由於傳統人工做測量的方式相當的耗費時間和體力，使用手工測量較大尺寸的物件更加困難，隨著影像處理技術與視覺精密儀器的發展，自動化光學檢測已使用在多項展業。
本論文設計的相機檢測系統應用近年來發展漸趨成熟的影像處理技術，根據太陽能板物件其特性設計出一個影像校正流程，包含魚眼校正、輪廓偵測技術、線段擬合技術和透視變換技術等等。測量過程會拍攝樣品板和需測量的待測板，並在物件周圍加上四個圓點維持測量時的穩定度，兩張相片在經過影像校正流程後為同一視角，並以單位長度推算物件的實際尺寸，量測出樣品板和待測板之間的公差範圍。
同時，與專業的游標尺相比對量測值，反覆檢測實驗結果，並以量測系統分析 (MSA) 評估量測系統的穩定性，如此非接觸型的測量方式不易損傷物件之外，也達到自動化生產的目的。

The traditional manual measurement method is quite time-consuming and labor-intensive, and it is more difficult to measure larger-sized objects by hand. With the development of image processing technology and visual precision instruments, automated optical inspection has been used in many industries.
The progressively developed image processing technology in recent years is applied by the camera based detection system in this thesis. An image calibration process is designed according to the characteristics of the solar panels, including fisheye calibration, contour detection technology, line segment fitting technology and perspective transformation technology, etc. In the measurement process, the sample board and the test board will be photographed respectively. Additionally, four dots added around the object to maintain the stability of the measurement. After the image calibration, the two photos are in the same angle of view. We can calculate the actual size of the object by the pixel size and obtain the tolerance range between the sample board and the test board finally.
Meanwhile, the experimental results are compared to the value measured by the professional vernier and checked repeatedly. The stability of the measurement system is evaluated with the measurement system analysis (MSA). It is a non-contact measurement method, which is not easy to damage the object, and achieve the purpose of automated production as well.

[1]非接觸測量, URL:
https://zh.wikipedia.org/zhtw/%E9%9D%9E%E6%8E%A5%E8%A7%A6%E6%B5%8B%E9%87%8F
[2]O. Hecht and G. Dishon, "Automatic Optical Inspection (AOI)," Proc. of Electronic Compon, vol. 1, pp. 659-661, 1990.
[3]H. Liao, Z. Lim, Y. Hu, and H. Tseng, "Guidelines of Automated Optical Inspection (AOI) System Development," Proc. of 2018 IEEE 3rd International Conference on Signal and Image Processing, pp. 362-366, 2018.
[4]A. A. R. M. A. Ebayyeh and A. Mousavi, "A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry," IEEE Access, vol. 8, pp. 183192-183271, 2020.
[5]B. Li, "Application of Machine Vision Technology in Geometric Dimension Measurement of Small Parts," EURASIP Journal on Image and Video Processing, 2018.
[6]OpenCV, URL: https://opencv.org/
[7]A. J. Qussay, A. N. Waleed, A. T. Majid, I. Young, "Towards Automated Length Estimation of Free-swimming Fish Using Machine Vsion," Proc. 2017 14th International Multi-Conference on Systems, pp. 469-474, 2017.
[8]S. N. Yaryshev, I. A. Konyakhin, A. N. Timofeev, V. V. Korotaev, and T. S. Djamiykov, "Universal Optoelectronic Measuring Modules in Advanced Distributed Measuring Systems," Proc. 2020 XXIX International Scientific Conference Electronics, pp. 1-4, 2020.
[9]J. Hu, F. Song, C. Luo, and Q. Huang, "Non-metric Distortion Correction Method Based on Adaptive Corner Detection," Laser & Optoelectronics Progress, vol. 58, no. 12, Jun. 2021.
[10]Y. S. Huang and C. S. Liu, "An Optical Sensor for Measuring the Position and Slanting Direction of Flat Surfaces," Sensors, vol. 16, May. 2016.
[11]Logitech Webcam BRIO 4K HD, URL:
https://www.logitech.com/zh-tw/products/webcams/brio-4k-hdr-webcam.960-001105.html
[12]DJI POCKET 2 口袋雲台相機, URL: https://www.dji.com/tw/pocket-2
[13]TBEN-S2-4IOL 產品說明, URL: https://www.turck.de/en/product/0000003100008dc50003003a
[14]Compact Multiprotocol I/O Module for Ethernet 使用手冊, URL: http://www.turck.de/datasheet/_en/edb_6814024_gbr_en.pdf
[15]LE250D W/30 產品說明, URL: https://www.bannerengineering.com/in/en/products/part.94203.html
[16]SOLA AZB3 防震水平尺, URL:
http://www.targettools.com.tw/products.phpfunc=p_detail&p_id=143&pc_parent=47
[17]M8 螺絲調整角, URL: https://images.app.goo.gl/AsEze7gxvqnpvKL38
[18]雙高斯鏡頭設計,URL: https://en.wikipedia.org/wiki/Double-Gauss_lens
[19]D. Brown, "Close-Range Camera Calibration," Photogramm. Eng. , 2002.
[20]L. Ai, F. Yuan, Z. Ding, "Further Study on Radial Distortion Model for Photographic Objective," Acta Optical Sinica, vol. 28, no. 10, Oct. 2008
[21]S. Feng, "Real-time 3D Measurement Based on Structured Light Illumination Considering Camera Lens Distortion," Proc. of the International Society for Optical Engineering, Nov. 2014.
[22]魚眼相機成像過程, URL: https://codeantenna.com/a/GLIMKKRZbU
[23]K. Juho, "A Generic Camera Calibration Method for Fish-eye Lenses," Proc. of the 17th International Conference on Pattern Recognition, 2004.
[24]J. Canny, "A Computational Approach to Edge Detection," IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 679-698, 1986.
[25]W. Xiang, Y. Weibo, M. Yanhui, and L. Keping. "A New Improved Canny Image Edge Detection Algorithm," Imaging Science and Photochemistry, vol. 34, no. 1, pp. 116-121, 2016.
[26]G. Tan, Y. Ding, D. Fu and Y. Wang, "A Distortion Image Correction Method Based on Machine Vision," International Conference on Computer Information Science and Artificial Intelligence, vol. 1453, Oct. 2019.
[27]二維平面中的座標轉換, URL:
https://zh.wikipedia.org/zh-tw/%E6%97%8B%E8%BD%AC
[28]R. O. Duda, P. E. Hart, "Use of the Hough Transformation to Detect Lines and Curves in Pictures," Communications of the ACM, 1972.
[29]P. E. Hart, "How the Hough Transform was Invented," IEEE Signal Processing Magazine, vol. 26, no. 6, pp. 18-22, Nov. 2009.
[30]Z. Andrea, "Repeatability and Reproducibility Techniques for the Analysis of Measurement Systems," Measurement, vol. 86, pp. 125-132, May. 2016.
[31]J. N. Pan, "Evaluating the Gauge Repeatability and Reproducibility for Different Industries," Quality and Quantity, vol. 40, pp. 499-518, 2006.
[32]AIAG, Measurement System Analysis Manual, United States of America, 4th Ed, 2010.