臺灣博碩士論文加值系統

本篇論文將提出運用可塑性認知網路（Plastic Perception Neural Network）來完成手寫身分證字號辨識系統。文中所運用的可塑性認知網路的架構是針對類神經網路(Artificial Neural Networks)中倒傳遞類神經網路(Back-propagation Neural Network) 的學習法則以及其網路架構做改進，來克服傳統的倒傳遞類神經網路在訓練時學習速度太慢、不易收斂、及當刪除或加入新的訓練樣本(patterns)時必須全盤重新訓練等問題。這些缺點成為實現即時的倒傳遞類神經網路系統的嚴重障礙。為了克服這樣的障礙，我們結合平行分散處理的觀念，對倒傳遞類神經網路的網路架構做一改進，以增快其學習速度，並克服全盤重新訓練的問題。本文尚包括文字切割、雜訊去除，以及字型特徵值的抽取，適切的字型特徵值抽取有助於字型的辨識，本文所採用的特徵向量是結合白色跑長碼（White Run-Length）與圖素密度（Pixel Density），可以分別表現出字型的結構性與整體性，以達到高準確的辨識率。

This thesis brings up the implementation of handwritten ID number recognition system by the application of plastic perceptron neural network（PPNN）. The applied structure of PPNN in this thesis is improved from the learning algorithm and network structure of back-propagation neural network （BPNN）in artificial neural networks. The problems of traditional BPNN such as longer learning period, not prone to convergence, re-training while delete or add new patterns make the realization of real time BPNN system impossible. The proposed methods are combined with the parallel distributive process concept and modification of the BPNN structure could accelerate the learning speed and solve the re-training problem. The character segmentation, noise removal and extraction of feature are also discussed. Adequate extracted feature make recognition of character easier. The adoption of white run-length and pixel density could clearly display the structural and integral of the character respectively, and facilitate to make higher recognition accuracy.

目 錄
　　　　　　　　　　　　　　　　　　　　　　
中文摘要 i
英文摘要 ii
誌謝 iv
目錄 v
圖目錄 vii
壹、緒論 1
一、 研究動機 1
二、 相關技術背景 1
三、 簡介 3
四、 本論文的組織 4
貳、 類神經網路原理的探討 5
一、 類神經元的模型 7
二、 類神經網路的架構 11
三、 多層感知網路與倒傳遞演算法 12
四、 類神經網路的學習規則的分析 18
五、 可塑性認知網路 19
參、手寫身分證字號辨識系統的架構 21
一、 前處理 22
二、 特徵抽取 26
三、 可塑性認知網路部分 29
肆、 系統的實作 33
一、 系統運作的流程 33
二、 樣本收集與前處理 33
三、 特徵向量抽取 38
四、 可塑性認知網路的訓練學習 43
伍、模擬結果與討論 46
一、 模擬結果 46
二、 討論 58
陸、結論與未來研究的方向 61
一、 結論 61
二、 未來研究的方向 61
參考文獻 63
附錄一 訓練程式 67
辨識程式 75

參考文獻
[1]林育慈，1997，離線手寫印刷體英數字之辨識，國立台灣師範大學，碩士論文
[2]王爵兒，1989，以神經網路作手寫英數字辨認，國立交通大學，碩士論文
[3]阮星明，1991，類神經網路在線上手寫英數字辨識應用之研究，國立交通大學，碩士論文,.
[4]藍天寶，1993，以二分類神經網路與模糊邏輯之手寫文字辨識系統，私立中原大學，碩士論文
[5]Yong Haur Tay, Pierre-Michel Lallican, Marzuki Khalid, Christian Viard-Gaudin, Stefan Knerr, “Offline Handwritten Word Recognition Using a Hybrid Neural Network and Markov Model”, International Symposium on Signal Processing and its Applications(ISSPA), pp.382-385, Kuala Lumpur, Malaysia, 13-16 August, 2001.
[6]Yann Lecun, Léon Bottou, Yoshua Bengio, and Patrick Haffner, “Gradient — Based Learning Applied to Document Recognition”, Proceedings of The IEEE, Vol. 86 No.11, pp.2278-2323 November 1998.
[7]戴敏倫，1989，快速學習類神經網路手寫英數字與中文字辨認系統，私立中原大學，碩士論文
[8]周義昌、蔡玉娟、劉榮宜、李素玲、戴敏倫，類神經網路的新架構：可塑性認知網路，電信研究季刊，第22卷第3期,pp.291-306,6月,1992.
[9] Rangachari Anand, Kishan Mehrotra, Chilukuri K. and Sanjay Ranka, “Efficient Classification for Multiclass Problems Using Modular Nerual Networks”, IEEE Transactions on Neural Networks, Vol. 5, No.1,pp.117-124, January 1995.
[10] Hsin-Chia Fu, Hung-Yuan Chang, Yeong Yuh Xu, and H-T Pao, “User Adaptive Handwriting Recognition by Self-Growing Probabilistic Decision-Based Neural Networks”, IEEE Transactions on Neural Networks, Vol. 11, No.6,pp.1373-1384, November 2000.
[11] Chin-Teng Lin and C.S. George Lee, Neural Fuzzy System, Chapter9, Prentice-Hall International, Inc..
[12] 蘇木春、張孝德，機器學習、類神經網路、模糊系統以及基因演算法則，第三章,全華科技圖書股份有限公司,1997.
[13] Jacques de Villiers and Etienne Bamard “Backpropagation Neural Nets with One and Two Hidden Layers”, IEEE Transactions on Neural Networks, Vol. 4, No.1, pp.136-141, January 1992.
[14] 蔡瑞煌，1995，類神經網路概論，第七章, 三民書局
[15] Barak A. Pearlmutter, “Gradient Calculation for Dynamic Recurrent Neural Network : A Survey”, IEEE Transactions on Neural Networks, Vol. 6, No. 5,pp.1212-1228, May 1995.
[16] Francesco Lampariello and Marco Sciandrone, “Efficient Training of RBF Neural Networks for Pattern Recognition”, IEEE Transactions on Neural Networks, Vol. 12, No. 5,pp.1235-1242, September 2001.
[17] V.V. Phansalkar and P.S. Sastry “Analysis of the Backpropagation Algorithm with Momentum” , IEEE Transactions on Neural Networks Vol. 5, No.3,pp.505-506, May 1994.
[18] MATLAB Online Manuals, “Image Processing Toolbox User’s Guide”, Math Works, Inc.
[19] 繆紹綱，1999，數位影像處理，第九、十章，全華科技圖書股份有限公司
[20] Richard G. Casey and Eric Lecolinet, “A Survey of Methods and Strategies in Character Segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 18, No. 7, pp.690-706, July 1996.
[21] C.G. Leedham and P.D. Friday, “Isolating Individual Handwritten Characters”, Character Recognition and Applications, IEE Colloquium on , 1989.
[22]Seong-Whan Lee, Dong-June Lee, Hee-Seon Park, “A New Methodology for Gray-Scale Character Segmentation and Recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 18, No. 10, pp.1045-1050, October 1996.
[23] C.E. Dunn and P.S.P. Wang, “Character Segmentation Techniques for Handwritten Text — A survey,” Proc. 11th Int’l Conf. Pattern Recognition, vol.2, p.577, Aug. 1992.
[24] Hiromitsu Yamada, Kazuhiko Yamamoto, Taiichi Saito, “A Nonlinear Normalization Kanji Character Recognition — Line Density Equalization,” Pattern Recognition, 1988., 9th International Conference on , vol.1 page(s): 172 —175, 1988.
[25] Sang-Yup Kim, Seong-Whan Lee, “Nonlinear Shape Normalization Methods for Gray-Scale Handwritten Character Recognition, ” Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on , Volume: 2 , page(s): 479 —482, 1997.
[26] Qing Wang; Zheru Chi; Feng, D.D.; Rongehun Zhao, “Match between Normalization Schemes and Feature Sets for Handwritten Chinese Character Recognition,” Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on , Page(s): 551 -555, 2001.
[27] Howard Demuth and Mark Beale, “Neural Networks Toolbox User’s Guide” , Math Works,Inc.