臺灣博碩士論文加值系統

近年來隨著經濟發展以及消費行為改變，消費者對於單價較高之個人化商品，與過往相比有更高的購買意願，因此使得有愈來愈多生產商，願意提供針對消費者之商品個人化服務。隨著資訊科技的發展，許多一般日常生活上時常會接觸之介面，也逐漸由傳統方式轉變為電子文件之數位形式。若是可以針對每一位使用者製作出一套對應其個人書寫文字特性之字型檔，使每一位使用者在利用電子文件與其他使用者溝通時，看到之介面字體是具有對方個人風格之字體，讓彼此在日常溝通過程中，增添許多親切感。
論文中主要分為，分析字元與特徵套用部份。分析字元，字元中存在一組控制點，針對其中各個控制點與其他控制點之間之連結所產生之空間關係，判斷其中所具有之筆劃種類，再藉由分析這些筆劃，找出其中是否有可以重組成一字根或特定之筆劃組合之特性，藉此將處理較大範圍之字元層級，縮減為較小規模之字根層級。
特徵套用，於分析字元時所得之字根與原來較大範圍之單一字元相比，筆劃組成之複雜度大為減低，因此有利於針對字根中各個筆劃特徵做個別處理，以得到特徵化之字根。最後再將特徵化之字根套用至所有具有該字根之字元中，以得到完整之個人化字元。

With the development of information technology，the interface of communication is changed into the digit form of the electronic file from the traditional way gradually∙We want make a Chinese font of script that has the characteristics of user，let the interface they used become a script interface with characteristics of other users，when they are communicate with each other∙
The quantity of the Chinese character is very huge，to deal with all Chinese characters step by step is almost impossible∙In order to solve this problem，we need to reduce the problem level from Chinese character to components of Chinese characters，because the components of Chinese characters are used as radical in many characters，by this way，we can use fewer input Chinese characters to make a large amount of Chinese characters personalizing∙
First，analyse all characters in True Type Font file∙Every character has a group of control points∙Calculate the spatial relationship between each control point and other adjacent control points，to judge what stroke type that control point have，then analyse all kinds of stroke types in character to check if there is the characteristics of control points can make some components of Chinese characters∙
Second，calculate features of handwritten radicals in input handwritten Chinese characters which radicals we can recognize in first step，then modify all control points in radical by this features to make radical personalizing∙
Final，replace the personalized radical into all characters which has this radical as components of character to get a personalized True Typr Font file∙

第一章 緒論 1
1.1前言 1
1.2個性化商品 1
1.3相關研究 7
1.4研究簡介 12
第二章 理論基礎 15
2.1正交投影法 15
2.1.1理論 15
2.2 THINNING 15
2.2.1理論 16
2.3 BEZIER CURVE 17
2.3.1理論 18
2.4 TRUE TYPE FONT 簡介 21
第三章 研究方法與步驟 29
3.1前置處理 29
3.1.1字元分類 29
3.1.2筆畫分類 32
3.1.3 字元拆解 34
3.1.4 字元拆解特性 36
3.2 特徵擷取 78
3.3 特徵套用 81
第四章 研究結果 85
第五章 結論 103
參考文獻 104

[1]陳水淋,“中文字型個性化系統之研究,”國立台灣大學碩士論文,1995.
[2]張皓傑,“個性化字型之筆劃特徵抽取系統,” 國立台灣大學碩士論文,1996.
[3] T.Y. Zhang and C.Y. Suen,“A Fast Parallel Algorithm for Thinning Digital Patterns,“Commun.ACM, 27(3):236–240, March 1984.
[4]Y. S. Chen and W. H. Hsu ,“A Modified Fast Parallel Algorithm for Thinning Digital Patterns,“Pattern Recognition Letters, Vol.7, pp.99-106, 1988.
[5]J.Lin and J.G.Li,“Off-Line Chinese Signature Verification,”Proc. Int''l Conf. Image Processing (ICIP), vol. 2, pp. 205-207, 1996.
[6]R. Cao and C.L. Tan,“A model of stroke extraction from Chinese character images,” in Proc. Int. Conf. Pattern Recognition, Spain, 3-8 Sept 2000, Vol 4, pp. 368-371.
[7]C.C. Hsu, L.F. Chen, P.C. Chang, and B.S. Jeng,“On-line chinese signature verification based on multi-expert strategy,”in Proc. 32nd Int.Carnahan Conf. Security Technology, 1998, pp. 169-173
[8]J. Lin, J.G. Li,“Off-Line Chinese Signature Verification,” in Proc. Int''l Conf. Image Processing (ICIP) vol. 2, pp. 205-207, 1996
[9]Y.J. Liu, L.Q. Zhang, J. Tai,“A new approach to on-line handwritten chinese character recognition,”in Proc. of Int. Conf. Document Analysis Recognition (ICDAR), 1993 , pp 192-195
[10]H.P. Chiu, D.C. Tseng,“A feature-preserved thinning algorithm for handwritten Chinese characters,”in Proc. The 13th Int''l Conf. on Pattern Recognition, Vienna, Austria, Aug.25-30, 1996, vol.III, pp. 235-239
[11]J.H. Wang, S.Ozawa,“Automated generation of Chinese character structure data based on extracting the strokes,”Proc. 2nd Int. Conference on Document Analysis Recognition (ICDAR), 1993 , pp 806-809
[12]U.-V. Marti, R. Messerli, H. Bunke,“ Writer identification using text line based features,”Proc. 6th Int. Conference on Document Analysis and Recognition(ICDAR), 2001, pp. 101-105
[13]H.E.S. Said, T.N. Tan, K.D. Baker,“Writer Identification Based on Handwriting, ”Proc. 3rd IEE European Workshop on Handwriting Analysis and Recognition, Brussels, July 14-15,1998, pp 4/1-4/6
[14]G. Leedham, S Chachra,“Writer Identification using Innovative Binarised Features of Handwritten Numerals, ”Proc. 7th Int. Conference on Document Analysis and Recognition(ICDAR), 2003 , pp 413-417

[15]H. Cha, S. Lee,“Establishing Handwriting Individuality Using Pattern Recognition Techniques, ”Proc. 6th Int. Conference on Document Analysis and Recognition(ICDAR), Seattle, WA, September 2001, pp. 1195-1204
[16]X. Gao, L. Jin, J. Yin, J. Huang,“A New Stroke-Based Directional Feature Extraction Approach for Handwritten Chinese Character Recognition, ”Proc. 6th Int. Conference on Document Analysis and Recognition(ICDAR),2001,pp 635-639
[17]D.S. Yeung, H.S. Fong,“An off-line Approach to Extract Natural Strokes from Handwritten Chinese Characters,” Proc. IEEE 1995 Int. Conf. Systems, Man and Cybernetics, Vol.2, pp.1933-1938, Vancouver, Canada, Nov,1995
[18]F. Lin, X. Tang, “offline handwritten Chinese character stroke extraction,” in Proc. Int. Conf. Pattern Recognition, 2002, pp. 249-252
[19]Hahn-Ming Lee and Chiung-Wei Huang,“Fuzzy Feature Extraction on Handwritten Chinese Characters, ”Proc. of IEEE Int. Conf. on Fuzzy Systems, vol. III, pp.1809-1814, USA June 1994.
[20]H.M. Yang, J.J Lu, H.J Lee,“A Bezier Curve-Based Approach to Shape Description for Chinese Calligraphy Characters,” in Proc. Int. Conf. Document Analysis Recognition (ICDAR), 2001, pp.276-280
[21]http://www.microsoft.com/typography/OTSPEC/otff.htm