
[24]Dingxuan. Zhao, Lili.Wang, Yilei.Li,and Miaomiao. Dua, Extraction of preview elevation of road based on 3D sensor, Measurement Volume 127, pp. 104-114, October 2018.