本文應用數位影像辨識分類技術檢測LCD平面顯示器之導光板網點微結構，以提高顯示器之輝度與均勻度。首先將LCD導光板之微結構二值化影像以不變矩的演算法計算每一種網點特徵之不變矩當作描述因子，之後由利用兩種分類器：貝氏分類器和類神經網路分類器，將每一網點特徵的描述因子作分類。演算參數為影像旋轉角度以及特徵值個數。藉由不變矩演算，可找出與影像檢測旋轉角度無關的網點單一描述因子，以達到智慧型檢測目的。

Inspection of LCD light-guide plate using digital image processing is proposed. Binary dot-pattern images from SEM observation are obtained by image segmentation. Pattern recognition for the images is then performed using moment invariants, Bayes classifier, and Neural network. The rotation independent classification for the recognition using only one descript shape factor are also proposed to reduce storage space. It is found the method has been applied successfully in inspection of different defects on the plate subject to any rotation angles and image scales.

中文摘要--------------------------------------------------I
英文摘要--------------------------------------------------II
目錄--------------------------------------------------------III
圖目錄-----------------------------------------------------VI
表目錄-----------------------------------------------------VII

第一章 緒論-----------------------------------------------1
1.1前言------------------------------------------------1
1.2研究動機與目的---------------------------------2
1.3文獻回顧------------------------------------------3
1.4論文架構------------------------------------------3
第二章 數位影像處理-----------------------------------4
2.1數位影像處理簡介------------------------------4
2.2數位影像處理流程------------------------------4
2.3數位影像之定義---------------------------------8
2.4影像二值化---------------------------------------8
2.5特徵擷取-----------------------------------------10
2.6分類方法-----------------------------------------13
2.6.1貝氏分類器------------------------------13
2.6.2類神經網路分類器---------------------16
2.7運算軟體-----------------------------------------19
第三章 影像樣本擷取與參數設定-------------------21
3.1影像樣本-----------------------------------------21
3.2瑕疵樣本-----------------------------------------21
3.3特徵值選取演算--------------------------------22
3.4影像尺度與角度設定--------------------------23
第四章 結果與討論-------------------------------------24
4.1貝氏分類-----------------------------------------24
4.1.1不同網點類型的分類------------------24
4.1.2瑕疵網點的分類------------------------25
4.2類神經網路分類--------------------------------27
4.2.1不同網點型態的分類------------------28
4.2.2瑕疵網點的分類------------------------28
4.3分類方法比較-----------------------------------29
4.4加權不變矩--------------------------------------29
4.4.1貝氏分類---------------------------------30
4.4.2類神經網路分類------------------------30
4.5樣本取樣的獨立性-----------------------------31
第五張 結論----------------------------------------------33
參考文獻--------------------------------------------------35

[1] Fukushima K., “Neocognitron of A New Version: Handwritten Digit Recognition” Artificial Neural Networks-Icann 2001, Proceedings Lecture Notes In Computer Science, Vol. 2130, pp. 987-992 (2001).
[2] Haddadnia J., Faez K., and Ahmadi M., “An Efficient Human Face Recognition System Using Pseudo Zernike Moment Invariant and Radial Basis Function Neural Network,” International Journal of Pattern Recognition And Artificial Intelligence, Vol. 17, No. 1, pp. 41-62 (2003).
[3] Hu M.K., “Visual Pattern Recognition by Moment Invariants,” IRE Trans. Info. Theory, Vol. 8, pp. 179-187 (1962).
[4] Salah A.A, Alpaydin E., and Akarun L., “A Selective Attention-Based Method for Visual Pattern Recognition with Application to Handwritten Digit Recognition and Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 3, pp. 420-425 (2002).
[5] Shioyama T., Wu H.Y., Nakamura N., and Kitawaki S., “Measurement of The Length of Pedestrian Crossings and Detection of Traffic Lights From Image Data,” Measurement Science & Technology, Vol. 13, No. 9, pp. 1450-1457 ( 2002).
[6] Yang G.Z., Dempere-Marco L., Hu X.P., and Rowe A., “Visual Search: Psychophysical Models and Practical Applications,” Image and Vision Computing, Vol. 20, No. 4, pp. 273-287 (2002).
[7] Zhang Y.N., Leung, Y., and Zhao R.C., “A New Method for Image Recognition,” Chinese Journal of Electronics, Vol. 11, No. 3, pp. 318-321 (2002).
[8] Ivar Balslev, Kasper Dùring, Rene Dencker Eriksen, “Weighted central moments in pattern recognition” Pattern Recognition Letters, 21 pp. 381-384(2000)
[9] Gonzale R.C., Tou J.T., “Pattern Recognition Principles,” Addison-Wesley
Publishing Company(1974).
[10] Gonzale R.C., Paul Wintz, “Digital Image Processing, second edition,”
Addison-Wesley Publishing Company(1987).
[11] Andrew W., “Statistical Pattern Recognition, second edition,” John Wiley & Sons, LTD(2002)
[12] 繆紹綱 編著,“數位影像處理-活用Matlab,”全華科技圖書股份有
限公司(1999)
[13] Matlab Image Processing Toolbox User’s Guide