臺灣博碩士論文加值系統

車牌辨識現今已被廣泛應用於高速公路收費系統，停車場管理系統，以及各項交通違規等系統中，可大幅提高效率。然而現行的系統，都為單一系統，即一個攝影機只能辨識一個車道。本論文提出，使用高解析度的攝影機，一個攝影機可同時辨識多個車道的車牌辨識，此方法不但可以大幅降低攝影機的建置成本，也可提高辨識的效率，使之更經濟且效益。因此，本研究包含動態車牌定位演算法與車牌辨識演算法。
首先是車牌定位演算法，本論文中使用車道切割的技術，我們可以使用單一攝影機拍攝出來的多車道影像，經過車道切割的方法，即可將影像切割成多個車道，達成使用單一攝影機同時辨識多車道的目的。我們動態多車道車牌定位成功率為94%。車牌辨識的部份，使用Tesseract-OCR當辨識的核心演算法，加上已訓練的車牌字庫，本論文的辨識系統可應用於多車道車牌辨識上。即一次可同時辨識多個車道的車牌，優於傳統的辨識系統只能應用於單一車道和辨識單一個車牌。我們測試本系統在高速公路多車道的環境中，拍攝行駛中的車輛，並得到了車牌辦識成功率為86％。

License Plate Recognition (LPR) System has now been widely used in highway toll collection, parking management, various traffic regulations enforcement, and other systems. Currently, most of the existing license plate localization systems are with single camera that is limited to recognizing vehicles in one lane. This thesis presents a license plate recognition system that simultaneously recognizes license plates of vehicles on multiple lanes by using single high-resolution camera. Our approach significantly reduces the hardware cost of LPR system without sacrificing the accuracy of recognition. Therefore, the dynamic LPR algorithm and recognition algorithm are included in this study.
First, about the dynamic LPR algorithm of this study, we apply lane separation technique on multi-lane image captured by single camera to separate image into individual lanes which makes possible for one camera to recognize vehicles in multiple lanes. Our success rate is about 94%. Furthermore, we employ Tesseract-OCR as the core engine and the well trained database for the license plates to recognize license plates in our system. Hence, our design makes our system superior to traditional LPR, which can only be used in one single lane to recognize one single license plate. We tested our system on highway to capture images of fast moving vehicles in multiple lanes and got a recognition success rate 86%.

摘 要 I
ABSTRACT II
誌謝 IV
目錄 V
圖目錄 VIII
表目錄 X
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 3
1.3 研究流程 4
1.4 論文架構 4
第二章 相關背景知識與相關文獻介紹 6
2.1 車牌辨識文獻介紹 6
2.1.1 近期文獻探討 6
2.1.2 歷年文獻探討 7
2.2 車體定位的背景知識 10
2.2.1 背景處理 10
2.2.2 圖形切割 11
2.3 車牌定位背景知識 11
2.3.1 色彩轉換 11
2.3.2 直方圖等化 14
2.3.3 邊緣偵測 15
2.3.4 影像二值化 19
2.3.5 影像雜訊處理 20
2.4 字元切割的背景知識 22
2.4.1 投影法 22
2.4.2 水平投影 22
2.4.3 垂直投影 22
2.5 字元辨識的背景知識 23
2.5.1 樣板比對 23
2.5.2 類神經網路 25
2.5.3 光學文字辨識(OCR) 26
2.5.4 三種字元辨識的比較 27
第三章 研究方法與系統架構 28
3.1 系統流程 28
3.2 系統整合 29
3.3 車體定位 29
3.3.1 車體區域定位 29
3.3.2 車道切割 31
3.4 車牌定位 31
3.4.1 影像灰階化 32
3.4.2 直方圖等化 32
3.4.3 邊緣偵測 34
3.4.4 影像二值化 36
3.4.5 車牌區域定位 38
3.5 字元切割 39
3.5.1 水平切割 39
3.5.2 垂直切割 40
3.6 字元辨識 41
3.6.1 尋找線與字 42
3.6.2 識別字元 43
3.6.3 特徵與匹配 43
3.6.4 Trained Image 44
3.6.5 訓練字元 45
第四章 實驗結果 48
4.1 系統條件說明 48
4.2 開發環境 48
4.3 原始圖 49
4.4 車體定位結果 49
4.5 車牌定位結果 50
4.5.1 影像灰階化結果 50
4.5.2 直方圖等化結果 51
4.5.3 邊緣偵測結果 52
4.5.4 影像二值化結果 52
4.5.5 車牌區域定位結果 53
4.6 字元切割結果 54
4.7 字元辨識結果 54
4.8 實驗軟體GUI介面 55
4.9 車牌定位成功率 56
4.10 車牌辨識成功率 58
4.11 系統測試成功範例 61
4.12 系統測試失敗範例 65
第五章 結論 67
5.1 研究成果 67
5.2 本論文和以往研究不同處 67
5.3 未來工作 68
參考文獻 70
附錄A 中英名詞對照表 77
附錄B 完成本論文計畫之重要性 78
附錄C 國內外有關本計畫之研究情況 79
附錄D 完成本論文的研究方法與進行步驟 80
附錄E 完成本論文預期可獲之訓練 81
附錄F 完成本論文預期可獲之成果 82
附錄G 作者簡介 83

[1]M. J. Ahmed, M. Sarfraz, A. Zidouri, and W. G. Al-Khatib, “License plate recognition system,” IEEE International Conference on Electronics, Circuits and Systems, Vol. 2, 2003, pp. 898-901.
[2]黃鍾木，徐世湧，「行動式車牌辨識系統」，中華民國專利公報，公告編號：191905.
[3]A. Taleb-Ahmed, D. Hamad, and G. Tilmant, “Vehicle license plate recognition in marketing application,” 2003 Proceedings of Intelligent Vehicles Symposium, IEEE, 2003, pp. 90-94.
[4]S. L. Chang, L. S. Chen, Y. C. Chung, and S. W. Chen, “Automatic license plate recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol. 5, 2004, pp. 42-53.
[5]C. T. Hsieh, Y. S. Juan, and K. M. Hung, “Multiple license plate detection for complex background,” 2005 Proceedings of International Conference on Advanced Information Networking and Applications, Vol. 2, 2005, pp. 389-392.
[6]D. Wazalwar, E. Oruklu, and J. Saniie, “A Design Flow for Robust License Plate Localization and Recognition in Complex Scenes”, Journal of Transportation Technologies, 2012, pp. 13-21.
[7]S. Himawan, Software design for license plate detection and recognition using Contour Extraction Algorithm and OCR, Binus University, Jakarta, DKI Jakarta, Indonesia, 2012.
[8]W. K. For, K. Leman, H. L. Eng, B. F. Chew, and K. W. Wan, “A Multi-Camera Collaboration Framework for Real-Time Vehicle Detection and License Plate Recognition on Highways,” IEEE Intelligent Vehicles Symposium, 2008, pp. 192-197.
[9]R. T. Lee and K. C. Hung, “Real-Time Vehicle License Plate Recognition Based on 1-D Discrete Periodic Wavelet Transform,” 2012 International Symposium on Computer, Consumer and Control (IS3C), 2012, pp. 914-917.
[10] Y. Wen, Y. Lu, J. Yan, Z. Zhou, K. M. V. Deneen, and P. Shi, “An Algorithm for License Plate Recognition Applied to Intelligent Transportation System,” IEEE Trans. on Intelligent Transportation Systems, Vol. 12, No. 3, 2011, pp. 830-845.
[11]H. R. A. Moghassemi and A. Broumandnia, “Iranian License Plate Recognition using connected component and clustering techniques,” IEEE Transactions. Networked Computing and Advanced Information Management (NCM), 2011, pp. 206-210.
[12]C. N. E. Anagnostopoulos, I. E. Anagnostopoulos, V. Loumos, and E. Kayafas, “A License Plate-Recognition Algorithm for Intelligent Transportation System Applications,” IEEE Transactions on Intelligent Transportation Systems, Vol. 7, Issue 3, 2006, pp. 377-392.
[13]J. W. Hsieh, S. H. Yu, and Y. S. Chen, “Morphology-based License Plate Detection from Complex Scenes,” Yuan Ze University, Department of Electrical Engineering, Taiwan, 2002.
[14]D. S. Gao and J. Zhou, “Car License Plates Detection from Complex Scene,” Signal Processing Proceedings, 2000 WCCC-ICSP, Vol. 2, 2000, pp. 1409-1414.
[15]J. C. H. Poon, M. Ghadiali, G. M. T. Mao, and L. M. Sheung, “A robust vision system for vehicle license plate recognition using grey-scale morphology,” Proceedings of the IEEE International Symposium on Industrial Electronics (ISIE ‘95), Vol. 1, 1995, pp. 394-399.
[16]M. H. ter Brugge, J. H. Stevens, J.A. G. Nijhuis and L. Spaanenburg,“License plate recognition using DTCNNs,” Proc. of 5th IEEE Int.Workshop on Cellular Neural Networks and Their Applications Proceedings, London, UK, 1998, pp. 212-217.
[17]S. Draghici, “A neural network based artificial vision system for license plate recognition,” Int. Journal of Neural Systems, Vol. 8, 1997, pp. 113-126.
[18]S. L. Chang, L. S. Chen, Y. C. Chung, and S. W. Chen, “Automatic license plate recognition,” IEEE Transactions on Intelligent Transportation Systems, Vol. 5, 2004, pp. 42-53.
[19]S. Draghici, “A neural network based artificial vision system for license plate recognition,” Int. Journal of Neural Systems, Vol. 8, No. 1, 1997, pp. 113-126.
[20]S. Kim, D. Kim, Y. Ryu, and G. Kim, “A robust license-plate extraction method under complex image conditions,” 2002 Proceedings of 16th International Conference on Pattern Recognition, Vol. 3, 2002, pp. 216-219.
[21]J. W. Hsieh, S. H. Yu, and Y. S. Chen, “Morphology-based license plate detection from complex scenes,” Proceedings of the 16th International Conference on Pattern Recognition, Vol. 4, 2002, pp. 176-179.
[22]H. Bai, J. Zhu, and C. Liu, “A fast license plate extraction method on complex background,” Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE, Vol. 2, 2003, pp. 985-987.
[23]H. R. Hegt, D. L. Haye, and N. Khan, “A high performance license plate recognition system,” Proc. of IEEE Int. Conf. on Systems, Man, and Cybernetics, Japan, Vol. 5, 1999, pp. 4357-4362.
[24]Y. Lu, “Machine printed character segmentation - an overview,” Pattern Recognition, Vol. 28, No. 1, 1995, pp. 67-80.
[25]R. P. W. Duin and D. M. J. Tax, “Experiments with classifier combining rules”, First International Workshop on Multiple Classifier System, Cagliari, Italy, 2000, pp. 16-29
[26]P. Comelli, P. Ferragina, M. N. Granieri, and F. Stabile, “Optical recognition of motor vehicle license plates,” IEEE Trans. on Vehicular Technology, Vol. 44, No. 4, 1995, pp. 790-799.
[27]R. Parisi, E. D. D. Claudio, G. Lucarelli, and G. Orlandi, “Car plate recognition by neural networks and image processing,” Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, Vol. 3, 1998, pp.195-198.
[28]S. Gendy, C. L. Smith, and S. Lachowicz, “Automatic car registration　plate recognition using fast Hough transform”, The Institute of Electrical and Electronics Engi-neers 31st Annual 1997 International Carnahan Conference on Security Technology, 1997, pp. 209-218.
[29]A. Mutholib, T. S. Gunawan, and M. Kartiwi, “Design and Implementation of Automatic Number Plate Recognition on Android Platform”, International Conference on Computer and Communication Engineering (ICCCE 2012), Kuala Lumpur, Malaysia, 2012, pp. 3-5.
[30]李經寧，即時手勢辨識系統應用於機上盒控制，碩士論文，國立中央大學資訊工程學系，桃園，2009。
[31]M. Sonka, V. Hlavac, and R. Boyle, Image Processing Analysis and Machine Vision, Boston : PWS Publisher, 2008.
[32]鍾國亮，影像處理與電腦視覺，臺灣：東華書局股份有限公司，2002。
[33]J. L. Wu, “An Automatic Enhancement Method for High Contrast Images via Bilateral Filtering”, Journal of Science and Engineering Technology, Vol. 3, No. 3, 2007, pp. 81-87.
[34]陳克智，照相手機的車牌偵測與辨識系統，碩士論文，國立中央大學資訊工程學系，桃園，2011。
[35]二值化，http://blog.csdn.net/rocky69/article/details/7238463
[36]陳光中，即時車牌辨識系統 - 動態影像中有效辨識多個車牌的方法，碩士論文，國立臺北科技大學電資學院電資碩士班，台北，2010。
[37]http://www.cavtc.net/jpkc/site-zhitu/course/02/2-1.htm
[38]簡維皇，用於路口查驗贓車的車牌辨識系統，碩士論文，國立中央大學資訊工程學系，桃園，2011。
[39]葉怡成，類神經網路模式應用與實作，台北：儒林書局，2006。
[40]http://history-computer.com/ModernComputer/Basis/magnetic_drum.html
[41]C. T. Hsieh, Y. S. Juan, and K. M. Hung, “Multiple License Plate Detection for Complex Background”, 19th International Conference on Advanced Information Networking and Applications (AINA 2005), Vol. 2, 2005, pp. 389 - 392.
[42]繆紹綱，數位影像處理，新北：台灣培生教育出版股份有限公司，2003。
[43]Y. K. Kim, J. K. Paik, and B. S. Kang, “Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering,” IEEE Trans. On Consumer Electronics, Vol. 44, No. 1, 1998, pp. 82-86.
[44]徐曉珮，數位影像處理，台北：高立圖書有限公司，2004。
[45]連國珍，數位影像處理，台北：儒林圖書公司，2008。
[46]周世育，非固定大小車牌定位系統，碩士論文，樹德科技大學資訊工程學系，高雄，2008。
[47]N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, 1979, pp. 62-66.
[48]繆紹綱，數位影像處理－活用Matlab，台北：全華圖書股份有限公司，2011。
[49]魏銪志，動態多標的車牌辨識系統之研究，碩士論文，元智大學資訊工程研究所，桃園，2000。
[50]Y. Yasuharu, M. Goto, D. Nishiyama, M. Soga, H. Nakatani, and H. Saji, “Extraction and Tracking of the License Plate using Hough Transform and Voted Block Matching,” Proceedings of IEEE Intelligent Vehicles Symposium, 2003, pp. 243-246.
[51]陳伯岳、 梁忠瑋、蔡銘鑫，「一個抗背景雜訊的車牌定位技術」，離島資訊技術與應用研討會，2003，pp. 445-451。
[52]R. Smith, “An overview of the Tesseract OCR engine,” Proceedings of the Ninth International Conference on Document Analysis and Recognition, Vol. 2, 2007, pp. 629-633.
[53]R. Smith, D. Antonova, and D. S. Lee, “Adapting the Tesseract open source OCR engine for multilingual OCR,” The Proceedings of the International Workshop on Multilingual OCR, 2009, pp. 1-8.
[54]P. Chirag, P. Atul, and P. Dharmendra, “Optical Character Recognition by Open Source OCR Tool Tesseract: A Case Study,” International Journal of Computer Applications, Vol. 55, No. 10, 2012, pp. 50-56.
[55]M. Nitin, C. Patvardhan, C. V. Lakshmi, and S. Singh, “Shirorekha Chopping Integrated Tesseract OCR Engine for Enhanced Hindi Language Recognition,” International Journal of Computer Applications, Vol. 39, No. 6, 2012, pp.19-23.
[56]M. A. Hasnat, M. R. Chowdhury, and M. Khan, “Integrating Bangla script recognition support in Tesseract OCR,” Proc. of Conference on Language and Technology 2009 (CLT09), Lahore, Pakistan, 2009.
[57]Tesseract-OCR , URL: http://code.google.com/p/tesseract-ocr/
[58]A. Tiwari and H. Ghosh, “Ticker text extraction from Bangla news videos,” Annual IEEE India Conference, 2010, pp. 1-4.
[59]P. J. Schneider, “An Algorithm for Automatically Fitting Digitized Curves,” in A.S. Glassner, Graphics Gems I, Morgan Kaufmann, 1990, pp. 612-626.
[60]D. Yamakawa and N. Yoshiura, “Applying Tesseract-OCR to Detection of Image Spam Mails,” Network Operations and Management Symposium (APNOMS), 2012 14th Asia-Pacific, 2012, pp. 1-4.