背光源模組藉由擴散板使光源能均勻分佈於LCD面板。於製造過程中，若無法有效檢測含有瑕疵的擴散板，則無法發揮使光源均勻的功能。本研究針對擴散板設計一套自動化光學檢測系統，利用瑕疵的光學特性與影像處理技術，檢測微觀瑕疵(黑點)與巨觀瑕疵(缺料、水波紋與刮痕)。

本研究提出的自動光學檢測系統可有效檢測上述四種瑕疵，由實驗結果顯示，擴散板瑕疵的平均檢測率約為91%，不易發生誤判。在檢測系統的即時性上，系統檢測32吋擴散板(影像大小約為7000×10000 pixels)，僅需1.6秒，可有效應用於即時檢測系統。

With the diffuser plate the backlight module could make light source distributed uniformly. If the diffuser plates with the defects on the surface could not be inspected during the manufactures, it will result in poor uniformity in light source distribution. In this essay, we construct an automatic optical inspection (AOI) system for diffuser plates, using defects of optics and digital image processing techniques to detect the defects of diffuser plates which include micro defect (e.g., black spots) and macro defect (e.g., queliao, water ripples and scratches).

The AOI system method we proposed in this essay could effectively detect these 4 types of defects mentioned above. From the experimental results the average detection rate is approximately at 91%, which is very precise for the inspection. For the real-time system, it only took 1.6 seconds to measure a 32-inch diffuser plate(the image size is about 7000×10000 pixels). This method could be effectively applied to real-time inspection system.

[1]T. S. Newman and A. K. Jain, "A Survey of Automated Visual Inspection," Computer Vision and Image Understanding, vol. 61, pp. 231-262 (1995).
[2]M. Bradshaw, "The application of machine vision to the automated inspection of knitted fabrics," Mechatronics, vol. 5, pp. 233-243 (1995).
[3]C. Sanby, L. Norton-Wayne, and R. Harwood, "The automated inspection of lace using machine vision," Mechatronics, vol. 5, pp. 215-231 (1995).
[4]M. Moganti, F. Ercal, C. H. Dagli, and S. Tsunekawa, "Automatic PCB inspection algorithms: A survey," Computer Vision and Image Understanding, vol. 63, pp. 287-313 (1996).
[5]蘇榮智，「自動化光學檢測之研究」，碩士論文，台灣科技大學，台北(2005)
[6]林義堂，「線掃瞄機器視覺檢測系統之開發與探討」，碩士論文，中華大學，新竹(2003)。
[7]C. S. Lin, W. Z. Wu, Y. L. Lay, and M. W. Chang, "A digital image-based measurement system for a LCD backlight module," Optics and Laser Technology, vol. 33, pp. 499-505 (2001).
[8]M. Kurumisawa, T. Suzuki, and H. Shimozono, "Human sensitivity of brightness uniformity for LCDs," in IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Japan (1997).
[9]C. S. Lin, K. H. Huang, Y. L. Lay, K. C. Wu, Y. C. Wu, and J. M. Lin, "An improved pattern match method with flexible mask for automatic inspection in the LCD manufacturing process," Expert Systems with Applications, vol. 36, pp. 3234-3239 (2009).
[10]S. M. Chao and D. M. Tsai , "An anisotropic diffusion-based defect detection for low-contrast glass substrates," Image and Vision Computing, vol. 26, pp. 187-200 (2008).
[11]H. I. Son, "Automatic inspection method for macro defects in TFT-LCD color filter fabrication process," IEICE Electronics Express, vol. 6, pp. 516-521 (2009).
[12]吳木杏，「彩色濾光片表面瑕疵檢測分析」，碩士論文，國立台灣大學，台北(2000)。
[13]K. Nakashima, "Hybrid inspection system for LCD color filter panels," IEEE Instrumentation and Measurement Technology Conference, Hamamatsu, Japan, pp. 689-692(1994).
[14]陳昱君，「應用機器視覺於彩色濾光片面板之表面瑕疵檢測」，碩士論文，元智大學，桃園(2008)。
[15]D. M. Tsai and C. Y. Hung, "Automatic defect inspection of patterned thin film transistor-liquid crystal display (TFT-LCD) panels using one-dimensional Fourier reconstruction and wavelet decomposition," International Journal of Production Research, vol. 43, pp. 4589-4607 (2005).
[16]D. M. Tsai, S. T. Chuang, and Y. H. Tseng, "One-dimensional-based automatic defect inspection of multiple patterned TFT-LCD panels using Fourier image reconstruction," International Journal of Production Research, vol. 45, pp. 1297-1321 (2007).
[17]H. D. Nam and S. U. Nam, "Frequency domain pre-processing for automatic defect inspection of TFT-LCD panels," Transactions of the Korean Institute of Electrical Engineers, vol. 57, pp. 1295-1297 (2008).
[18]曾彥馨，「應用機器視覺於TFT面板之表面瑕疵檢測與分類」，碩士論文，元智大學，桃園(2003)。
[19]C. J. Lu and D. M. Tsai, "Automatic defect inspection for LCDs using singular value decomposition," International Journal of Advanced Manufacturing Technology, vol. 25, pp. 53-61 (2005).
[20]Y. H. Liu, S. H. Lin, Y. L. Hsueh, and M. J. Lee, "Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble," Expert Systems with Applications, vol. 36, pp. 1978-1998 (2009).
[21]C. J. Lu and D. M. Tsai, "Defect inspection of patterned thin film transistor-liquid crystal display panels using a fast sub-image-based singular value decomposition," International Journal of Production Research, vol. 42, pp. 4331-4351 (2004).
[22]石士欣，「以Haar小波轉換與空間濾波於TFT-LCD面板之瑕疵檢測」，碩士論文，台灣科技大學，台北(2009)。
[23]J. S. Ryu, J. H. Oh, J. G. Kim, T. M. Koo, and K. H. Park, "TFT-LCD panel blob-mura inspection using the correlation of wavelet coefficients," IEEE Region 10 Annual International Conference, Proceedings of TENCON, Chiang Mai, Thailand, pp. 219-222(2004).
[24]陳學宇，「應用機器視覺於LCD擴散片之檢測」，碩士論文，中華大學，新竹(2005)。
[25]莊東漢、黃漢邦、謝國煌、蔡豐羽、陳炳宏、鄭晃忠，平面顯示器概論，高立圖書有限公司，台北(2008)。
[26]R. C. Gonzalez and R. E. Woods, Digital Image Processing, Third Edition Prentice-Hall, New York (2008).
[27]R. Jain, R. Kasturi and B. G. Schunck, Machine Vision, McGRAW-HILL International editions (1995).
[28]鐘國亮，影像處理與電腦視覺，東華書局，台北(2006)。
[29]田民波，TFT液晶顯示原理與技術，五南圖書出版公司，台北(2008)。
[30]J. M. Zhou and Y. Yang, "Detection of surface defects on steel balls using image processing technology," in Proceedings of SPIE - The International Society for Optical Engineering, Anhui (2008).
[31]張振堶、金美敬，「自動光學檢測(AOI)市場及技術發展趨勢調查」，產業技術知識服務計畫產業報告(ITRIEK-0453-S103)，新竹，台灣(2002)。