臺灣博碩士論文加值系統

在交通工具不斷增加的情況下，衍生出許多問題，車牌不僅是車輛的代表，也可以利用車牌資訊找尋犯罪或違規問題，如失竊和停車問違規等。在本論文中，我們提出多張車牌辨識系統，利用小波轉換用以探討多張車牌辨識系統的應用，提供一個能夠使用照相手機或攝影機等設備來快速查詢車牌資訊。車牌辨識的流程分為三個步驟：分別是車牌定位、字元切割和字元辨識。
在車牌定位，我們先將全彩影像轉換成灰階化影像，利用小波轉換找出灰階化影像的邊界點，並將邊界點的數量先利用水平投影的方式計算邊界點並找出水平位置，接著再利用垂直投影方式找出車牌正確位置。

In case of transportation increased steadily, there are more problems has appear. For example: license plate, it’s not only the representative of automobile but also searching crime or violation issues by using license plate information. For example: stolen cars and violation of parking. In this paper, we provide license plate recognition system by using wavelet transform to investigate the application of license plate recognition system. Also provide equipment that be able to use camera mobile or video camera to search license plate information quickly.
There are three steps of licenses recognition: license plate location, character cutting and character recognition.
In license plate location, we transform full-color image to gray scale first, and using wavelet transform to find the border point of gray scale image. After that, the quantity of border point by using horizontal projection to scale border point and find the horizontal position. And then, by using vertical projection to find the correct position of license plate.
In character cutting and recognition, all the license plates after cutting by using binarization to transfer black and white, after that, by using horizontal and vertical character cutting and normalization the characters to 25*25, and match database with template.

目錄
論文指導教授推薦書
論文口試委員審定書
長庚大學博碩士紙本論文著作授權書 iii
誌謝 iv
摘要 v
Abstract vi
目錄 vii
圖目錄 x
表目錄 xii
第一章 緒論 - 1 -
1.1 研究背景與動機 - 1 -
1.2 研究目的 - 2 -
1.3 系統流程 - 3 -
1.4 論文架構 - 4 -
第二章 文獻探討 - 6 -
2.1 汽機車相關統計 - 6 -
2.2 車牌定位 - 7 -
2.3 文字切割 - 10 -
2.4 文字辨識 - 11 -
2.4.1 類神經網路 - 11 -
2.4.1 樣板比對法 - 13 -
2.4.2 統計分類 - 13 -
第三章 車牌定位 - 15 -
3.1 影像前處理 - 16 -
3.2 小波轉換 - 18 -
3.3 車牌定位 - 21 -
3.3.1 水平投影 - 23 -
3.3.2 垂直投影 - 26 -
第四章 車牌辨識 - 30 -
4.1 影像二值化 - 31 -
4.2 文字分割 - 34 -
4.2.1 分割上下 - 34 -
4.2.2 文字分割 - 36 -
4.3 文字辨識 - 40 -
4.3.1 正規化與樣板建立 - 40 -
4.3.2 樣板比對 - 41 -
第五章 實驗結果 - 43 -
5.1 實驗環境 - 43 -
5.2 車牌定位 - 43 -
5.3 文字分割 - 46 -
5.4 文字辨識 - 49 -
第六章 結論 - 52 -
參考文獻 - 53 -

圖目錄
圖1-1. 系統流程圖 - 4 -
圖2-5. 利用水平與垂直投影照出車牌位置 - 9 -
圖2-6. 小波掃描車牌 - 9 -
圖2-7. 垂直投影切割文字 - 10 -
圖2-8. 水平與垂直投影切割文字 - 11 -
圖2-9. 類神經網路基本架構 - 12 -
圖2-10. 統計式與結構兩階階段混合辨識 - 14 -
圖3-1.車牌定位流程圖 - 16 -
圖3-2.汽車車牌影像(a)(c)位元全彩影像(b)(d)8位元灰階影 - 17 -
圖3-3. 影像示意圖 - 18 -
圖3-4. 灰階值落差示意圖 - 19 -
圖3-5. (a)(c)灰階影像(b)(d)邊界點影像 - 21 -
圖3-6. 簡單車牌示意圖 - 23 -
圖3-8. (a)(c)邊界點(b)(d)超過12以上的邊界點 - 25 -
圖3-9.切割相連最多行數位置 - 25 -
圖3-10. 依字元高度與寬度畫出長方形範圍 - 27 -
圖3-11. (a)(c)車牌定位範圍。(b)(d)切割出車牌 - 28 -
圖3-12. 車牌文字高度 - 28 -
圖3-13. 判斷車牌 - 29 -
圖4-1. 系統辨識流程圖 - 30 -
圖4-2. 二值化示意圖 - 31 -
圖4-3. 全域二值化 - 32 -
圖4-4. 區域二值化 - 32 -
圖4-5. (a)(c)原始車牌影像(b)(d)分段式平均二值化 - 34 -
圖4-6. 分割文字上下 - 36 -
圖4-7. 四連結區塊標記示意圖 - 37 -
圖4-8. 四連結區塊標記過程示意圖 - 38 -
圖4-9. (a) (c)車牌原圖(c) (d)框出車牌文字 - 39 -
圖4-10. 文字分割字母與數字 - 40 -
圖5-1. 汽車車牌定位 - 44 -
圖5-2. 機車車牌定位 - 45 -
圖5-3. 汽車車牌文字分割 - 46 -
圖5-4. 機車車牌分割結果 - 47 -

表目錄
表2-1. 機動車輛登記數(來源:交通部)。 - 6 -
表2-2. 汽、機車竊盜案概況(來源:警政署)。 - 7 -
表5-1. 汽車車牌辨識結果 - 49 -
表5-2. 機車車牌辨識結果 - 50 -

[1]Capar, A. and M. Gokmen, "Concurrent segmentation and recognition withshape-driven fast marching methods," in Proceedings 18th International Conference on Pattern Recognition, Hong Kong, vol.1, pp.155-158, Aug.20-24, 2006.
[2]Parisi, R., Di Claudio, E.D., G. Lucarelli, and G. Orlandi, “Car plate recognition by neural networks and image processing,” in Proceedings of IEEE International Symposium on Circuits and Systems, Monterey, California, vol.3, pp.195-198, May 31-June 3,1998.
[3]Zhang, H., W. Jia, X. He, and Q. Wu, “A fast algorithm for license plate detection in various conditions,” in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Taipei, Taiwan, vol.3,pp.2420-2425, Oct.8-11, 2006.
[4]Rahman, C. A., Badawy, W. and Radmanesh, A. “A real time vehicle's license plate recognition system,” in Proceedings IEEE Conference on Advanced Video and Signal Based Surveillance, Miami, FL,pp.163-166, Jul.21-23, 2003.
[5]Bai, H. and Liu, C. “A hybrid license plate extraction method based on edge statistics and morphology,” in Proceedings 17th IEEE Conference on Pattern Recognition, Hangzhou, China, pp.831-834, Aug.23-26, 2004.
[6]Kamat, V. and Ganesan, S. "An efficient implementation of the Hough transform for detecting vehicle license plates using DSP'S," in Proceedings Conference Real-Time Technology and Application., Chicago, IL,pp.58-59, May 15-17, 1995.
[7]Hegt, H. A., Haye, R. J. and Khan, N. A. “A high performance license plate recognition system,” in Proceedings International Conference on Systems, Man, and Cybernetics, San Diego, CA, pp.4357-4362, Oct.11-14, 1998.
[8]Tsang-Hong Wang, Feng-Chou Ni, Keh-Tsong Li, Yon-Ping Chen, "Robust license plate recognition based on dynamic projection warping," in Proceedings IEEE International Conference Networking Sensing and Control, vol.2, pp.784-788, Sep. 2004
[9]Huaifeng Zhang, Wenjing Jia, Xiangjian He, Qiang Wu, "Learning-based license plate detection using global and local features," in Proceedings 18th International Conference Pattern Recognition, Hong Kong, vol.2, pp.1102-1105, Sep.18, 2006.
[10]YDanian Zheng, Yannan Zhao, Jiaxin Wang, "An efficient method of license plate location," Pattern Recognition Letters, vol.26, no.15, pp.2431-2438, Nov. 2005.
[11]Shi, X., W. Zhao, and Y. Shen, "Automatic license plate recognition system based on color image processing," Computational Science and ITS Applications(ICCSA), vol.3483, pp.1159-1168, 2005.
[12]Broumandnia, A. and M. Fathy, "Application of pattern recognition for farsi license plate recognition," Int. Journal on Graphics, Vision and Image Processing, vol.5, no.2, pp.25-31, Jan. 2005.
[13]Kertesz, A., Kertesz, V. and T. Muller, “An on-line image processing system for registration number identification,” in Proceedings of IEEE International Conference on Neural Networks, Orlando, Florida, vol.6,pp.4145-4148, June 27-29, 1994.
[14]Qian Gao, Xinnian Wang and Gongfu Xie,“License plate recognition based on prior knowledge,” in Proceedings of IEEE International Conference on Automation Logistics, Shandong, China, pp.2964-2968, Aug.18-21, 2007.
[15]Juntanasub, R. and Sureerattanan, N., “Car license plate recognition through hausdorff distance technique,” in Proceedings of IEEE 17th International Conference on Tools with Artificial Intelligence, Hong Kong, China, pp.647-651, Nov.14-16,2005.
[16]Yi Lu, “Machine printed character segmentation - an overview,”Pattern Recognition, vol.28, no.1, pp.67-80, Jan. 1995.
[17]Lee, C.-H., K.-L. You, and Y.-P. Lin, “Dynamic real-time license plate recognition” Journal of Technology, vol.25, no.2, pp.151-165, Jun. 2010.
[18]Pan Xiang, Ye XiuZi and Zhang Sanyuan, "A hybrid method for robust car plate character recognition," in Proceedings International Conference on Systems Man and Cybernetics, Hague, Netherlands, pp.4733-4737, Oct.10-13, 2004.
[19]Lu, Y., "On the segmentation of touching characters," in Proceedings 2nd International Conference on Document Analysis and Recognition, Tsukuba Science City, Japan, pp.440-443, Oct.20-22,1993.
[20]Pu Han, Wei Han, Dong-Feng Wang, Yong-Jie Zhai, "Car license plate feature extraction and recognition based on multi-stage classifier," in Proceedings International Conference on Machine Learning and Cybernetics, Hebei, China, pp.128-132, Nov.2-5, 2003.
[21]Canny, J., "A computational approach to edge detection," IEEE Tran. on Patt. Anal. and Machine Intell., vol. 8, no. 6, pp. 679-698, Jan. 2009.
[22]Yi Lu, "Machine printed character segmentation - an overview, " Pattern Recognition, vol.28, no.1, pp.67-80, Jan. 1995.
[23]Zheng, D., Y. Zhao, and J. Wang, "An efficient method of license plate location, " Pattern Recognition Letters, vol.26, no.15, pp.2431-2438, Nov. 2005.
[24]Hasan, YY, and Karam, LJ, "Morphological text extraction from image, " IEEE Transactions on Image Processing, vol.9, no.11, pp.1978-1983, Nov.2000.
[25]Cheokman Wu, Lei Chan On, Chan Hon Weng, Tong Sio Kuan, Kengchung Ng , "A Macao license plate recognition system," in Proceedings IEEE International Conference on Machine Learning and Cybernetics Vol.7, pp.4506- 4510, Aug. 2005.
[26]Yungang Zhang and Changshui Zhang, "A new algorithm for character segmentation oflicense plate, " in Proceedings IEEE International Conference on Intelligent Vehicles Symposium, pp.106-109, Jun.9-11, 2003.
[27]陳克智，〈照相手機的車牌偵測與辨識〉，國立中央大學，碩士論文，民國100年。
[28]簡維皇，〈用於路口查驗贓車的車牌辨識系統〉，國立中央大學碩士，碩士論文，民國100年。
[29]王中山，〈使用小波轉換於車牌偵測〉，國立中山大學，碩士論文，民國93年06月。