在大量自動化的產品生產過程中，使用影像處理或機器視覺等技術，取代人工的檢測方式是必然的趨勢，現今數位信號處理器的優異性能，使得許多濾波器的設計與發展等技術可以應用於瑕疵偵測與辨識的領域中，其中以Gabor濾波器具有良好的特徵抽取能力與設計簡單等優點，引起廣泛的研究與發展。
在紋理瑕疵偵測上，通常所使用Gabor濾波往往受限於不同紋理的結構上差異而影響偵測的正確率，為了解決這問題，本論文希望使用GWN(Gabor Wavelet Network)作為設計Gabor 濾波器的依據，在論文中使用GWN重建紋理影像，具有不錯的效果，但實際應用於瑕疵偵測，由於計算成本的考量，需要採用單一神經元的GWN架構，使得GWN的訓練成效上受限於紋理的頻率與角度，所以在論文中加入了STFT(Short Time Fourier Transform)，用來估測紋理的頻率與角度，將其設定為GWN的初始值，讓GWN能有效的完成紋理特徵抽取，並利用訓練後的GWN設計Gabor濾波應用於瑕疵偵測上。
論文中使用許多不同結構與角度的紋理瑕疵影像作為驗證，實做的結果顯示加入STFT所估測的頻率與角度的GWN，除了能有效的重建出紋理影像，同時也提昇了瑕疵偵測的能力。

The recent rapid developments in DSP techniques, such as filter design and pattern recognition have made decent feature extraction possible. As a result, in many automatic-process based mass productions, combining machine vision and image processing have gradually replaced human in defect inspection.
Gabor filters are known to have excellent feature extraction capability if they are designed and implemented carefully. In texture defect detection, with all possible different texture structures and possible rotation angles, even they are so slightly altered from one another, the well known general Gabor method must be adjusted accordingly to prevent from severe sensibility suffering. For this reason, in our research, a new technique, by considering the Gabor filter as the only neuron of a single layer GWN(Gabor Wavelet Network) has been developed.
In order to reduce the training cost, STFT has been used in estimating the frequency and orientation characteristics of the texture roughly, and the results are used as the initial values of the GWN. The performance of this scheme has been evaluated on a variety of textures with various defects and orientations. The results have shown the effectiveness of this new technique.

[1] J.G. Daugman〝 Complete Discrete 2-D Gabor Transform by Neural Networks for Image analysis and Compression〞IEEE Trans. ASSP , 1988.
[2] Q. Zhang and A. Benveniste〝 Wavelet networks〞. IEEE Trans. on Neural Networks, 3 no. 6 pp. 889-898, 1992.
[3] Harold H. Szu and Brian A. Telfer〝 Neural network adaptive wavelets for signal representation and classification〞Optical Engineering September 1, 1992 -- Volume 31, Issue 9, pp. 1907-1916.
[4] Stéphane Mallat〝A theory for Multi Resolution Signal Decomposition : the Wavelet representation〞 IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 11, p. 674-693, 1989.
[5] Q. Zhang〝Using wavelet network in nonparametric estimation.〞 IEEE Trans. on Neural Networks, 8 no. 2 pp. 227-236,1997
[6] Q. Zhang.〝Regressor selection and wavelet network construction.〞IEEE Conference on Decision and Control (CDC), 1993.
[7] Gaviphat Lekutai .〝Adaptive Self-Tuning Neuro Wavelet. Network Controllers〞by Dissertation submitted to the Faculty of the. Virginia Polytechnic Institute and State University,1997
[8] V. Krueger and G. Sommer.〝Gabor Wavelet Networks for Object Representation〞Journal of the Optical Society of America(JOSA) 2002
[9] V. Krueger and R. Feris〝Wavelet Subspace Method for Real-Time Face Tracking.〞 Pattern Recognition, 23rd DAGM Symposium, 2001
[10] V. Krueger and G. Sommer. 〝Gabor Wavelet Networks for Efficient Head Pose Estimation.〞Image and Vision Computing ,2002
[11] Hao Lin Jiuqiang Han.〝Defect Detection Textiles Using Optimal Gabor Wavelet Filter〞IEEE Trans on Intelligent Control and Automation ,2006

[12] Mak, K.L. Peng, P. Lau, H.Y.K. 〝Optimal morphological filter design for fabric defect detection〞IEEE International Conference on Industrial Technology,2005
[13] J.G. Daugman.〝Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical Filters.〞 J. Opt, 1985.
[14] Martin T. Hagan, Howard B. Demuth, Mark H. Beale.〝Neural Network Design〞PWS Pub. Co.1996
[15] José.C.Principe, Neil.R.Euliano,W.CurtLefebvre.〝Neural and Adaptive Systems: Fundamentals through Simulations〞 John Wiley & Sons Ltd. 1999
[16] Husain. H. Khalid. M. Yusof. R.〝Nonlinear Function Approximation Using Radial Basis Function Neural Networks〞IEEE Conference on Research and Development,2002
[17] Stéphane Mallat〝A Wavelet Tour of Signal Processing〞2nd Edition. Academic Press, 1999
[18] Tai Sing Lee〝Image Representation Using 2D Gabor Wavelets〞IEEE Transactions on Pattern Analysis and Machine Intelligence,1996
[19] J.L. Sobral〝Optimised Filter for Texture Defect Detection〞IEEE Transactions on Pattern Analysis and Machine Intelligence,2005
[20] Martin T. Hagan, Mohammand B. Menhaj〝Tranning Feedforward Neural Networks with the Marquardt Algorithm〞IEEE Transactions on Neural Network ,Vol ,5,1994
[21] Jie Yao 〝Complete Gabor Transform for Signal Representation〞IEEE Transactions on Image Processing, Vol ,2,1993
[22] Francois Bergeaud ,Stéphane Mallat〝Matching Pursuit of Image〞IEEE Transactions on Image Processing,1995
[23] L.E. Scales〝Introduction to Nonlinear Optimization〞Macmillan Ltd.,1985
[24] Karlheinz Gröchenig〝Foundations of Time-Frequency Analysis〞
[25] Sharat Chikkerur,Alexander N.Cartwright,Venu Govindaraju〝Finger Print Enhancement Using STFT Analysis〞Pattern Recognition 2006
[26] S. Sitharama Iyengar,E.C. Cho, V.V. Phoha 〝Foundations of Wavelet Networks and Applications〞Chapman & Hall/CRC 2002
[27] Jain, A.K,Farrokhnia, F.〝Unsupervised texture segmentation using Gabor filters〞IEEE Transactions on Processing ,1990
[28] Teuner, A Pichler, O Hosticka, B.J.〝Unsupervised texture segmentation of images using tuned matched Gabor filters〞IEEE Transactions on Image Processing, 1995
[29] Bovik, A.C. Clark M. Geisler, W.S.〝Multichannel texture analysis using localized spatial filters〞IEEE Transactions on Pattern Analysis and Machine Intelligence
[30] Dunn, D. Higgins, W.E.〝Optimal Gabor filters for texture segmentation〞 IEEE Transactions on Image Processing,1995
[31] Leon Cohen〝Time Frequency Analysis: Theory and Applications〞Prentice Hall 1994
[32] Boualem Boashash〝Time Frequency Analysis〞Elsevier Science, 2003
[33] Shie Qian, Dapang Chen〝Joint Time-Frequency Analysis: Method and Application〞Prentice Hall,1996
[34] Ali H. Sayed〝Fundamentals of Adaptive Filtering〞Wiley-IEEE Press,2003
[35] Maria Petrou ,Pedro Garcia Sevilla〝Image Processing: Dealing With Texture〞Wiley 2006
[36] Rafael C. Gonzalez and Richard E. Woods〝Digital Image Processing (2nd Edition)〞Prentice Hall, 2002
[37] Alan V. Oppenheim, Ronald W. Schafer〝Discrete-Time Signal Processing〞Prentice Hall; 2nd edition (February 15, 1999)
[38] Alan V. Oppenheim, Alan S. Willsky〝Signals and Systems〞Prentice Hall; 2 edition (August 6, 1996)
[39] Athanasios Papoulis, S.Unnikrishna Pillai〝Probability, Random Variables and Stochastic Processes(Fourth Edition)〞McGraw-Hill Publishing Co,2002
[40] Jae S. Lim〝Two-Dimensional Signal and Image Processing〞,Prentice Hall PTR,1989
[41] Rao, A.R. Schunck, B.G. 〝Computing oriented texture fields〞, IEEE Conference on Computer Vision and Pattern Recognition, 1989.
[42] Jean-Pierre Antoine, Romain Murenzi, Pierre Vandergheynst, Syed Twareque Ali 〝Two-Dimensional Wavelets and their Relatives〞 Cambridge University Press,2004