本研究提出一套在三維空間中的工件缺陷檢測系統，藉由結合電腦圖學和影像處理技術，進行工件的缺陷檢測，以虛擬空間中的工件模型資訊做為理想樣本，同時取得實際空間中的工件影像，經由影像處理萃取影像特徵和比對，獲得相關參數資訊後，進而評估工件是否符合設計標準。
本研究將自行設計一運動機構平台，平台上裝設一台攝影機，藉由平台的機構運動，使得攝影機可以相對於進行檢測的工件作一半球面的運動，並可拍攝工件相對於攝影機的任一視角之影像；擷取工件的影像後，將其輸入至系統，藉由OpenGL的開源程式函式庫，可將由工件的CAD模型轉換而來的.OBJ檔繪製於Microsoft Visual Studio的Windows Form視窗上，並模擬於虛擬空間中攝影機拍攝虛擬工件的視角影像，藉由同步實際和虛擬的工件影像後，以背景消去法將工件影像分割出來，之後以影像處理等技術將兩者影像進行比對，以檢測工件是否存在缺陷。由目前的實驗結果可知，本研究目前可偵測之最小缺陷尺寸為3 mm。

An inspection system for defects detection of three-dimensional workpieces is proposed. This work proposes an idea of implementation of defects detection by combining computer graphics and digital image processing. The virtual CAD model of the workpiece is taken as the ideal sample. Meanwhile, the image of the real workpiece is captured by the camera. The proposed system extracts the features from both the real and virtual images and compares them by image processing. The acquired information by image processing is evaluated to examine if the workpiece is acceptable.
A moving platform mechanism, on which a camera is set, will be built up in the system. The camera is enabled to move along a surface of hemisphere through the movement of the platform. Thus it is able to acquire the images of the workpiece from every viewpoint. The acquired image is then input to the system. The CAD model of the workpiece which is converted from the .OBJ file is drawn on the Windows Form of the Microsoft Visual Studio. In this way, the images rendered from different viewpoints can be simulated in the virtual environment. By synchronizing the real and virtual images, the images of the workpiece, which is segmented from background subtraction, can be inspected with image processing. Both the real and virtual images will be compared to check if any defect exists. So far, the minimal defect size which could be detected by the proposed system is 3 mm.

Abstract I
摘要 II
致謝 III
目錄 VII
圖目錄 XI
表目錄 XX
第一章 緒論 1
1.1 前言 1
1.2 研究動機 1
第二章 文獻回顧 4
2.1 電腦輔助 4
2.2 測量技術 8
2.2.1 接觸式量測 8
2.2.2 非接觸式量測 9
2.2.2.1 非視覺量測 10
2.2.2.2 視覺量測 14
2.2.3 複合式量測 19
2.3 影像匹配 23
2.3.1 Harris Corner特徵 23
2.3.2 SIFT特徵 25
2.3.3 SURF特徵 29
2.4 幾何特徵識別 32
2.5 缺陷檢測 39
第三章 研究方法 48
3.1 實驗架構 49
3.2 運動平台 50
3.3 攝影機 52
3.4 影像處理 52
第四章 研究結果與討論 56
4.1 運動平台建構 56
4.1.1 平台機構實作 60
4.1.2 控制系統程式 63
4.1.2.1 運動平台初始化定位 65
4.1.2.2 運動轉換方程式推導 67
4.1.2.3 攝影機運動座標補償 70
4.1.2.4 運動方程式推導驗證 72
4.2 影像擷取系統 77
4.3 實驗方式 79
4.4 研究結果 81
4.4.1 工件影像分割 81
4.4.2 虛實影像比對 89
4.4.2.1 使用塊規進行檢測測試 90
4.4.2.2 使用正常工件進行檢測 92
4.4.2.3 使用缺陷工件進行檢測 95
4.4.2.4 比較不同缺陷程度之工件檢測結果 98
4.4.3 缺陷檢測結果 101
4.4.3.1 檢測結果呈現 105
4.4.3.2 檢測紀錄檔案輸出 106
4.4.4 不同外型物件之實驗結果 107
4.4.5 系統誤差來源 109
第五章 結論 116
5.1 本研究之貢獻 117
5.2 未來展望 118
5.2.1 硬體設備之改善 118
5.2.2 演算法之改良 119
5.2.3 未來發展趨勢 120
參考文獻 121

[1] I. Ainsworth, M. Ristic and D. Brujic, “CAD-based measurement path planning for free-form shapes using contact probes.” The International Journal of Advanced Manufacturing Technology, vol. 16, no. 1, pp. 23–31, 2000.
[2] T. J. Ko, J. W. Park, H. S. Kim and S. H. Kim, “On-machine measurement using a noncontact sensor based on a CAD model.” The International Journal of Advanced Manufacturing Technology, vol. 32, no. 7, pp.739–746, 2007.
[3] T. Lilienblum, P. Albrecht and B. Michaelis, “3D-Measurement of geometrical shapes by photogrammetry and neural networks.” Proceedings of the 13th International Conference on Pattern Recognition, pp. 330-334, 1996.
[4] S. Desai and B. Bidanda, “Reverse engineering: A review & evaluation of contact based systems.” Rapid Prototyping, vol. 6, pp. 107–131, 2006.
[5] Y. Li and P. Gu, “Free-form surface inspection techniques state of the art review.” Computer-Aided Design, vol. 36, no. 13, pp. 1395–1417, 2004.
[6] C. L. Chang and Y. H. Chen, “Measurements of fillet weld by 3D laser scanning system.” The International Journal of Advanced Manufacturing Technology, vol. 25, no. 5, pp. 466–470, 2005.
[7] T. H. Hsieh, W. Y. Jywe, H. L. Huang and S. L. Chen, “Development of a laser-based measurement system for evaluation of the scraping workpiece quality.” Optics and Lasers in Engineering, vol. 49, no. 8, pp. 1045–1053, 2011.
[8] R. Xia, J. Han, R. Lu and L. Xia, “Vision-based on-machine measurement for CNC machine tool.” Proc. SPIE 9446, Ninth International Symposium on Precision Engineering Measurement and Instrumentation, vol. 9446, pp. 94462P-1–94462P-8, 2015.
[9] Y. Huang, J. Gu, S. Wang, H. Xiao and K. Yuan, “Vision based embedded tiny spur gear inspection and measurement system.” IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1679-1684, 2016.
[10] J. Jurkovic, M. Korosec and J. Kopac, “New approach in tool wear measuring technique using CCD vision system.” International Journal of Machine Tools and Manufacture, vol. 45, no. 9, pp. 1023–1030, 2005.
[11] M. Ngom and F. Nagata, “Detection of workpieces on a CNC machining table for measurement and automatic tool positioning.” 14th International Conference on Control, Automation and Systems (lCCAS), pp. 55-58, 2014.
[12] M. Ngom and F. Nagata, “Basic design of a computer vision based controller for desktop NC engraving machine.” Proceedings of 2013 IEEE International Conference on Mechatronics and Automation (lCMA), pp. 1293-1298, 2013.
[13] H. P. Moravec, “Obstacle avoidance and navigation in the real world by a seeing robot rover.” Tech ReportCMU-RI-TR-3, Carnegie-Mellon University, Robotics Institute, 1980.
[14] C. Harris and M. Stephens, “A combined corner and edge detector.” In Fourth Alvey Vision Conference, Manchester, UK, pp. 147–151, 1988.
[15] D. G. Lowe, “Distinctive image features from scale-invariant keypoints.” International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004.
[16] H. Bay, A. Ess, T. Tuytelaars and L. Van Gool, “Speeded-up robust features (SURF).” Computer Vision and Image Understanding, vol. 110, no. 3, pp. 346–359, 2008.
[17] Wikipedia. Speeded up robust features. (December, 2016). Available:
https://en.wikipedia.org/wiki/Speeded_up_robust_features
[18] R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures.” Communications of the ACM, vol. 15, no. 1, pp. 11–15, 1972.
[19] G. Biegelbauer and M. Vincze, “Fast and robust bore detection in range image data for industrial automation.” Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission(3DPVT), pp. 526-533, 2004.
[20] Wikipedia. Hough transform. (December, 2016). Available:
https://en.wikipedia.org/wiki/Hough_transform#History
[21] P. V. C. Hough. “Method and means for recognizing complex patterns.” US 3,069,654, 1962.
[22] J. Canny, “A computational approach to edge detection.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679 - 698, 1986.
[23] Y. Xie and Q. Ji, “A new efficient ellipse detection method.” Proceedings. 16th International Conference on Pattern Recognition, pp. 957-960, 2002.
[24] N. Bonnot, R. Seulin and F. Merienne, “Machine vision system for surface inspection on brushed industrial parts.” Proc. SPIE 5303, Machine Vision Applications in Industrial Inspection XII, vol. 5303, pp. 64-72, 2004.
[25] H. Jia, Y. L. Murphey, J. Shi and T. S. Chang, “An Intelligent Real-time Vision System for Surface Defect Detection.” Proceedings of the 17th International Conference on Pattern Recognition(ICPR), pp. 239-242, 2004.
[26] X. W. Zhang, Y. Q. Ding, Y. Y. Lv, A. Y. Shi and R. Y. Liang, “A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM.” Expert Systems with Applications, vol. 38, no. 5, pp. 5930–5939, 2011.
[27] T. Y. Ong, Z. Samad and M. M. Ratnam, “Solder joint inspection with multi-angle imaging and an artificial neural network.” The International Journal of Advanced Manufacturing Technology, vol. 38, no. 5, pp. 455–462, 2008.
[28] M. Castejόn, E. Alegre, J. Barreiro and L.K. Hernánde, “On-line tool wear monitoring using geometric descriptors from digital images.” International Journal of Machine Tools and Manufacture, vol. 47, no. 12–13, pp. 1847–1853, 2007.
[29] H. Wu, X. Zhang, Y. Kuang and S. Lu, “A real-time machine vision system for solder paste inspection.” IEEE/ASME International Conference on Advanced Intelligent Mechatronics(AIM), pp. 205-210, 2008.
[30] D. M. Tsai, J. J. Chen and J. F. Chen, “A vision system for surface roughness assessment using neural networks.” The International Journal of Advanced Manufacturing Technology, vol. 14, no. 6, pp. 412–422, 1998.
[31] J. Illingworth and J. Kittler, “A survey of the hough transform.” Computer Vision, Graphics and Image Processing, vol. 44, no. 1, pp. 87–116, 1988.
[32] D. M. Tsai and C. T. Lin, “Fast normalized cross correlation for defect detection.” Pattern Recognition Letters, vol. 24, no. 15, pp. 2625–2631, 2003.
[33] Open GL web site. (December, 2016). Available:
https://www.opengl.org/
[34] Open CV web site. (December, 2016). Available:
http://opencv.org/
[35] Arduino official web site. (December, 2016). Available:
https://www.arduino.cc/
[36] RAMPS 1.4 – RepRapWiki. (June, 2017). Available:
http://reprap.org/wiki/RAMPS_1.4
[37] XD - 206 Collision Switch / Single Chip Microcomputer Module for Robot. (June, 2017). Available:
http://www.dealexpress.xyz/Boards-Shields-c18?product_id=21701&sort=rating&order=ASC&limit=75
[38] Point Grey web site. (December, 2016). Available:
https://www.ptgrey.com/
[39] AZURE Photonics web site. (December, 2016). Available:
http://www.azurephotonics.com/index.php?sn=home
[40] L. Y. Lei, X. J. Zhou, and M. Q. Pan, “Automated Vision Inspection System for the Size Measurement of Workpieces.” Instrumentation and Measurement Technology Conference, pp. 872-877, 2005.
[41] M. Leo, A. Natale, M. D. Coco, P. Carcagni and C.Distante, “Robust Estimation of Object Dimensions and External Defect Detection with a Low-Cost Sensor.” Journal of Nondestructive Evaluation, vol. 36, no. 1, pp. 1–16, 2017.