本研究提出一種以積層製造(Additive Manufacturing, AM)的熔融沉積成型(Fused Deposition Modeling, FDM)技術為基礎，塑料為材料的新型佈料技術的影像監控成型品質方法。

該熔融沉積成型技術主要問題在於成型過程中尚未有良好的機制檢測成型過程中產生的缺陷，以至於成型品質難以掌控。因此，本研究提出一套以影像為基礎的檢測機制，在熔融沉積成型的過程中，透過影像系統監控熔融沉積成型機台的噴嘴，以及被擠出熔融狀的材料過程中之各項影像資訊，擠出塑料的高度與寬度可以經由處理過後的影像計算得到。

在擠出料頂面與側面灰階值差異度至少百分之四的情況下，本研究由實驗結果訂定出品質標準：間隔特定幀數影像之寬度的變化百分比在二十以內，或是高度的變化百分比在四十以內；同時，長期高度與寬度的變化百分比亦能維持在上述相同變化百分比以內，便能夠稱之為正常佈料的品質。系統可以從高度與寬度上的大幅變化得知是否有異常的狀況，並達成工件品質管控的目的。

This study proposes an image based inspection and monitoring system for a new type of Fused Deposition Modeling (FDM) technology using plastic material.

During the manufacturing process, the quality is difficult to control due to insufficient inspection methods to detect defects in the FDM processes. The quality of FDM products are difficult to be controlled. Therefore, this study proposes image-based detection mechanisms. During the process of FDM, the images of the nozzle is captured by the monitoring system. The height and the width information can be acquired by the images.

When the gray-scale value difference of adjacent surfaces of extruded material is at least four percent, a criterion can be established according to experimental result in this study. The extruded material meets the production standards when it satisfies the following conditions: the width and height variations of specific frame series should be under 20 percent and 40 percent respectively in both short and long term frame intervals, defined in this study. Monitoring systems can detect whether there are any abnormal circumstances by determining variations in both width and height from images.

參考文獻
[1]B. Zhang, W. Huang, J. Li, C. Zhao, S. Fan, J. Wu, C. Liu (2014). "Principles, developments and applications of computer vision for external quality inspection of fruits and vegetables: A review." Food Research International, 62: 326–343.
[2]H.Y.Y. Ngan, G.K.H. Pang, N.H.C. Yung (2011). "Automated fabric defect detection – a review." Image and Vision Computing, 29: 442–458.
[3]https://en.wikipedia.org/wiki/3D_printing
[4]S.S. Crump, J.W. Comb, W.R. Priedeman Jr., R.L. Zinniel (1996). Process of Support Removal For Fused Deposition Modeling, US Patent No.5503785 A
[5]P.M. Pandey, N. V. Reddy., S.G. Dhande (2003). "Real time adaptive slicing for fused deposition modelling." International Journal of Machine Tools & Manufacture, 43(1): 61-71.
[6]M.K. Agarwala, V.R. Jamalabad, N.A. Langrana, A.Safari, P.J. Whalen, S.C. Danforth (1996). "Structural quality of parts processed by fused deposition." Rapid Prototyping, 2(4): 4-19.
[7]A. Boschetto, L. Bottini, F. Veniali (2016). "Finishing of Fused Deposition Modeling parts by CNC machining," Robotics and Computer-Integrated Manufacturing, 41:92-101.
[8]S. Wu, S. Rangarajan, C. Dai, N.A. Langrana, A. Safari, and S.C. Danforth (2003). "Warm Isostatic Pressing (WIP'ing) of GS44 Si_3 N_4 FDC Parts for Defect Removal," Journal of Materials & Design, 24:681–686.
[9]S.M. Bhandarkar, X. Luo, R. Daniels, E.W. Tollner (2006). "A novel feature-based tracking approach to the detection, localization, and 3-D reconstruction of internal defects in hardwood logs using computer tomography." Pattern Anal. Appl. 9(2–3): 155-17
[10]T. Fang, M.A. Jafari, S.C. Danforth, A. Safari (2003). "Signature analysis and defect detection in layered manufacturing of ceramic sensors and actuators." Machine Vision and Applications, 15(2): 63-75.
[11]R.C. Luo, J.H. Tzou., Y.C. Chang (2001). "Desktop rapid prototyping system with supervisory control and monitoring through Internet." IEEE/ASME Transactions on Mechatronics, 6(4): 399-409.
[12]M. Asselin, E. Toyserkani, M. Iravani-Tabrizipour, A. Khajepour (2005). "Development of Trinocular CCD-Based Optical Detector for Real-Time Monitoring of Laser Cladding." Proceedings of the IEEE International Conference on Mechatronics and Automation, 3: 1190 - 1196.
[13]R.C. Gonzalez, R.E. Woods (2008). Digital Image Processing, 3rd Edition. New York : Prentice Hall.
[14]www.dandiggins.co.uk
[15]N. Otsu (1979). "A Threshold Selection Method from Gray-Level Histograms." IEEE Transactions on Systems, Man, and Cybernetics, 9(1): 62-66.
[16]S. Gauglitz, T. Höllerer, M. Turk (2011). "Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking." International Journal of Computer Vision, 94(3): 335-360.
[17]http://www.sherline.com/8540pg.htm
[18]http://goo.gl/Cjw93V
[19]http://www.ptgrey.com/blackfly-14-mp-color-gige-vision-poe-sony-imx104-camera
[20]http://www.tokina.co.jp/en/security/machine-vision-lenses/tc1614-3mpg-1.html