請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66702
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 劉長遠(Cheng-Yuan Liou) | |
dc.contributor.author | Chia-Ching Lin | en |
dc.contributor.author | 林佳慶 | zh_TW |
dc.date.accessioned | 2021-06-17T00:52:19Z | - |
dc.date.available | 2013-01-17 | |
dc.date.copyright | 2012-01-17 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-11-02 | |
dc.identifier.citation | [1] C. Y. Liou and H. C. Yang, “Handprinted character recognition based on spatial topology distance measurements,” IEEE Trans. Pattern Anal. Machine Intell., vol. 18, pp. 941-945, Sept. 1996.
[2] D. Gillevic and C.Y. Suen, “HMM-KNN Word Recognition Engine for Bank Cheque Processing,” Proc. 14th Int'l Conf. Pattern Recognition, pp. 1526-1529, Brisbane, Australia, Aug. 1998. [3] F. T. Yarman-Vural and A. Atici, “A segmentation and feature extraction algorithm for Ottoman cursive script,” in Proc. 3rd Turkish Symp. Artif. Intell. Neural Networks, 1994. [4] F. T. Yarman-Vural and E. Ataman, “Noise histogram and cluster validity for Gaussian mixtured data,” Pattern Recognit., vol. 20, no. 4, pp. 385-401, 1987. [5] H. D. Block, B. W. Knight, and F. Rosenblatt, “Analysis of a four layer serious coupled perceptron,” Rev. Mod. Phys., vol. 34, pp. 135-152, 1962. [6] J. Serra, “Morphological filtering: An overview,” Signal Processing, vol.38, no. 1, pp. 3-11, 1994. [7] K. M. Mohiuddin and J. Mao, “A comparative study of different classifiers for handprinted character recognition,” Pattern Recognit. Practice IV, pp. 437-448, 1994. [8] L. Lam, S. W. Lee, and C. Y. Suen, “Thinning methodologies-A comprehensive survey,” IEEE Trans. Pattern Anal. Machine Intell., vol. 14, pp. 869-885, Sept. 1992. [9] L. O’Gorman, “The document spectrum for page layout analysis,” IEEE Trans. Pattern Anal. Machine Intell., vol. 15, pp. 162-173, 1993. [10] M. A. Mohamed and P. Gader, “Generalized hidden Markov models-Part II: Application to handwritten word recognition,” IEEE Trans. Fuzzy Syst., vol. 8, pp. 82-95, Feb. 2000. [11] M. Bokser, “Omnifont technologies,” Proc. IEEE, vol. 80, pp. 1066-1078, 1992. [12] M. L. Minsky and S. Papert, Perceptrons: An Introduction to Computational Geometry. Cambridge, MA: MIT Press, 1969. [13] M. Okamoto and K. Yamamoto, “On-line handwriting character recognition method with directional features and direction change features,” in Proc. 4th Int. Conf. Document Anal. Recognit., Ulm, Germany, 1997, pp. 926-930. [14] N. Arica and F. T. Yarman-Vural, “One dimensional representation of two dimensional information for HMM based handwritten recognition,” Pattern Recognit. Lett., vol. 21, no. 6-7, pp. 583-592, 2000. [15] Niranjan Joshi, G. Sita, A. G. Ramakrishnan, Deepu V., Sriganesh Madhavanath, 'Machine Recognition of On-line Handwriteen Devangari Characters,' IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 12, No. 8, pp. 787-807, 2005. [16] Ø. D. Trier, A. K. Jain, and T. Taxt, “Feature extraction method for character recognition—A survey,” Pattern Recognit., vol. 29, no. 4, pp. 641-662, 1996. [17] R. G. Casey and E. Lecolinet, “A survey of methods and strategies in character segmentation,” IEEE Trans. Pattern Anal. Machine Intell., vol.18, pp. 690-706, July 1996. [18] S. L. Xie and M. Suk, “On machine recognition of hand-printed Chinese characters by feature relaxation,” Pattern Recognit., vol. 21, no. 1, pp. 1-7, 1988. [19] S. Madhvanath and V. Govindaraju, “Reference lines for holistic recognition of handwritten words,” Pattern Recognit., vol. 32, no. 12, pp. 2021–2028, 1999. [20] S. Madhvanath, G. Kim, and V. Govindaraju, “Chaincode contour processing for handwrittenword recognition,” IEEE Pattern. Anal. Machine Intell., vol. 21, pp. 928-932, Sept. 1999. [21] S. Madhvanath, G. Kim, and V. Govindaraju, “Chaincode contour processing for handwrittenword recognition,” IEEE Pattern. Anal. Machine Intell., vol. 21, pp. 928-932, Sept. 1999. [22] S. Mo and V. J. Mathews, “Adaptive, quadratic preprocessing of document images for binarization,” IEEE Trans. Image Processing, vol. 7, pp. 992-999, July 1998. [23] S. O. Belkasim, M. Shridhar, and M. Ahmadi, “Pattern recognition with moment invariants: A comparative survey,” Pattern Recognit., vol. 24, no. 12, pp. 1117-1138, 1991. [24] S. Smith et al., “Handwritten character classification using nearest neighbor in large databases,” IEEE. Trans. Pattern Anal. Machine Intell., vol. 16, pp. 915-919, Sept. 1994. [25] K. C. Santosh and C. Nattee, “Effect of Pre-processing and feature Selection in Recognition for Nepali” The first International Conference on Knowledge, Information and Creativity Support Systems (KICSS), Ayuthya, Thailand, pp. 139-146, 2006. [26] S. M. Watt, X. Xie, “Recognition of Large Sets of Handwritten Mathematical Symbols”, IEEE International Conference on Document Analysis and Recognition (ICDAR), pp. 39–43, 2005. [27] T. Kohonen, “The self-organizing map,” Neurocomputing, vol. 21, pp. 1-6, 1998. [28] T. Kohonen, “The self-organizing map,” Proc. IEEE, vol. 78, pp. 1464-1480, 1990. [29] T. Kohonen. Self-Organizing Maps, Springer Series in Information Sciences, vol. 30, Springer, Heidelberg, 1995. [30] T. Kunango, R. Haralick, and I. Phillips, “Nonlinear local and global document degradation models,” Int. J. Imaging Syst. Technol., vol. 5, no. 4, pp. 274-282, 1994. [31] T. Pavlidis, “Recognition of printed text under realistic conditions,” Pattern Recognit. Lett., p. 326, 1993. [32] T. Shioyama, H. Y. Wu, and T. Nojima, “Recognition algorithm based on wavelet transform for handprinted Chinese characters,” in Proc. 14th Int. Conf. Pattern Recognit., vol. 1, pp. 229-232, 1998. [33] W. Lu, Y. Ren, and C. Y. Suen, “Hierarchical attributed graph representation and recognition of handwritten chinese characters,” Pattern Recognit., vol. 24, no. 7, pp. 617–632, 1991. [34] X. Li, W. Oh, J. Hong, and W. Gao, “Recognizing components of handwritten characters by attributed relational graphs with stable features,” in Proc. 4th Int. Conf. Document Anal. Recognit., 1997, pp. 616-620. [35] X. Zhu, Y. Shi, and S. Wang, “A new algorithm of connected character image based on Fourier transform,” in Proc. 5th Int. Conf. Document Anal. Recognit., Bangalore, India, 1999, pp. 788-791. [36] Y. Hamamoto, S. Uchimura, K. Masamizu and S. Tomita, “Recognition of handprinted Chinese characters using Gabor features,” in Proc. 3rd Int. Conf. Document Anal. Recognit., Montreal, QC, Canada, 1995, pp. 819-823. [37] Y. Tao and Y. Y. Tang, “The feature extraction of Chinese character based on contour information,” in Proc. 5th Int. Conf. Document Anal. Recognit., Bangalore, India, 1999, pp. 637-640. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66702 | - |
dc.description.abstract | 在本篇論文中我們研究如何設定形狀規則,並將他們轉換為邏輯規則來篩選掉不正確的標準字元,目的是為了減少在空間拓樸失真量測方法中的候選標準字元 [1],如此一來能大量減少不必要的計算,此外,利用形狀限制加入自組織網路訓練流程來提高辨識率,這些篩選規則與限制是讓辨識演算法減少執行時間與增加辨識率最關鍵的兩個步驟。 | zh_TW |
dc.description.abstract | This work shows how to set shape rules and convert them into logical rules to skip incorrect templates and reduce the number of candidate templates in the spatial topology distortion measurement method [1]. This will drastically reduce the number of computations with improved recognition. Also, the recognition rate is improved by including shape constraints in the self-organizing matching process. The rules and constraints compose the two key steps to reduce the running time and improve the recognition rate. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T00:52:19Z (GMT). No. of bitstreams: 1 ntu-100-R96922142-1.pdf: 1927032 bytes, checksum: 1df2231b7e47eba32ef6585085437e5a (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 誌謝 i
摘要 ii Abstract iii 目錄 iv 圖目錄 vi 表目錄 ix 第一章 緒論 1 1.1 動機 1 1.2 背景 1 1.3 論文架構 4 第二章 手寫辨識流程 5 2.1 離線手寫辨識 5 2.1.1 前置處理 5 2.1.2 分割方法 7 2.1.3 表現方法 8 2.1.4 訓練與辨識技術 8 2.1.5 後處理 11 2.2 線上手寫辨識 12 2.2.1 前置處理 12 2.2.2 特徵擷取 13 2.2.3 距離度量 13 第三章 類神經網路 17 3.1 自組織網路介紹 18 3.2 自組織網路組成與條件 19 3.3 自組織網路演算法 20 第四章 手寫辨識演算法 24 4.1 背景 24 4.2 橢圓表示法 27 4.3 SOM訓練與匹配 31 4.4 演算法細節改進 34 4.5 篩選機制 41 4.5.1 篩選規則 41 4.5.2 篩選結果 46 4.6 加入限制 52 4.6.1 區域鄰居限制 55 4.6.2 拓樸結構限制 57 4.6.3 幾何位置限制 59 4.6.4 模擬結果 60 第五章 結論 66 5.1 討論 66 5.2 未來發展與應用 67 參考文獻 68 | |
dc.language.iso | zh-TW | |
dc.title | 設定形狀規則用於手寫字辨識 | zh_TW |
dc.title | Setting Shape Rules for Handprinted Character Recognition | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 呂育道(Yuh-Dauh Lyuu),黃昭綺(Jau-Chi Huang),鄭為正(Wei-Chen Cheng) | |
dc.subject.keyword | 樣式辨識,手寫字辨識,自組織網路,形狀規則,形狀限制, | zh_TW |
dc.subject.keyword | Pattern recognition,Handprinted character recognition,Self-organizing map,Shape rule,Shape constraint, | en |
dc.relation.page | 71 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-11-02 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf 目前未授權公開取用 | 1.88 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。