(34.237.52.11) 您好!臺灣時間:2021/05/18 13:55
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:蔡旻諺
研究生(外文):Ming-Yen Tsai
論文名稱:點分佈模型在線上手寫中文辨識之應用
論文名稱(外文):Applications of the Point Distribution Model to Online Chinese Handwriting Recognition
指導教授:藍呂興
指導教授(外文):Leu-Shing Lan
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:電子與資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2005
畢業學年度:93
語文別:中文
論文頁數:81
中文關鍵詞:文字辨識自動產生文字資料庫使用者確認線上手寫中文辨識點分佈模型
外文關鍵詞:Generation of DatabaseWriter IdentificationPDMOnline Chinese Handwriting Recognition
相關次數:
  • 被引用被引用:0
  • 點閱點閱:137
  • 評分評分:
  • 下載下載:11
  • 收藏至我的研究室書目清單書目收藏:0
線上手寫中文輸入系統為大家所熟知,是一種最直覺與自然的輸入方式,而為了使資料正確並且更容易完成輸入,手寫輸入與文字辨識即成了重要的技術之一。線上手寫中文辨識最主要的困難在於手寫有很高的變動性與不確定性,因此本論文提出以點分佈模型(Point Distribution Model, PDM)[1]為基礎的方法應用於自動產生文字模型、使用者確認和線上手寫中文字辨識。本論文使用PDM法主要有兩個部分所組成,其一為使用對正演算法(approximate alignment of similar training shapes)訓練點模型,其二為使用主要特徵分析(Principal Component Analysis, PCA),本論文中並加以改進方法使得更符合中文辨識之需要與應用。自動產生文字模型由實驗結果可顯示出只需要少量訓練資料即可產生大量可變文字模型使收集文字模型資料更為方便。而在使用者確認方面,十五個使用者書寫相同文字字串,則辨識率最高可達97.3%。線上中文手寫辨識方面,使用四劃字與十二劃字做為測試資料,收集十個使用者書寫,四劃字平均辨識率可達97%與距離比對法[10]相比提升5.6%,而十二劃字平均辨識率98%,與距離比對法相比提升3%,因此不管筆劃多寡,PDM都能顯著地提升線上手寫中文文字辨識率。
In this thesis, we investigate the applications of the point distribution model (PDM) to online Chinese handwriting recognition. Three possibilities have been considered, including (1) an improved online Chinese handwritten character recognition scheme, (2) a generative model for online Chinese handwriting, and (3) a writer identification method using the PDM. High recognition rates were obtained from various experimental settings. These results confirm the applicability of the PDM approach.
中文摘要.......................................................... i
英文摘要 ......................................................... ii
誌 謝 ......................................................... iii
目 錄 ......................................................... iv
表 目 錄 ......................................................... vi
圖 目 錄 ......................................................... vii

第一章 簡 介 …………………………………………………………………… 1
1.1 研究動機 ………………………………………………………………… 1
1.2 研究目的 ………………………………………………………………… 2
1.3 本論文之貢獻 …………………………………………………………… 3
1.4 章節概要 ………………………………………………………………… 4

第二章 文字辨認簡介與相關研究 ……………………………………………… 5
2.1 文字辨認簡介 …………………………………………………………… 5
2.2 相關研究 ………………………………………………………………… 7

第三章 文字變形技術與點分佈模型 …………………………………………… 8
3.1 文字變形技術介紹……………………………………………………… 8
3.2 點分佈模型簡介………………………………………………………… 12
3.3 訓練點分佈模型………………………………………………………… 13
3.4 點分佈模型特徵粹取…………………………………………………… 15
3.5 點分佈模型變形技術…………………………………………………… 16

第四章 點分佈模型之應用 …………………………………………………… 19
4.1 系統架構與簡介………………………………………………………… 19
4.2 自動產生大量文字模型 ……………………………………………… 20
4.3 線上手寫相似字辨識 ………………………………………………… 24
4.4 線上手寫使用者確認 ………………………………………………… 29

第五章 點分佈模型在線上手寫中文辨識之實驗結果 ……………………… 34
5.1 辨識字庫與模擬環境說明 …………………………………………… 34
5.2 各項實驗參數設定 …………………………………………………… 35
5.3 實驗結果 ……………………………………………………………… 35

第六章 線上手寫中文辨識與使用者適應……………………………………… 42
6.1 使用者適應簡介………………………………………………………… 42
6.2 使用者適應方法介紹…………………………………………………… 43
6.3 實驗結果………………………………………………………………… 54

第七章 結論與未來研究方向…………………………………………………… 56
7.1 結論 …………………………………………………………………… 56
7.2 未來研究方向 ………………………………………………………… 57

參考文獻 …………………………………………………………………………… 58
附 錄 A 常用5401中文字字集表………………………………………………… 61
附 錄 B 測試字字集……………………………………………………………… 71
[1] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, “Active Shape Models-Their Training and Application,” Computer Vision and Image Understanding Vol. 61, No. 1, January, pp. 38-59, 1995.
[2] Jian Yang, Jing-yu Yang, “From image vector to matrix: a straightforward image projection technique-IMPCA vs. PCA,” Pattern Recognition, Vol. 35 (2002) 1997-1999.
[3] A. Hill, T. F. Cootes, C. J. Taylor, “Active Shape Models and the shape approximation problem,” Image and Vision Computing , Vol.14 (1996) 601-607.
[4] Jian Yang, David Zhang, Alejandro F. Frangi, and Jing-yu Yang, “Two Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 1, January 2004.
[5] Michael Revow, Christopher K. I. Williams, and Geoffrey E. Hinton, “Using Generative Models for Handwritten Digit Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 6, June 1996.
[6] D. Ghosh, A.P. Shivaprasad, “An analytic approach for generation of artificial hand-printed character database from given generative models,” Pattern Recognition , Vol. 32 (1999) p. 907-920
[7] T. Wakahara, “On-line cursive Kanji character recognition using Local Affine Transformation,” Proc. Ninth Intl. Conf. Pattern Recognition, pp. 1133 ~ 1137, Nov. 1988.
[8] Kwok-Wai Cheung, Dit-Yan Yeung, Roland T. Chin, “On Deformable models for visual pattern recognition,” Pattern Recognition, Vol. 35 (2002) 1507-1526.
[9] Toru Wakahara and Kazumi Odaka, “On-Line Cursive Kanji Character Recognition Using Stroke-Based Affine Transformation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 12, December 1997.
[10] T. Wakahara, H. Murase, and K. Odaka, “On-line handwriting recognition,” Proceedings of the IEEE, Vol. 80(7), pp. 1181 ~ 1194, Jul. 1992.
[11] Evelin J. Bellegarda, Jerome R. Bellegarda, David Nahamoo, and Krishna S. Nathan, “A Fast Statistical Mixture Algorithm for On-Line Handwriting Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 12, December 1994.
[12] V. Vuori, J. Laaksonen, E. Oja, J. Kangas, “Experiments with adaptation strategies for a prototype-based recognition system for isolated handwritten characters,” International Journal on Document Analysis and Recognition (2001) 3: 150-159
[13] Cheng-Lin Liu, Masaki Nakagawa, “Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition,” Pattern Recognition, Vol. 34 (2001) 601-615
[14] Scott D. Connell, Anil K. Jain, “Writer Adaptation for Online Handwriting Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 3, March 2002
[15] K. Yoshida and H. Sakoe, “Online Handwritten Character Recognition for a Personal Computer System,” IEEE Tr. Consumer Electronics, Vol. 28 No. 3, pp. 202-208, 1982.
[16] Yih-Tay Tsay and Wen-Hsiang Tsai, ”Attributed string matching by split-and-merge for on-line Chinese character recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15(2), pp. 180 ~ 185, 1993.
[17] Hang Joon Kim, Jong Wha Jung, and Sang Kyoon Kim, “On-line Chinese character recognition using ART-based stroke classification,” Pattern Recognition Letters, Vol. 17 (12), pp. 1311-1322, Dec. 1996.
[18] M. Dehghan, K. Faez, M. Ahmadi, and M. Shridhar, “Holistic handwritten word recognition using discrete HMM and self-organizing feature map,” Proc. IEEE Intl. Conference on Systems Man and Cybernetics 2000, Vol. 4, pp. 2735 ~ 2739, Dec. 2000
[19] Hahn-Ming Lee, Chiung-Wei Huang, and Chung-Chieh Sheu, “A fuzzy rule-based system for handwritten Chinese characters recognition based on radical extraction,” Fuzzy Sets and Systems, Vol. 100(1-3), pp. 59 ~ 70, Nov. 1998.
[20] Cheng-Lin Liu, Stefan Jaeger, and Masaki Nakagawa, “Online Recognition of Chinese Characters: The State-of-the-Art,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 2, February 2004.
[21] K. P. Chan and Y. S. Cheung, “Fuzzy-Attribute Graph with Application to Chinese Character Recognition,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 22, No. 1, January/February 1992.
[22] M. Okamoto and K. Yamamoto, “On-Line Handwriting Character Recognition Using Direction-Change Features that Consider Imaginary Strokes,” Pattern Recognition, Vol. 32, no. 7, pp. 1115-1128, 1999.
[23] Charles C. Tappert、Ching Y. Suen and T. Wakahara “The State of the Art in On-Line Handwriting Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 8, August 1990.
[24] T. Wakahara, and K. Odaka, “Adaptive normalization of handwritten characters using global/local affine transformation,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 20(12) , pp. 1332 ~ 1341, Dec. 1998.
[25] A.K. Jain, and D. Zongker, “Representation and recognition of handwritten digits using deformable templates,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19(12) , pp. 1386 ~ 1390, Dec. 1997.
[26] X. Huang, J. Gu, and Y. Wu, ” A constrained approach to multifont Chinese character recognition,“ IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15(8), pp. 838 ~ 843, Aug. 1993.
[27] C.K.Y. Tsang, and F.-L. Chung, “A structural deformable model with application to post-recognition of handwriting,” Proc. IEEE Intl. Conference on Pattern Recognition 2000, Vol. 2, pp. 129 ~ 132, 2000.
[28] Wen-Tsuen Chen and Tzren-Ru Chou, “A hierarchical deformation model for online cursive script recognition,” Proc. IAPR Intl. Conference on Pattern Recognition Methodology and Systems, pp. 195 ~ 199, Aug 1992
[29] Wen-Tsuen Chen and Tzren-Ru Chou, “A Stochastic Representation of Cursive Chinese Characters for On-Line Recognition,” Pattern Recognition, Vol. 30(6), pp. 903 ~ 920, 1997
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top