電腦刺繡製版的目的是將設計圖轉換成電子訊號，用以控制繡花機。目前的製版方法尚仰賴傳統人工作業，須耗費大量人力且十分費時。
本研究藉由圖學的理論與影像處理的技術，提出電腦刺繡製版的流程與模式。研究範圍鎖定英文字母與阿拉伯數字。先萃取影像之中心軸、分枝點與端點等特徵以表示刺繡樣本，以上述特徵規劃刺繡時針頭移動的路徑，並定位刺繡點的座標。本研究成果尚可擴展至圖案與中文刺繡的探討。
在規劃刺繡路徑方面，本研究提出了先求最長路徑，再以深度優先搜尋法巡視分枝的演算法。規劃所得之結果接近最佳路徑，甚至擴展至中文字亦能求得可行之路徑。
在計算刺繡點方面，先以逆傳遞類神經網路辨識中心軸之分枝形態，針對不同的分枝形態，加以適當地分割或合併，並指定中心軸對應之繡線方向。再以polyline和circular arc逼近中心軸，最後配合指定之密度與先前決定之繡線方向，求出刺繡點座標。經由刺繡點座標，即可模擬繡件成品。

In this thesis, a prototype of an automatic embroidery digitizing system is proposed. First, medial axes are found to represent the embroidery in a compact form. Back-propagation neural network is then used to classify different types of junctions and endpoints along the skeleton. A silk threading plan is then determined via a greedy path planning algorithm that is very efficient in minimizing the number of extraneous path while maintaining the look and feel of an acceptable end product. Experiments have shown that the proposed method can produce satisfactory results on printed English alphabets and on digits 0 through 9.

[1] H. Blum. “A transformation for extracting new descriptors of shape,” Models for the Perception of Speech and Visual Form, Wathen-Dunn, W., ed., MIT Press, Cambridge, MA., 1967.
[2] O. Baruch. “Line thinning by line following,” Pattern Recognition Letters, 8(4):271-276, 1988.
[3] Burden and Faires. Numerical Analysis,5th Edition. PWS-KENT publishers, USA, 1993.
[4] Y. S. Chen. “Hidden deletable pixel detection usnig vector analysis in parallel thinning to obtain bias-reduced skeletons,” Computer Vision and Image Understanding, 71(3):294-311, 1998.
[5] J. A. Dossey, A. D. Otto, L. Spence and C. V. Eynden. Discrete Mathematics, Foresman, Scott, 1987.
[6] C. R. Dyer and A. Rosenfeld. “Thinning algorithms for grayscale pictures,” IEEE Transactions On Pattern Analysis and Machine Intelligence, 1(1): 88-89, 1979.
[7] L. Euler. “Leonhard Euler and th Koenigsberg bridges,” J. R. Newman, ed., Scientific America, pp.66-70, 1953.
[8] S. Even. Graph Alogrithms, Computer Science Press, Rockville, Md., 1979.
[9] J. A. Freeman and D. M. Skapura. Neural Networks Algorithms, Applications, and Programming Techniques, Addison-Wesley, 1992.
[10] R. Gould. Graph Theory, The Benjamin/Cummings Publishing Company, Inc., 1988.
[11] A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Prentice-Hall, 1988.
[12] R. Jain, R. Kasturi and B. G. Schunck. Machine Vision, McGraw-Hill, 1995.
[13] B. K. Jang and R. T. Chin. “Analysis of thinning algorithms using mathematical morphology,” IEEE Transactions On Pattern Analysis and Machine Intelligence, 12(6):541-551, 1990.
[14] R. Johnsonbaugh. Discrete Mathematics, Revised Edition, Macmillan, 1986.
[15] T. Kim, J. C. Bezdek and R. J. Hathaway. “Optimality tests for fixed points of the fuzzy c-means algorithm,” Pattern Recognition, 21(6):651-663, 1988.
[16] L. Lam, S. W. Lee and C. Y. Suen. “Thinning methodologies-a comprehensive survey,” IEEE Transactions On Pattern Analysis and Machine Intelligence, 14(6):869-885, 1991.
[17] L. Lam, and C. Y. Suen. “An evaluation of parallel thinning algorithms for character recognition,” IEEE Transactions On Pattern Analysis and Machine Intelligence, 17(9):914-919, 1995.
[18] H. E. Lu and P. S. P. Wang. “A comment on a fast parallel algorithm for thinning digital patterns,” Communcations of the ACM, 29(3):239-242, 1986.
[19] T. Pavlidis. “Curve fitting as a pattern recognition problem,” In Proc. Int. Conf. on Pattern Recognition, pp.853-859, 1982.
[20] D. F. Rogers and J. A. Adams. Mathematical Elements for Computer Graphics, McGraw-Hill, New York, 1976.
[21] D. Shaked and A. M. Bruckstein. “The curve axis,” Computer Vision And Image Understanding, 63(2):367-379, 1996.
[22] S. Suzuki and K. Abe. “Binary picture thinning by an iterative parallel two-subcycle operation,” Pattern Recognition, 20(3):297-307, 1987.
[23] Z. S. G. Tari, J. Shah and H. Pien. “Extraction of shape skeletons form grayscale images,” Computer Vision and Image Understanding, 66(2):133-146, 1997.
[24] S. Tehrani, T. E. Weymouth, and B. G. Schunck. “Interpolating cubic spline contours by minimizing second derivative discontinuity,” In Proceedings of the International Conference on Computer Vision, pp.713-716, 1990.
[25] A. C. Tucker. A New Application Proof of the Euler Circuit Theorem. Amer. Math. Monthly, 83, pp. 683-640, 1976.
[26] R. J. Wilson & J. J Watkins. Graphs An Introductory Approach, Wiley, New York, 1990.
[27] X. L. Xie and G. Beni. “A validity measure for fuzzy clustering,” IEEE Transactions On Pattern Analysis and Machine Intelligence, 13(8):841-847, 1991.
[28] S. S. Yu and W. H. Tsai. “A new thinning algorithm for gray-scale images,” Pattern Recognition, 23(10):1076-1076, 1990.
[29] T. Y. Zhang and C. Y. Suen. “A fast parallel algorithm for thinning digital patterns,” Communcations of the ACM, 27(3):236-239, 1984.
[30] H.-J. Zimmermann. Fuzzy Set Theory and Its Applications, 2nd edition. Kluwer Academic Publishers, Boston, 1991.
[1] 新聞局網頁http://www.gio.gov.tw/info/culture_c/aei025.html
[32] 儀千中國服飾http://new.net.tw/Yc/as2-22-2-7.htm
[33] 三友刺繡製版公司http://mail.ht.net.tw/~creator/30.htm
[34] Balarad http://www.balarad.sk/sw/fa/manual.htm
[35] SofTeam http://www.softeamweb.com/product/punto_lettering.html
[36] Proel http://www.proel.it/w_prof_e.htm
[37] Dalco Athletic http://www.dalcoathletic.com/software/ss3/stockstitch3.html
[38] Brother Products http://www.brother.com/embroidery/be100/be100.html
[39] Data-Stitch Inc. http://www.datastitch.com/stitch.html
[40] B & V http://www.bnvsoft.com/ED.htm
[41] Melco http://www.melco.com/page5/software/software.html
[42] MESA Distributors, Inc. http://www.mesadist.com/
[43] WINgs http://www.gunoldtechnology.com/wings/levels/wngscom1.thml
[44] Richpeace http://www.richpeace.com/newen/es2-98.htm
[45] Wilcom http://www.wilcom.com.au/sbonus.htm
[46] Sierra http://www.gosierra.com/eod2.html
[47] Punchperfect http://www.punchperfect.com/picture.htm
[48] Macpherson-Meistergram http://www.mac-meister.com/hyperstitch.html