對於平面顯示器面板產業而言，在各種元件中，諸如：玻璃基板(glass substrate)、偏光板(polarizer)、背光板模組(backlight module)及彩色濾光片(color filter)等皆扮演著重要的角色。而為了能在色彩上有高品質的顯示能力，彩色濾光片更是不可或缺的重要元件。
然而在彩色濾光片在製造流程中，常會因為外在環境及機台本身的因素發生瑕疵。傳統上，以人工來進行彩色濾光片的瑕疵檢測，常會有疲勞導致漏檢、檢測效率低，造成彩色濾光片良率下降以及生產成本增加。為了改善這些問題，本研究發展出一套彩色濾光片自動化檢測系統來取代傳統的人工檢測方式。
本研究針對彩色濾光片的毛屑(fiber)、粉塵(particle)、膠化(gel)及光阻覆蓋(resist coating)四種瑕疵，使用影像處理技術把瑕疵影像強化後，利用影像分割將瑕疵分割出來，並找出面積(area)、長寬比(aspect ratio)、矩形比(squareness ratio)及毀損率(damage rate)四個有效的特徵值。
最後，選用倒傳遞類神經網路(back-propagation neural network)及模糊類神經網路(fuzzy neural network)為分類器，進行瑕疵辨識分類。在160個測試樣本中，倒傳遞類神經網路辨識率為92.5%，模糊類神經網路辨識率為96.25%，由實驗結果證實本論文所提出之方法可以成功的應用於彩色濾光片瑕疵檢測系統，以降低人工檢測的誤差，提高生產良率。

Glass substrate, polarizer, backlight module and color filter are important components of the liquid crystal display (LCD) flat panel industry. Color filter is important in providing high-quality color ability. However, the manufacturing process for color filters often produces defects from the external environment and mechanical factors. Traditionally, artificial inspection is applied to detect color filter defects with low efficiency, resulting in decreasing the color filter production yield and increasing the production cost. To resolve these problems, this study develops a color filter automatic inspecting system as an alternative for artificial detection.
In this study, we selected four defects of different color filters including fiber, particle, gel, and resist coating. Image processing, image enhancement, and image segmentation were used to separate defects to obtain area, aspect ratio, squareness ratio, and damage rate.
Finally, the back-propagation neural network and fuzzy neural network were adopted to classify these defects. The recognition rate of back-propagation neural network was 92.5% for 160 test samples, with a 96.25% recognition rate of fuzzy neural network. The experimental results indicated that the proposed method can be successfully applied to inspect color filter defects. In addition, the error of manual detection could be reduced effectively.

1.B. C. Jiang and S. J. Jiang, “Machine VisionBased
Inspection of Oil Seals,” Journal of Manufacturing
Systems, Vol.17, No.3, pp. 159-166, 1998.

2.P. L. Hostis, F. Byers, F. Podio, and X. Tang,
“Microscopic Image Analysis of Defect Areas in
Optical Disks,” Proceedings of SPIE - The International
Society for Optical Engineering, Vol. 3806, pp.106-112,
1999.

3.S. Y. Chul, C. D. Hyun, and P. K. Houm, “Multiscale
Detection Defect in Thin Film Transistor Liquid Crystal
Display Panel,” Japanese Journal of Applied Physics,
Vol. 43, No. 8, pp. 5465–5468, 2004.

4.B. C. Jiang, C. C. Wang, and H. C. Liu, “Liquid Crystal
Display Surface Uniformity Defect Inspection Using
Analysis of Variable Exponentially Weighted Moving
Average Techniques,” International Journal of
Production Research, Vol. 43, pp. 67-80, 2005.

5.D. M. Tsai, P. C. Lin, and C. J. Lu, “An Independent
Component Analysis Based Filter Design for Defect
Detection in Low-Contrast Surface Images,” Pattern
Recognition, Vol. 39, pp. 1679-1694, 2006.

6.K. B. Lee, M. S. Ko, J. J. Lee, T. M. Koo, and K. H.
Park, “Defect Detection Method TFT-LCD Panel Based on
Saliency Map Model,” IEEE International Conference,
Vol. 1, pp. 223-226, 2004.

7.J. Y. Lee and S. I. Yoo, “Automatic Detection of Region-
Mura Defect in TFT-LCD,” IEICE Transactions on
Information and Systems, Vol. E87-D, No. 10, pp. 2371-
2378, 2004.

8.K. Nakashima, “Hybrid Inspection System for LCD Color
Filter Panels,” IEEE Instrumentation and Measurement
Technology Conference, Vol. 2, pp. 689-692, 1994.

9.B. C. Jiang, S. L. Tsai, and C. C. Wang, “Machine
Vision-Based Gray Relational Theory Applied to IC
Marking Inspection,” IEEE Transactions on Semiconductor
Manufacturing, Vol. 15, No. 4, pp. 531-539, 2002.

10.C. L. Lee and S. Y. Chen, “Classification of Leaf
Images,” International Journal of Imaging Systems and
Technology, Vol. 16, No. 1, pp. 15-23, 2006.

11.B. Gunsel and A. M. Tekalp, “Shape Similarity Matching
for Query by Example,” Pattern Recognition, Vol. 31,
No. 7, pp. 931-944, 1998.

12.C. T. Su, T. Yang, and C. M. Ke, “A Neural Network
Approach for Emiconductor Wafer Post-Sawing
Inspection”, IEEE Transactions on Semiconductor
Manufacturing, Vol. 15, No. 2, pp. 260-266, 2002.

13.Y. Yao, X. Li, and Z. Yuan, “Tool Wear Detection with
Fuzzy Classification and Wavelet Fuzzy Neural
Network,” International Journal of Machine Tools and
Manufacture, Vol. 39, pp. 1525-1538, 1999.

14.C. L. Chang, H. H. Chang, and C. P. Hsu, “An
Intelligent Defect Inspection Technique for Color
Filter,” IEEE International Conference on
Mechatronics, pp. 933-936, 2005

15.顧鴻壽等編著，“光電平面面板顯示器基本概論”，高立圖書有
限公司，2004.

16.莊東漢等編著，“平面顯示器概論”，高立圖書有限公司，
2008.

17.繆紹綱，“數位影像處理活用Matlab”，全華科技圖書股份有限
公司，1999.

18.鍾國亮編著，“影像處理與電腦視覺”，東華書局，2006.

19.N. Otsu, “A Threshold Selection Method from Gray Level
Histogram,” IEEE Transactions on Systems, Man and
Cybernetics, SMC-8, pp. 62-66, 1978.

20.I. E. Sobel, “Camera Models and Machine Perception,”
Ph.D. thesis, Stanford University, pp. 99, 1970.

21.Gonzalez Woods, “Digtial Image Process,” Prentice
Hall, New York, 2002.

22.J. Canny, “A Computational Approach to Edge
Detection,” IEEE Transactions on Pattern Analysis and
Machine Intelligence, Vol. PAMI-8, No. 6, pp. 679-714,
1986.

23.F. Chang, C. J. Chen, and C. J. Lu, “A Linear-Time
Component Labeling Algorithm Using Contour Tracing
Technique,” Computer Vision and Image Understanding,
Vol. 93, No. 2, pp. 206-220, 2004.

24.葉怡成編著，“類神經網路模式應用與實作”，儒林圖書，
2006.

25.李允中等編著，“模糊理論及其應用”，全華圖書，2008.

26.I. C. Yeh, “Modeling Chaotic Two-Dimensional Mapping
with Fuzzy Neuron Networks,” Fuzzy Sets and Systems,
pp. 421-427, 1999.