分析織物組織圖方面，以往需要人工使用分析鏡來記錄組織號碼，而此方法將傷害視力且耗費時間，此外，若採用拆布的方式，則會破壞梭織物的組織結構。本論文使用電腦視覺系統與數位影像處理技術，可在無需拆布的情況下，直接對梭織物進行非破壞性分析。本論文提出了自動化梭織物組織辨識方法，以提高辨識系統的實用性及容錯能力。一開始先採用正面光源與背面光源拍攝梭織物影像，再利用中值濾波減少梭織物影像的雜訊，進行直方圖等化法以調高對比度，之後使用統計式門檻值分割出經紗區域，配合形態學中的斷開運算以斷開相連之區塊，並侵蝕小雜訊；利用水平投影及垂直投影以區隔經紗與緯紗；繪製組織圖以改善灰階共生矩陣的運算時間，接著選擇灰階共生矩陣中的相關性作為特徵值。然而在梭織物樣本方面，搜尋100筆樣本，利用FCM (Fuzzy c-means)分類，並規劃訓練樣本與測試樣本進行實驗，其結果顯示，辨識率皆可達100%，可明顯看出本論文採用的辨識系統可有效的應用在梭織物組織辨識工作上。

Drawing the weave chart need workers to use analyzer (count glass) to mark numbers. But this way is not only harmful to the eyes but also wastes time. It will damage the weave if we tear down the woven instead of the analyzer (count glass). The thesis uses a computer vision system and digital image processing to perform non-destructive analysis for woven fabrics. So in this situation, we don’t need to tear down the woven fabrics. We propose a new automatic recognition algorithm for woven fabric weave to increase reliability and fault-tolerance of this system. First, we adopt the lights forward and backward to take the woven fabrics images. Second, we use the median filter to reduce noise and the histogram equalization method to increase contrast. Then, we use the statistical threshold values to segment the warp region and the morphology to erode noise. The horizontal and vertical projection are used to discriminate warps and wefts. Finally, we draw weave charts to improve the computation time of gray co-occurrence matrix. We choose the correlation of gray co-occurrence matrix as features values. We have twenty training samples and eighty testing samples for experiment. A database with the Fuzzy c-means(FCM), is train by the training samples. The results show that the recognition rate is 100%. Obviously, this recognition system can be successfully applied to the weave analysis.

[1] E. J. Wood, “Carpet texture measurement using image analysis,” Textile Research Journal, Vol. 59, No. 1, pp. 1-12, 1989.
[2] Z. Xingye, G. Weidong and L. Jihong, “Automatic recognition of yarn count in fabric based on digital image processing,” 2008 Congress on Image and Signal Processing, Vol. 3, pp. 100-103, 2008.
[3] D. M. Tsai and C. Y. Hsieh, “Automated surface inspection for directional textures,” Image and Vision Computing, Vol. 18, No. 1, pp. 49-62, 1999.
[4] C. H. Chan and G. K. H. Pang, “Fabric defect detection by fourier analysis,” IEEE Trans. on Industry Applications, Vol. 36, No. 5, pp. 1267-1276, 2000.
[5] Y. B. Salem and S. Nasri, “Texture classification of woven fabric based on a GLCM method and using multiclass support vector machine,” The 6th International Multi-Conference on Systems, Signals and Devices, pp. 1-8, 2009.
[6] X. Bugao, “Identification fabric structures with fast fourier transform techniques,” Textile Research Journal, Vol. 66, No. 8, pp. 496-506, 1996.
[7] S. A. H. Ravandi and K. Toriumi, “Fourier transform analysis of plain weave fabric appearance,” Textile Research Journal, Vol. 65, No. 11, pp. 676-683, 1995.
[8] T. L. Su, L. S. Chang and F. C. Kung, “Intelligent computerized fabric texture recognition system by using Grey-based neural fuzzy clustering,” International Conference on Wavelet Analysis and Pattern Recognition, pp. 185-189, 2009.
[9] 柳善聰，“影像處理於梭織物分析之研究”，國立台灣科技大學高分子工程技術研究所，1997。
[10] 何承恩，“應用倒傳遞類神經網路進行電腦視覺在梭織布的織物組織辨識”，國立台灣科技大學高分子工程技術研究所，2008。
[11] C. C. Chang, J. Y. Hsiao and C. P. Hsieh, “An adaptive median filter for image denoising,” Second International Symposium on Intelligent Information Technology Application, Vol. 2, pp. 346-350, 2008.
[12] P. S. Windyga, “Fast impulsive noise removal,” Trans. on Image Processing, Vol. 10, No. 1, pp. 173-179, 2001.
[13] H. Ibrahim and N. S. P. Kong, “Brightness preserving dynamic histogram equalization for image contrast enhancement,” IEEE Trans. on Consumer Electronics, Vol. 53, No. 4, pp. 1752-1758, 2007.
[14] N. Otsu, “A threshold selection method from gray - level histograms,” IEEE Trans. on System, Man and Cybernetics, Vol. SMC-9, No. 1, pp. 62-66, 1979.
[15] I. S. Tsai, C. H. Lin and J. J. Lin, “Applying an artificial neural network to pattern recognition in fabric defects,” Textile Research Journal, Vol. 65, No. 3, pp. 123-130, 1995.
[16] S. W. Chen, C. F. Chen, M. S. Chen, S. Cheng, C. Y. Fang and K. E. Chang, “Neural-fuzzy classification for segmentation of remotely sensed images,” IEEE Trans. on Signal Processing, Vol. 45, No. 11, pp. 2639-2654, 1997.
[17] Z. X. Guang, “The research of defect recognition for radiographic weld image based on fuzzy neural network,” IEEE Trans. on Intelligent Control and Automation, Vol. 3, pp. 2661-2665, 2004.
[18] 余明興、吳明哲、黃世陽、黃豐隆、紀旺松、潘能煌編著，“Borland C++ Builder 6程式設計經典”，文魁資訊股份有限公司，2007。
[19] 郭東瀛編譯，“紡織概論”，財團法人徐氏文教基金會，2003。
[20] 鐘國亮編著，“影像處理與電腦視覺第三版”，東華書局，2006。
[21] 繆紹綱編譯，“數位影像處理”，台灣培生教育出版股份有限公司，2009。
[22] S. Kim, M. H. Lee and K. B. Woo, “Wavelet analysis to fabric defects detection in weaving process,” Proceedings of The IEEE International Symposium on Industrial Electronics, Vol. 3, pp. 1406-1409, 1999.
[23] Y. Du, C. I. Chang and C. Y. Thouin, “Unsupervised approach to color video thresholding,” Optical Engineering, Vol. 43, No. 2, pp. 282-289, 2004.
[24] 林孝忠，“群集中心具有體積之模糊分群績效比較”，國立成功大學資訊管理研究所，2004。
[25] J. C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well-seperated clusters,” Journal of Cybernetics, Vol. 3, No. 3, pp. 32-57, 1973.
[26] J. C. Bezdek, “Pattern recognition with fuzzy objective function algorithm,” Pattern Recognition, Vol. 37, No. 1, pp. 33-45, 1981.
[27] R. Babuska, P. J. Veen and U. Kaymak, “Improved covariance estimation for Gustafson-Kessel clustering,” IEEE International Conference on Fuzzy Systems, Vol. 2, pp. 1081-1085, 2002.
[28] L. X. Wang, “A course in fuzzy systems and control,” Prentice Hall PTR, Inc. Upper Saddle River, NJ, USA, pp. 424, 1997.