臺灣博碩士論文加值系統

本論文提出一個新穎的印花布的自動化影像分析系統，此系統能對印花布影像進行自動化分色及辨識重複圖案。此系統是以掃描器進行影像的取得，所使用到的彩色格式有紅綠藍(RGB)及色調飽和度亮度(HSI)兩種。在分色上，本論文是以兩種方式進行，一是以非監督式聚類法(Unsupervised Clustering Method)於印花布的RGB影像上進行分色。另一是先以基因演算(Genetic Algorithm)法找出與原織物HSI影像有相同顏色分佈的較小HSI子影像，再以遞迴式區域分裂法(Region Splitting Method)進行分色。在重複圖案的辨識上，是以非監督式分類法及模板匹配法(Template Matching)找出相同圖案元件的分佈，再以霍弗(Hough)轉換法找出重複圖案的切割位置及尺寸，然後於印花圖案影像中切割出矩形的單位重複圖案的影像。最後依顏色類別產生相對應的黑圖重複單位，然後再擴展成製版用的黑圖。由實驗結果可知，本系統能自動化且快速地完成印花布影像的自動化分色及重複圖案的辨識。

This dissertation proposes a novel automatic image analysis system for printed fabrics that can automatically make color separation and identify repeat patterns. This system uses a scanner to obtain color images of printed fabrics. There are two types of color models, RGB (red, green, blue) and HSI (hue, saturation, intensity). In the color separation, this system can be operated by two ways. One is conducted by an unsupervised clustering method on the RGB image of the printed fabrics. Another uses a genetic algorithm to search for a smaller HSI sub-image with the same color distribution of the printed fabrics, and then the color separation is conducted by use of a recursive region splitting method. In identifying the repeat patterns, an unsupervised classification method and a template matching method are used to identify distributions of same pattern elements, and then a Hough transform method is applied to obtain the cut positions and dimensions of repeat patterns. Next, an image of the repeat pattern is cut out of the fabrics’ image. Finally, the repeated units of black pictures are generated based on color categories and are then expanded to become black pictures used for plate making. According to the experimental results, this system can rapidly and automatically complete color separation and identify repeat patterns for printed fabrics’ images.

中文摘要 I
Abstract II
誌謝 III
目錄 IV
圖表索引 VII
第1章 前言 1
1.1. 研究動機 1
1.2. 文獻回顧 3
1.3. 研究目的 4
1.4. 論文架構 7
第2章 研究理論 8
2.1. 色彩原理 8
2.1.1. 紅綠藍(RGB)色彩空間 8
2.1.2. 色調飽和度亮度(HSI)色彩空間 10
2.1.3. 兩影像色彩相似度的衡量 11
2.2. 濾波 13
2.2.1. 均值濾波 13
2.2.2. 中值濾波 14
2.3. 基因演算法 15
2.4. 非監督式聚類法 17
2.4.1. 模糊C平均(FCM)聚類法 19
2.4.2. 聚類適切性分析 21
2.5. 區域分裂法 22
2.6. 模版匹配法 23
2.7. 霍弗(Hough)轉換法 24
第3章 實驗 26
3.1. 以非監督聚類法進行印花布RGB影像的分色 27
3.2. 以圖案元件分類法及霍弗(Hough)轉換法進行重複圖案的切割 30
3.3. 以區域分裂法進行印花布HSI影像的分色 34
3.4. 以模版匹配法及霍弗(Hough)轉換法進行重複圖案的切割 38
第4章 結果與討論 44
4.1. 以非監督聚類法進行印花布RGB影像的分色 44
4.2. 以圖案元件分類法及霍弗(Hough)轉換法進行重複圖案的切割 48
4.3. 以區域分裂法進行印花布HSI影像的分色 53
4.4. 以模版匹配法及霍弗(Hough)轉換法進行重複圖案的切割 58
第5章 結論 64
參考文獻 67
附錄 已接受之國內外期刊 71
作著簡介 72

1. Lung, H. J., “Application and Development of Automatic Color Separating System for Print,” Journal of the China Textile Institute, Vol.2, No.4, pp.24-31, 1992.
2. Lung, H. J., “Development of Automatic Color separating System for Print,” Journal of the China Textile Institute, Vol.4, No.2, pp.111-115, 1994.
3. Akin, D. E., Epps, H. H., Archibald, D. D., and Shekhar Sharma, H. S., “Color Measurement of Flax Retted by Various Means,” Textile Research J., Vol.70, No.10, pp.852-858, 2000.
4. Bernard, P., Vanderhaeghen, K., and Kiekens, P., “Color Measurement of Pile Fabrics,” Textile Research J., Vol.69, No.8, pp.552-558, 1999.
5. Dupont, D., Steen, D., and Caze, C., “Modeling Color Alteration After the Spinning Process,” Textile Research J., Vol.71, No.9, pp.755-761, 2001.
6. Xu, B., Su, J., and Dale, D.S., “Cotton Color Grading with a Neural Network,” Textile Research J., Vol.70, No.5, pp.430-436, 2000.
7. Plataniotis, K. N., and Venetsanopoulos, A. N., Color Image Processing and Applications, Springer, New York, pp.239-246, 2000.
8. Liu, J., and Yang Y. H., “Multiresolution Color Image Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., Vol. 16, pp.689-700, 1994.
9. More, J. M. & Solimini, S., Variational Methods in Image Segmentation, Birkhäuser, Boston, pp. 21-34, 1995.
10. Gauch, J., and Hsia, C., “A Comparison of Three Color Image Segmentation Algorithms in Four Color Spaces,” Visual Communications and Image Processing, Vol. 1818, pp. 1168-1181, 1992.
11. Fan, J., Aref, W. G., Hacid, M. S., and Elmagarmid, A. K., “An improved automatic isotropic color edge detection technique,” Pattern Recognition Letters, Vol.22, pp. 1419-1429, 2001.
12. Lin, H. C., Wang, L. L., and Yang, S. N., “Extracting Periodicity of a Regular Texture Base on Autocorrelation Functions,” Pattern Recognition Letters, Vol. 18, pp. 433-443, 1997.
13. Russ, J., The Image Processing Handbook, second ed., CRC Press, 1995.
14. Zucker S. W., and Terzopoulos, D., “Finding Structure in Cooccurrence Matrices for Texture Analysis,” Proc, Int’l Conf. Color in Graphics and Image Processing, Vol. 12, no. 3, pp. 286-308, 1980.
15. Liu, Y., Collins, R. T., and Tsin, Y., “A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 3, 2004.
16. Rafael, C. G., and Richard, E. W., Digital Image Processing 2nd edition, Addison-Wesley, Tokyo, pp.282-348, 2002.
17. Plataniotis, K.N., and Venetsanopoulos, A. N., Color Image Processing and Applications, Springer, New York, 2000.
18. Swain, M. J., and Ballard, D.H., “Color Indexing,” International Journal of Computer Vision, Vol.7, No.1, pp.11-32, 1991.
19. Nixon, M. S., and Aguado, A. S., Feature Extraction and Image Processing, Newnes, Oxford, pp. 89-95, 2002.
20. Holland, J., Adaptation in Natural and Artificial Systems, MIT press, Cambridge, 1992.
21. Mitsuo, G., and Runwei, C., Genetic Algorithms & Engineering Optimization, Wiley-Interscience, New York, 2000.
22. Frank, H., Frank, K., Rudolf, K., and Thomas, R., Fuzzy Cluster Analysis, John Wiley & Sons, New York, 1999.
23. Wong, C. C., Chen, C. C., and Su, M. C., “A Novel Algorithm for Data Clustering,” Pattern Recognition, Vol.34, pp.425-442, 2001.
24. Bezdek, J. C., Pattern Recognition with Fuzzy Objective Function Algorithm, Plenum Press, NY, 1981.
25. Zahid, N., Abouelala, O., Limouri, M., and Essaid, A., “Unsupervised Fuzzy Clustering,” Pattern Recognition Letters, Vol. 20, pp.123-129, 1999.
26. Lim, Y.W., and Lee, S.U., “On the Color Image Segmentation Algorithm Based on the Thresholding and the Fuzzy C-means Techniques, Pattern Recognition, Vol. 23, No. 9, pp.1235-1252, 1990.
27. Trivedi, M. and Bezdek, J.C., “Low-level Segmentation of Aerial Images with Fuzzy Clustering,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 16, No. 4, pp.589-598, 1986.
28. Schalkoff, R. J., Digital Image Processing and Computer Vision, John Wiley & Sons, Singapore, pp.279-286, 1989.
29. Hough, P.V.C., Methods and Means for Recognizing Complex Patterns., U.S. Patent 3, 069, 654, 1962.
30. Umbaugh, S. E., Computer Vision and Image Processing, Prentice Hall PTR, NJ, pp.75-79, 1999.
31. Fausett, L. V., Applied Numerical Analysis using MATLAB, Prentice Hall, NJ, 1999.
32. Kuo, C. F., Shih, C. Y., Kao, C. Y., and Lee, J. Y., “Color and Pattern Analysis for Printed Fabric by Unsupervised Clustering Method,” Textile Research J., Vol.75, No.1, pp.9-12, 2005.
33. Kuo, C. F., Shih, C. Y., and Lee, J. Y., “Repeat Pattern Segmentation of Printed Fabrics by Hough Transform Method,” Textile Research J., Vol.75, No.11, pp.779-783, 2005.
34. Kuo, C. F., Shih, C. Y., and Lee, J. Y., “Separating Color and Identifying Repeat Pattern through the Automatic computerized Analysis System for Printed Fabrics,” Journal of Information Science and Engineering, (accepted, 2006).