本論文提出一個新穎的刺繡織物的自動化影像分析系統，此系統能對刺繡布影像進行自動化分色及紋理分析。首先以掃描器取得刺繡織物在紅綠藍(RGB)格式的數位影像，再將RGB格式的數位影像轉換以L表示亮度分量、A表示綠色和紫紅色分量與B表示藍色和黃色分量的CIELAB色彩空間。對CIELAB色彩空間中亮度層做抑制雜訊的影像處理實驗，如:均值濾波、中值濾波、一次與兩次小波轉換法處理，並藉由峰値信號雜訊比(Peak Signal to Noise Ratio)指標來比較原始影像和經抑制雜訊處理後的影像品質。結果顯示一次小波轉換法在抑制雜訊處理中除可提高數位影像的平滑化及具較少的影像處理失真效果，所以使用一次小波轉換進行刺繡織物影像的濾波處理
。接著，再以模糊C平均(Fuzzy C-means)聚類演算法於刺繡布的影像上進行區域分裂的分色。刺繡織物的主紋理分析是使用熵和Hough變換方法獲得到主紋理特徵，而紗線紋理分析，以賈柏濾波器處理產生紗線紋理的特徵，使用一組具有不同頻率和方向的賈伯濾波器由刺繡織物濾波處理後的影像中提取出紗線紋理訊息，賈伯濾波器中使用的方向參數是由紋理方向計算演算法中得到，再以3個尺度和3個方向的賈柏濾波器組分別對待測的刺繡織物影像進行迴旋積運算提取灰階的紗線紋理訊息。紗線紋理特徵的顯現是透過自動化二值化的處理，通過Otsu演算法，它可以計算出最佳化的門檻值，並且執行二值化處理。最後經過細線化方法處理、去除孤立點而擷取紗線紋理特徵結果。由實驗結果，可看出本論文的方法適用於刺繡布的分色和紋理特徵分析。

This study created an automated color and texture image analyzing system for embroidery fabrics. First, a scanner was used to obtain the digitized color image of the embroidery fabric in RGB mode. Then the image was converted to a digitized color image in CIELAB mode. In this stage, noise reduction methods such as mean filtering, median filtering, one-time and two-time wavelet transformation processing on lightness layer of CIELAB color space were conducted. The Peak Signal to Noise Ratio (PSNR) method compared the digitized image quality status between the original to the de-noising image. In the results, one-time wavelet transformation de-noising processing improved the digitized image smoothing with low processing loss. The pre-processed embroidery fabric images were developed with the one-time wavelet transformation. The Fuzzy C-means (FCM) clustering method was employed to run color separation and regional separation. The main texture analysis of embroidery fabrics is based in Entropy and Hough transform approach to main texture feature is obtained. The yarn texture analysis was based on Gabor filters approach to obtain yarn texture features. Pre-processed embroidery fabric images used a set of Gabor filters with different frequencies and orientations for extracted yarn texture information. The orientation parameter for Gabor filters was one algorithm of texture recognition on directional fields. Using three scales and three directional convolution operations, the Gabor filters detected gray level yarn texture information of the embroidery fabric. The appearance of the yarn texture feature was found with automated threshold processing. It calculated the optimal threshold through the Otsu algorithm and executed binary processing. Finally, the result was
 
achieved by thinning method processing, which removed the outlier to obtain yarn texture feature. The results of this study confirmed that the method could be applied to embroidery color and texture analysis.

[1] J. Liu, Y.H. Yang, “Multiresolution Color Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vo1. 16, pp. 689-700, 1994.
[2] V.S. Rathore, M.S. Kumar, A. Verma, “Colour Based Image Segmentation Using L*A*B* Colour Space Based on Genetic Algorithm,” International Journal of Emerging Technology and Advanced Engineering, Vol. 2, pp. 156-162, 2012.
[3] C.F.J. Kuo, C.T.M. Hsu, C.Y. Shin, “Automatic Pattern Recognition and Color Separation of Embroidery Fabrics,” Textile Research Journal, Vol. 81, No. 11, pp. 1145-1157, 2011.
[4] J. Tang, “A Color Image Segmentation Algorithm Based on Region Growing,” IEEE International Conference on Computer Engineering and Technology, Vol. 6, pp. 634-637, 2010.
[5] K.C. Liu and C.H. Chou, “Perceptual Contrast Estimation for Color Edge Detection,” IEEE International Workshop on Systems, Signals and Image Processing, 2007 and 6th EURASIP Conference focused on Speech and Image Processing, pp. 86-89, 2007.
[6] J. Fan, W. G. Aref, M. S. Hacid, A. K. Elmagarmid, “An Improved Automatic Isotropic Color Edge Detection Technique,” Pattern Recognition Letters, Vol. 22, pp. 1419-1429, 2001.
[7] X. Wang, N. D. Georganas, “GLCM Texture Based Fractal Method for Evaluating Fabric Surface Roughness,” IEEE Canadian Conference on Electrical and Computer Engineering, DOI: 10.1109/ CCECE.2009.5090100 pp. 104-107, 2009.
 
[8] H. Zuo, Y. Wang, X. Yang, X. Wang, “Fabric Defect Detection Based on Texture Enhancement,” IEEE International Congress on Image and Signal Processing, DOI: 10.1109/CISP.2012.6469799, pp. 876-880, 2012.
[9] R.W. Ehrich, J.P. Foith, “A View of Texture Topology and Texture Description,” Computer Graphics and Image Processing, Vol. 8, No. 2, pp. 174-202, 1978.
[10] 鄭雪妮，電腦視覺系統在印刷產業之應用，印刷科技，第二十三卷，第一期，2007。
[11] C.F.J. Kuo, C.Y. Shih, J.Y. Lee, “Automatic Recognition of Fabric Weave Patterns by Fuzzy C-Means Clustering Method,” Textile Research Journal, Vol. 74, No 2, pp. 107-111, 2004.
[12] C.F.J. Kuo, C.Y. Kao, C.H. Chiu, “Integrating a Genetic Algorithm and a Self-organizing Map Network for an Automatically Separating Color Printed Fabric System,” Textile Research Journal, Vol. 79, No 13, pp. 1235-1244, 2009.
[13] C.F.J. Kuo, Y.J. Huang, T.L. Su, C.Y. Shih, “Computerized Color Distinguishing System for Color Printed Fabric by Using the Approach of Probabilistic Neural Network,” Polymer-Plastics Technology and Engineering, Vol. 47, pp. 264-272, 2008.
[14] 施中揚、許銘訓、許根榮，以模糊聚類法進行印花布彩色圖案分析之研究，中華民國紡織工程學會誌，第21卷，第1期，第69-80頁，2003。
[15] 林淑心，巧手慧思色彩絢麗的中國刺繡，台灣台北:台灣國立歷史博物館，1989。
[16] 曹煥旭，中國古代的工匠，中國北京:商務印書館國際有限公司，1996。
 
[17] 楊家駱，繡譜，台灣台北:世界書局，1982。
[18] 譚旦冏，中國美術史論集3，台灣台北:中國文化出版事業，1955。
[19] 粘碧華，刺繡針法百種：簡史與示範，台灣台北:雄獅圖書股份有限公司，2003。
[20] 陳席卿、鄭淑琴合著，刺繡鄉情樸仔腳，台灣嘉義縣:朴子市公所出版，2005。
[21] 張翠，吳珍霞，刺繡針法大全，中國瀋陽:遼寧科學技術出版社，2010。
[22] 何應勤、曹又仁，結合小波轉換與紋理特徵之彩色影像檢索，國立中山大學機械與機電工程研究所碩士論文，2005。
[23] 章毓晉編著，圖像處理和分析，中國北京:清華大學出版社，1999。
[24] Gonzalez、繆紹綱編譯，數位影像處理第三版(Digital Image Processing 3/E)，台灣台北:普林斯頓國際有限公司，2009。
[25] International Commission on Illumination,“Recommendations on Uniform Color Spaces, Color-Difference Equations, Psychometric Color Terms,” Paris: Bureau Central de la CIE, No. 2-15, pp.1-21, 1978.
[26] 蘇文鈺、王派洲、王建斌，數位影像分割技術的應用與比較，國立成功大學資訊工程系碩士論文，2003。
[27] 楊傳凱、楊惠琳，秀拉點描派之電腦模擬，國立臺灣科技大學資訊管理系碩士論文，2006。
[28] M.S. Alam, S.F. Goh, S. Dacharaju, “Three-Dimensional Color Pattern Recognition using Fringe-Adjusted Joint Transform Correlation With CIELAB Coordinates,” IEEE Transaction on Instrumentation and Measurement, Vol. 59, pp. 2176-2184, 2010.
 
[29] M.D. Fairchild, “Color Appearance Models Second Edition,” New York: John Wiley & Sons, pp. 248, 2005.
[30] D. Pascale, “A Review of RGB Color Spaces ... from xyY to R'G'B',
” Montreal: Quebec: Babel Color, pp. 14, 2002.
[31] K. Leon, D. Mery, F. Pedreschi, J. Leon, “Color Measurement in L*a*b* Units from RGB Digital Images,” Food Research International, Vol. 39, pp. 1084-1091, 2006.
[32] R.C. Gonzalez and R.E. Woods, “Digital Image Processing,” 3nd edition, Englewood Cliffs, New Jersey: Person Prentice Hall, 2007.
[33] G. Gupta, “Algorithm for Image Processing Using Improved Median Filter and Comparison of Mean, Median and Improved Median Filter,” International Journal of Soft Computing and Engineering (IJSCE), Vol. 1, pp. 304-311, 2011.
[34] M.S. Nixon, and A.S. Aguado, “Feature Extraction and Image Processing,” Oxford: Newnes, pp.89-95, 2002.
[35] 曹又仁、何應勤，結合小波轉換與紋理特徵之彩色影像檢索，國立中山大學機械與機電工程研究所碩士論文，2005。
[36] C. Hsia, J.S. Chiang and J.M. Guo, “Multiple Moving Objects Detection and Tracking Using Discrete Wavelet Transform,” Croatia: Intech, DOI: 10.5772/15772, 2011.
[37] 連國珍，數位影像處理MATLAB，台灣台北:儒林圖書有限公司，2007。
[38] 繆紹綱，數位影像處理 活用Matlab (第二版)，台灣台北:全華圖書有限公司，2000。
[39] J. C. Bezdek, “Pattern Recognition with Fuzzy Objective Function Algorithms,” New York: Plenum Press, 1981.
 
[40] Z.K. Huang, Y.M. Xie, D.H. Liu, L.Y. Hou, “Using Fuzzy C-means Cluster for Histogram-Based Color Image Segmentation,” IEEE International Conference on Information Technology and Computer Science, Vol. 1, pp. 597-600, 2009.
[41] Z. Yux, W. Yuhua, L. Haibo, “A Fuzzy C-means Clustering Based on Hybrid Color Space,” IEEE International Conference on Electrical and Control Engineering, DOI: 10.1109/iCECE.2010. 1112, pp. 4605-4607, 2010.
[42] Y.W. Lim, S.U. Lee, “On the Color Image Segmentation Algorithm Based on the Thresholding and the Fuzzy C-means Techniques,” Sciencedirect Pattern Recognition, Vol. 23(9), pp. 1235-1252, 1990.
[43] W. Dongyun, N. Zhengguang, “Improved Method of Fabric Defects Inspection Based on Local Entropy,” IEEE Control Conference, DOI: 10.1109/CHICC.2008.4605080, pp. 208-211, 2008.
[44] C.F.J. Kuo, C.Y. Shih, J.Y. Lee, “Repeat Pattern Segmentation of Printed Fabrics by Hough Transform Method,” Textile Research Journal, Vol. 75, No 11, pp. 779-783, 2005.
[45] S. Yong-li, Z. Bo, Z. Shu-ling, “Improved Method for Getting Orientation Field of Fingerprint Image,” Computer Engineering and Applications, Vol. 45, pp. 184-186, 2009.
[46] M Kass, A Witkin, “Analyzing Oriented Patterns,” Computer Vision
, Graphics, and Image Processing, Vol. 37, pp. 362-385, 1987.
[47] D. Gabor, “Theory of Communications,” Journal Institution of Electrical Engineers, Vol. 93, pp. 429-457, 1946.
[48] J.G. Daugman, “Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters,” Journal of the Optical Society of America, Vol. 2, pp. 1160-1169, 1985.
 
[49] W. Li, K. Mao, H. Zhang, and T. Chai, “Designing Compact Gabor Filter Banks for Efficient Texture Feature Extraction,” IEEE International Conference on Control Automation Robotics & Vision, DOI: 10.1109/ ICARCV. 2010.5707806, pp.1193-1197, 2010.
[50] R. Roslan, N. Jamil, “Texture Feature Extraction Using 2-D Gabor Filters,” IEEE Symposium on Computer Applications and Industrial Electronics, DOI: 10.1109/ISCAIE.2012.6482091, pp. 173-178, 2012.
[51] Z. Hai Ying, Xu Guang Mei, Xu Zheng Guang, “An Algorithm of Extraction Visual Texture Features Based on Gabor Transformation,
” IEEE Chinese Conference on Pattern Recognition (CCPR), DOI: 10.1109/ CCPR. 2010. 5659252, pp. 1-6, 2010.
[52] R. Han and L. Zhang, “Fabric Defect Detection Method Based on Gabor Filter Mask,” IEEE Intelligent Systems, Vol. 3, pp. 184-188, 2009.
[53] M. Sivalingamaiah, B. D. Venakramana Reddy, “Texture Segmentation Using Multichannel Gabor Filtering,” IOSR Journal of Electronics and Communication Engineering, Vol. 2, pp. 22-26, 2012.
[54] S. Chen, J. Feng, L. Zou, “Study of Fabric Defects Detection through Gabor Filter Based on Scale Transformation,” IEEE International Conference on Image Analysis and Signal Processing, DOI: 10.1109 /IASP.2010.5476155, pp. 97-99, 2010.
[55] J. K. Kamarainen, V. Kyrki, and H. Kalviainen, “Invariance Properties of Gabor Filter Based Features–Overview and Applications,” IEEE Transactions on Image Processing, Vol. 15, pp. 1088-1099, 2006.
 
[56] 林佳弘、李貴琪，陳鑫湶，電性織物製備熱塑性複合材料之電氣/機械特性與其最佳化電磁效應驗證，逢甲大學紡織工程研究所博士論文，2007。
[57] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on System, Vol. 9, pp. 62-66, 1979.
[58] T.Y. Zhang, C.Y. Suen, “A Fast Parallel Algorithm for Thinning Digital Patterns,” Image Processing and Computer Vision, Vol. 27, pp. 236-239, 1984.
[59] Y. Zhang, X. Jing, X. Wang, “An Approach to Improve the ZS Thinning Algorithm,” IEEE Network Infrastructure and Digital Content, DOI: 10.1109/ICNIDC.2009.5360858, pp. 750-751, 2009.