臺灣博碩士論文加值系統

本研究設計並探討一種階層式的ART類神經網路於設計它的演算法則並用於文字上的辨認。文字圖形採用二值化的型樣參數並將它擷取低維度的特徵參數。決策樹的最底層的節點為簡化的ART1類神經網路，主要是針對二值化型樣參數的存取與演算，非最底層的節點主要是針對低維度的特徵參數與向量量化法做分類與演算。本研究在最底層簡化的ART1類神經網路節點設計一種方法來處理塑性跟穩定性的平衡問題，可以將干擾少得乾淨型樣做有效的儲存，干擾多的型樣可以分別儲存，同時規劃一種辨識與存取策略。非最底層的節點採用低維度的特徵參數可以大幅減少判斷與訓練的時間。向量量化法做分類。使用二十六個字母與十個阿拉伯數字，針對不同字體與不同程度的干擾分別作案例來觀察與驗證。

In this article, we design simplified ART neural networks based on the concept of In-star and Out-star loop in store and retrieve patterns, and include the simplified ART neural networks in the form of decision tree to make a hierarchical classifier. We investigate the characteristics of the classifier, and design the algorithms for storing and testing patterns. To each pattern of word characters, the binary parameters are adopted, and then the related feature parameters are taken.
The bottom nodes of the decision tree are implemented with the simplified ART neural networks, those are designed to work on the binary pattern vectors; On the other hand, the non-bottom nodes of the decision tree are classifiers of vector quantization work on the feature parameters for clusters classification. By doing this we can highly reduce the computation requirement for training and decision making. For the simplified ART neural networks of the bottom nodes of the decision tree, an algorithm of pattern recognition, pattern storage and retrieve is designed, also an adjusting method is included to handle the problem of stability-plasticity dilemma, in the way that the clean and confirmed patterns can be stored efficiently, while the patterns with different degrees of distortion or noise corrupted can be store separately.
About the experiments, 26 alphanumeric characters and 10 Arabic numerals in the phone of time new Roman are adopted. The experiments are divided into three stages, the first stage transfer and save each of the 36 characters into binary pattern. The second stage we transfer and save each of the binary patterns of the 36 characters into 7 feature parameters. Finally, in the last stage, we adopt the hierarchical ART neural networks, train the networks and use it to recognize the tested character patterns those may or may not included in the 36 trained patterns.

誌謝 i
中文摘要 ii
Abstract iii
目錄 v
第一章 緒論 1
1.1 前言 1
1.2 文獻回顧 2
1.3 研究動機與目的 3
1.4 章節概要 4
第二章 理論基礎 5
2.1　二值化 5
2.2　特徵參數擷取 6
2.2.1 直方圖 6
2.2.2　六個參數所代表的涵意 7
2.3 決策樹 8
2.4　資料分群 9
2.5 主要分量分析 10
2.6　ART 12
2.6.1　自適應共振理論І-運算法則 13
2.6.2　自適應共振理論І-結構 15
2.6.3　簡化的ART1類神經網路 17
第三章 研究方法 18
3.1 實驗流程 18
3.2　實驗方法 18
第四章 電腦模擬 22
4.1 案例模擬 22
4.2 電腦規格使用說明 22
4.3　案例模擬結果 24
4.4　案例模擬之結果 51
4.5　本文模擬結果 52
4.4.1 第一層分類結果 53
4.4.2　第二層分類辨識結果 54
第五章 討論與結論 55
5.1 討論 55
5.2 結論 56
參考文獻 57

[1] Y. P. Huang, S. Y. Lai and W. P. Chuang, “A template-based modelfor license plate recognition,” in Proc. IEEE International Conference on Networking, Sensing and Control,vol.2, pp.737-742, March 2004
[2] M. A. Ko and Y. M. Kim, “License plate surveillance system usingweighted template matching,” in Proc. The 32nd Applied Imagery Pattern Recognition Workshop, pp. 269-274, Oct. 2003
[3] H. A. Hegt, R. J. de la Haye and N. A. Khan, “A high performance license plate recognition system,” in Proc. IEEE International Conference on Systems,Man, and Cybernetics,vol. 5, pp.4357-4362, Oct. 1998
[4] G..A.Carpenter and S. Grossberg, “A massively parallel architecture for a self-organizing neural pattern recognition machine,” Computer Vision Graphics Image Process, vol. 37,pp. 54-115, 1987
[5] C. Coetzee, C. Botha and D. Weber, “PC based number plate recognition system,” in Proc. IEEE Symposium on Industrial Electronics, vol. 2, pp. 605-610, July 1998
[6] P. Comelli, P. Ferragina, M. N. Granieri and F. Stabile, “Optical recognition of motor vehicle license plates,” IEEE Transactions on Vehicular Technology, vol. 44, pp. 790-799, Nov. 1995
[7] Y. P. Huang, S. Y. Lai and W. P. Chuang, “A template-based model for license plate recognition,” in Proc. IEEE International Conference on Networking, Sensing and Control,vol.2, pp.737-742, March 2004
[8] G Carpenter and S. Grossberg, “A massively parallel architecture for self-organizing neural pattern recognition machine,” Computer Vision Graphics Image Process, vol. 37,pp. 54-115, 1987
[9] V.oval, V. Turchenko, V. Kochan, A. Sachenko and G. Markowsky, “Smart license plate recognition system based on image processing using neural network,” in Proc. The Second IEEE International Workshop on Intelligent Data Acquisition And Advanced Computing Systems: Technology and Applications, pp.123-127, Sep. 2003
[10] L. W. Jin and J. Z. Qin, “Car plate number characters recognition using Gabor orientation features and neural networks,” in Proc. The 2003 International Conference on Neural Networks and Signal Processing, vol. 2, pp. 1628-1631, Dec. 2003
[11] X. W. Wang, X. Q. Ding and C. S. Liu, “Optimized Gabor filter based feature extraction for character recognition,” in Proc. 16th International Conference on Pattern Recognition, vol. 4, pp.223-226, Aug. 2002
[12] K. Chao and M. D. Srinath, “Invariant character recognition With Zernike and orthogonal Fourier–Mellin moments,” Pattern Recognition, vol. 35, no. 1, pp. 143-154, January 2002
[13] Y. C. Chim, A. A. Kassim and Y. Ibrahim, “Character recognition using statistical moments,” Image and Vision Computing, vol. 17,no. 3, pp. 299-307, March 1999