臺灣博碩士論文加值系統

隨著經濟活動的蓬勃發展，交通建設日趨完善，使得國民擁有的車輛數目大幅提升，衍生出的交通管理問題也相對增加。以往的車牌追蹤以及辨識，必須以人工方式在眾多的視訊影像中找尋目標，不僅費時也相當費力，因此本研究藉由模擬人腦智能之方式，透過連續的視訊影像畫面分析自動對目標車牌進行定位追蹤與辨識，以提升整體辨識效果。
本研究透過連續的視訊畫面對車牌進行追蹤辨識，由於採用固定式攝影機，因此在前景物體偵測方面使用背景相減法來偵測出前景物體，再透過Sobel邊緣點偵測以及霍夫直線轉換定位出車牌位置，在完成車牌定位之後對車牌進行特徵抽取，在車牌追蹤部分，以一開始定位之車牌位置為中心向外擴大範圍，搜索車牌在下一張影像中的位置，同時找出車牌移動之方向，其後追蹤便以該方向定義為追蹤範圍的依據，提升車牌追蹤準確率。在辨識的過程中，本研究加入了特定字集的辨識核心以及特定字串的檢索機制，透過特定字集的辨識核心技術，能夠有效的減少辨識的時間，並且提升辨識準確度；而特定字串的車牌檢索機制，則是用於找尋特定車牌的快速搜尋方法，利用此兩種方法來有效的提升整體辨識效率。實驗結果在導入特定字集辨識核心之後，其辨識準確率能夠達到96.4%，而時間的花費上也能夠節省達26%，證明本研究所提方法能確實提升辨識準確度且能夠減少辨識時所花費之時間。

As economic activity to flourish and traffic's complete, people have more car than before. Therefore, traffic management becomes more important. In before, traffic monitoring was using people watching video. It is very waste time and human. So our proposed a new approach to improve this status.
Our tracking and recognition license plate using the sequential video images. First, our using background subtraction to detection foreground objects. Second, our using Sobel edge detection to finding foreground objects edge. Finally, using Hough transform to location the license plate. After license plate location, our extract features for tracking. Our tracking’s approach is using the license plates locations range extend double to finding license plate location in the next image. By using this approach we can get the license plates moving direction. Another, we propose an approach of license plate recognition. Our propose a specific character set recognitions core join to the recognition system, and we also propose a specific strings search mechanism for license plates search. Our using by those, specific character set recognitions core and specific strings search mechanism, to improvement license plates recognition accuracy and its search speed.

中文摘要 ．．．．．．．．．．．．．．．．．．．．．．iii
英文摘要 ．．．．．．．．．．．．．．．．．．．．．．iv
致謝辭 ．．．．．．．．．．．．．．．．．．．．．．．v
內容目錄 ．．．．．．．．．．．．．．．．．．．．．．vi
表目錄 ．．．．．．．．．．．．．．．．．．．．．．．viii
圖目錄 ．．．．．．．．．．．．．．．．．．．．．．．ix
第一章 緒論．．．．．．．．．．．．．．．．．．．．．1
　第一節 研究背景與動機．．．．．．．．．．．．．．．1
　第二節 研究目的．．．．．．．．．．．．．．．．．．3
　第三節 系統流程．．．．．．．．．．．．．．．．．．4
　第四節 研究範圍與限制．．．．．．．．．．．．．．．4
　第五節 論文架構．．．．．．．．．．．．．．．．．．5
第二章 文獻探討．．．．．．．．．．．．．．．．．．．6
　第一節 移動物體偵測與追蹤．．．．．．．．．．．．．6
　第二節 車牌定位．．．．．．．．．．．．．．．．．．9
　第三節 車牌文字辨識．．．．．．．．．．．．．．．．12
第三章 移動車輛之車牌定位與追蹤．．．．．．．．．．．16
　第一節 移動車輛物體之偵測與判定．．．．．．．．．．16
　第二節 連續畫面之車牌定位．．．．．．．．．．．．．21
　第三節 移動車輛之車牌追蹤．．．．．．．．．．．．．25
第四章 視訊畫面車牌辨識之準確度提升．．．．．．．．．27
　第一節 特定字集之車牌辨識核心．．．．．．．．．．．27
　第二節 特定字串之車牌檢索機制．．．．．．．．．．．33
　第三節 連續畫面車牌辨識之整體效能提升．．．．．．．35
第五章 實驗結果與討論．．．．．．．．．．．．．．．．38
第六章 結論．．．．．．．．．．．．．．．．．．．．．41
參考文獻 ．．．．．．．．．．．．．．．．．．．．．．42

一、 中文部分
交通部統計處。機動車輛登記數。2012年1月15日，取自：http://www.motc.gov.tw/mocwebGIP/wSite/public/Attachment/f1326673691586.xlsf

二、 英文部分
Anitha, M., Bhargavi, R. (2011). “Accurate License Plate Localization,” International Conference on Computer, Communication & Electrical Technology – ICCCET2011, 18th & 19th

Antonini, M., Barlaud, M., Mathieu, P. and Daubechies, I. (1992). “Image Coding Using Wavelet Transform,” IEEE Trans on Image Processing, vol. 1, no. 2, April.

Ashtari, A.H., Nordin, M.J., Kahaki, S.M.M. (2011). “A New Reliable Approach for Persian License Plate Detection on Colour Images,” International Conference on Electrical Engineering and Informatics July 17-19 pp.1-5.

Bernsen, J. (1986), “Dynamic thresholding of grey-level images,” in Proc. 18th Int. Conf. Pattern Recognition, Paris, pp.1251-1255.

Chao, K., Srinath, M.D. (2002). “Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments,” Pattern Recognition, vol. 35, no.1, pp. 143-154, January.

Chen, Z.X., Liu, C.Y., Chang, F.L., and Wang, G.Y. (2009). “Automatic License-Plate Location and Recognition Based on Feature Salience,” IEEE Transactions on Vehicula Technology, vol. 58, no. 7, September.

Chen, B., Cao, W., Zhang, H. (2008). “An Efficient Algorithm on Vehicle License Plate Location ,” Proceedings of the IEEE International Conference on Automation and Logistics Qingdao, China

Chen, Z., Wang, G., Liu, J. and Liu, C. (2009). “Automatic License Plate Location and Recognition Based on Feature Salience,” International Journal of Computational Cognition (http://www.ijcc.us), vol. 5, no. 2, June.

Cheokman, W., Lei, C.O., Chan, H.W., Tong, S.K., Kengchung, N. (2005). “A Macao License Plate Recognition System,” Int. Conf. on Machine Learning and Cybernetics, vol. 7, pp.4506-4510.

Chim, Y.C., Kassim, A.A, Ibrahim, Y. (1999). “character recognition using statistical moments,” Image and Vision Computing, vol. 17, no. 3, pp. 299-307, March.

Comelli, P., Ferragina, P., Granieri, M.N., Stabile, F. (1995). “Optical Recognition of Motor Vehicle License Plates,” IEEE Trans. on Vehicular Technology, vol. 44, pp. 790-799.

Glauberman, M.H. (1956). “Character recognition for business machines,” Proc. IEEE 80, 1066-1078, July.

Hegt, H.A., Haye, R.J.D.L., Khan, N.A. (1998). ”A High Performance License Plate Recognition System” IEEE International Conference on Systems, Man and Cybernetics, pp. 4357-4362, San Diego, California, USA, 11-14 October.

Huang, Y.P., Lai, S.Y., Chuang, W.P. (2004). “A Template-based Model for License Plate Recognition,” IEEE Int. Conf. on Networking, Sensing and Control, vol. 2, pp. 737-742.

Junga, K., Kimb, K.I., Jainc, A.K. (2004). “Text Information Extraction in Images Andvid eo: A Survey,” Pattern Recognition 37, 977–997.

Khotanzad, A., Hong, Y.H. (1990). “Invariant image recognition by Zernike moments,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 12, Page(s):489-497, May.

Li, X., Zhang, L., Dong, H., Xu, J. (2010). “ Comparative Study on Wavelet Transform and Traditional Image Processing,” Information Sciences and Interaction Sciences (ICIS), pp. 13-17.

Lin, C.S., Wu, W.Z., Lay, Y.L., Chang, M.W. (2001). “A digital image-based measurement system for a LCD backlight odule” Optics & Laser Technology, Vol.33, pp.499–505.

Lu, Y. (1995). “Machine printed character segmentation an overview,” Pattern Recognition, vol. 28, no.1, 67-80.
Lu, Y. and SHRIDHAR, M. (1996) “Character Segmentation in Handwritten Words--An Overview,” Pattern Recognition, Vol. 29, No. 1, pp. 77-96.

Mallat, S.G. (1989). “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,” IEEE Trans. On PAMI, vol. 11, no. 7, pp. 674-693, July.

Nukano, T., Fukumi, M., Khalid, M. (2004). “Vehicle license plate character recognition by neural networks,” Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems, pp.771-775.

Paeisi, R., Claudio, E.D.D., Lucarelli, G., Orlandi, G. (1998). “Car plate recognition by neural networks and image processing,” Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, vol. 3, pp.195-198.

Qin, Z., Shi, S., Xu, J. and Fu, H. (2006). “Method of License Plate Location Based on Corner Feature,” Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21 - 23, Dalian, China

Tseng, Y.H., Kuo, C.C. and Lee, H.J. (1997). “Speeding Up Chinese Character Recognition in An Automatic Sutomatic Document Reading System,” Pattern Recognition, vol.31, no.11, 1601-1612.

Wu, M.K., Wei, L.S., Shih, H.C., Ho, C.C. (2009).“License Plate Detection Based on 2-Level 2D Haar Wavelet Transform and Edge Density Verification,” IEEE International Symposium on Industrial Electronics July 5-8 pp. 1699-1704.

Ymaguchi, J.I., Kita, T., Ishihara, Y. (2008). “Detection of License Plate Using Matched Filter,” Electronics and Communications in Japan, Vol. 91, No. 9.