摘 要
本研究主要在探討正交軸投影法(orthogonal projection)與樹狀決策(tree decision)作為汽車牌照辨識中的應用。汽車牌照辨識系統在停車場管理與安全區域車輛進出管制和警察單位執法等方面的應用可以有效節省人力與資源。本研究利用正交軸投影與字元輪廓型態和投影剖面特徵等決策歸類作為牌照字元辨識的主軸。本文分為主要的幾個部分，第一個部分是影像中汽車牌照的定位，第二個部分是牌照中字元的偵測與分割，第三個部分是牌照字元的辨識。而字元辨識的部分是本論文的中心，探討利用字元的垂直與水平方向的灰階投影所呈現的數值分佈，作為比較的基礎。在經過歸一化後，每一個待測字元將與標準字元作比較，計算其累計差異值(cumulative difference values, CDV)並由累計差值的大小作為字元辨識的依據。為提高辨識的正確率，根據字元的輪廓特徵與投影剖面的差異，訂定判別分類的決策，作為累計差值法的輔助辨識方法。在59組影像中，成功定位出牌照並判讀成功的比率為86.44%。在312個字元中，利用正交軸投影與樹狀決策作為字元辨識方法的辨識率為99.68%

關鍵詞：汽車牌照辨識、字元辨識、字元分割、正交軸投影法、累計差值比較法、樹狀決策。

Abstract
Our purpose of this research is to utilize the measures of orthogonal projection and tree decisions on vehicle license plate recognition (LPR). Our research uses orthogonal projection as the core of character recognition. In order to raise the recognition rate, tree decisions based on features of character contours and projection profiles are employed. This thesis consists of three main parts. The first part is to locate the license plate in an image. The second part is to detect and segment each character of the license plate. The third part is on character recognition of license plates. Character recognition is more concerned in our research. Horizontal and vertical projections on orthogonal axes are adopted as comparisons between input characters and standard ones. An argument called cumulative difference values (CDV) is introduced to give a solution from standard database. Tree decisions are added to assist in distinguishing characters. The recognition rate from 59 images is 86.44%, and the recognition rate of 312 characters is 99.68%.

Keywords: license plate recognition, LPR, optical character recognition (OCR), character segmentation, orthogonal projection, cumulative difference values (CDV), tree decisions.

參考文獻
1. R.C. Gonzalez, R. E. Woods, Digital Image Processing, MA,
Adsison - Wesley, 1993.
2. W. K. Pratt, Digital Image Processing, John-Wiley & Sons,
1991.
3. M. Rafael, Application of Machine Vision to Traffic
Monitoring and Control, IEEE Vehicular Technology, 38, 112-
122, 1989.
4. K. Yamada, T. Nakano, S. Yamamoto, A Vision Sensor Having an
Expanded Dynamic Range for Autonomous Vehicles, IEEE Trans.
Vehicular Technology, 47, 332-341, 1998.
5. S. G. Chamberlain, J. P. Y. Lee, A Novel Wide Dynamic Range
Silicon Photodetector and Linear Imaging Array, IEEE Trans.
Electron Devices, ED-31, 175-182, 1984.
6. G. Auty et al., An Image Acquisition System for Traffic
Application, Proc. SPIE, 2416, 119-133, 1995.
7. M. Takatoo et al., Gray Scale Image Processing Technology
applied to Vehicle License Number Recognition System, Proc.
IEEE Int. Workshop Industrial Applications of Machine Vision
and Machine Intelligence, 76-79, 1987.
8. Y. Cui, Q. Huang, Automatic License Extraction from Moving
Vehicles, Proc. Int. Conf. Image Processing, 126-129, 1997.
9. P. Comelli, P. Ferragina, M. N. Granieri, F. Stabile,
Optical Recognition of Motor Vehicle License Plates, IEEE
Trans. Vehicular Technology, 44, 1995.
10. Q. D. Trier, A. K. Jain, T. Taxt, Feature Extraction
Methods for Character Recognition---A Survey, Pattern
Recognition, 29, 641-662, 1996.
11. Y. Lu, M. Shridhar, Character Segmentation in Handwritten
Words---An Overview, Pattern Recognition, 29, 77-96, 1996.
12. D. Cheng, H. Yan, Recognition of Handwritten Digits based
on Contour Information, Pattern Recognition, 31, 235-255,
1998.
13. G. Iannizzoto, L. Vita, Fast and Accurate Edge-Based
Segmentation with No Contour Smoothing in 2-D Real Images,
IEEE Trans. Image Processing, 9, 1232-1237, 2000.
14. S. W. Lee, D. J. Lee, H. S. Park, A New Methodology for
Gray-Scale Character Segmentation and Recognition, IEEE
Trans. Pattern Analysis and Machine Intelligence, 18, 1045-
1050, 1996.
15. Y. Lu, Machine Printed Character Segmentation---An
Overview, Pattern Recognition, 28, 67-80, 1995.
16. H. Al-Yousefi, S. S. Udpa, Recognition of Arabic
Characters, IEEE Trans. Pattern Analysis and Machine
Intelligence, 14, 853-857, 1992.
17. R. G. Casey, E. Lecolinet, A Survey of Methods Strategies
in Character Segmentation, IEEE Trans. Pattern Analysis and
Machine Intelligence, 18, 690-706, 1996.
18. T. Naito, T. Tsukada, K. Yamada, K. Kozuka, S. Yamamoto,
Robust License-Plate Recognition Method for Passing Vehicles
Under Outside Environment, IEEE Trans. Vehicular Technology,
49, 2309-2319, 2000.
19. B. Hussain, M. R. Kabuka, A Novel Features Recognition
Neural Network and its Applications to Character
Recognition, IEEE Trans. Pattern Analysis and Machine
Intelligence, 16, 98-106, 1994.
20. P. Morns, S. Dlay, Character Recognition Using Fourier
Descriptors And A New Form of Dynamic Semi-supervised Neural
Network, Microelectronic Journal, 28, 73-84, 1997.
21. W. A. Gowan, Optical Character Recognition Using Fuzzy
Logic, Microprocessors and Microsystems, 423-434, 1995.
22. J. W. T. Walsh, Photometry, Dover, New York, 1958.
23. M. S. Kiver, Color Television Fundamentals, Mcgraw-Hill,
New York, 1965.
24. 吳成柯、戴善榮、程湘君、雲立實，數位影像處理（譯），儒林，台
北，1996。
25. A. Rosenfeld, A. C. KaK, Digital Picture Processing, New
York, 1983.
26. A. K. Jain, Fundamentals of Digital Image Processing,
Prentice-Hall, New Jersey, 1989.
27. Hi Tech Solutions OCR Products Ltd., Rishon Le-Zion,
Israel, http://www.htsol.com/
28. Perceptics Ltd., Tennessee, USA, http://www.perceptics.com/
29. Zamir Recognition System Ltd., Jerusalem, Israel,
http://www.zamir.com/
30. W. N. Lie, Automatic Target Segmentation by Locally
Adaptive Image Thresholding, IEEE Trans. Image Processing,
4, 1036-1041, 1995.