對於層出不窮的汽機車偷竊案件已成現今重要的議題，警方也針對這些議題提出了相關處理辦法，為了使警方能更有效率及便利性來偵辦失竊問題，本研究提出基於影像處理及電腦視覺技術的自動贓車偵測系統，其結合了智慧型手機應用、車牌辨識系統以及智慧查詢贓車資料庫等等，這將改善警方目前以人力手動輸入車牌號碼的方式，減輕人力的負擔及減少操作時的疏失，並結合現有網路系統，提供即時更新的能力。
　　本研究利用搭載Android系統的智慧型手機取代利用行動電腦手動輸入車牌的方式，由於現在的智慧型手機相當地普及且方便又多功能，使用者不須再手動一台一台輸入車牌號碼，只需要將手機掃過停在停車場的靜態汽機車車牌，便能將所擷取到的影像透過無線網路傳回伺服器端做贓車偵測。伺服器端首先對傳來的影像進行車牌辨識，接著再利用具有容錯功能的智慧查詢系統進行贓車資料庫的比對，此智慧查詢系統是基於馬可夫編輯距離計算出與車牌辨識結果最相似的贓車號碼，經使用者確認兩者號碼相符後，再將贓車資訊包含贓車影像、贓車號碼、時間、地點以及贓車所在地之Google Map傳送至偵辦中心以利警員處理。
　　本研究是架構於Model-View-Controller（MVC）的設計模式上，使整個系統更有效率與效能，除此之外民眾也可以從Google Play商店免費下載本研究之APP，達到全民抓贓車之精神。

　　Stolen vehicle detection has become an important task for police officers in many countries. In order to make investigating and seizing the stolen vehicles more convenient and efficient, we propose a smartphone-based automatic stolen vehicle detection system based on image processing and computer vision technologies, combining with license plate recognition (LPR) and fault-tolerant retrieval techniques. The proposed system will improve efficiency of investigation and reduce the burden of human operation.
　　In this study, we utilize the smartphone equipped with Android operating system instead of personal digital assistant (PDA) because the smartphones are more and more popular and powerful. We just scan and capture images of the static vehicles on the roadside by using cell phone camera instead of manually inputting the license numbers one by one. Next, the captured images are sending to the server via wireless network, and then the license plate numbers can be obtained based on the LPR procedure. After finishing this procedure, the system will use the fault-tolerant retrieval technique based on Markov edit distance to retrieve the license numbers of stolen vehicles in database even though the LPR result are imperfect. Finally, the server will send the stolen vehicle information to the smartphone for user confirmation. If the matching is correct, the user can press “Confirm” button to send the image, license number, time, location and Google Map to the police center.
　　The proposed system is developed based on Model-View-Controller (MVC) design pattern. It will make system more efficiency and better performance. In addition, people can download the APP to help the police with stolen vehicle detection.

[Cha 09] S.L. Chang, “Intelligent Parking Lot System: License Plate Recognition, Vehicle Guidance, and Device Control Subsystems,” Jul. 2009.

[Che 96] S.W. Chen, G.C. Stockman, and K.E. Chang, “SO Dynamic Deformation for Building of 3-D models,” IEEE Trans. Neural Networks, vol. 7, pp. 374-387, Jun. 1996.

[Don 04] Z.P. Dong, “Retrieval of Vehicle License Number from a Database Using Imperfect Input,” Dec. 2004.

[Fou 03] C. Fouard, “Automatic calculation of chamfer mask coefficients for large masks and anisotropic images,” INRIA, pp. 7-10, 2003.

[Gao 07] Q. Gao, X. Wang and G. Xie, “License Plate Recognition Based On Prior Knowledge,” IEEE Int’l Conf. on Automation and Logistics, pp. 2964-2968, Aug. 2007.

[Gar 03] J. R. Garitagoitia, J. R. G. de Mendivil, J. Echanobe, J. J. Astrain, and F. Farina, “Deformed Fuzzy Automata for Correcting Imperfect Strings of Fuzzy Symbols”, IEEE Transactions on Fuzzy Systems, Vol. 11, No. 3, pp. 299-310, Jun. 2003.

[Gua 08] J. M. Guo, and Y. F Liu “License Plate Localization and Character Segmentation With Feedback Self-Learning and Hybrid Binarization Techniques,” IEEE Trans. on Vehicular Technology, Vol. 57, No. 3, pp. 1417-1424, May 2008.

[Kel 94] J.M. Keller and R. Krishnapuram, “Fuzzy Decision Models in Computer Vision,” Fuzzy Sets, Neural Networks, and Soft Computing, R.R. Yager and L.A. Zadeh, Eds. New York: Van Nostrand, pp.213-232, 1994.

[Koh 89] T. Kohonen, Self-Organization and Associative Memory. New York: Springer-Verlag, 1989.

[Lai 11] G.H. Lai,“A Study of Applying Smart Phone to The Client-Server Architecture — Using the Stolen Vehicle Investigation System as an example,” Sep. 2011.

[Nak 79] Y. Nakagawa and A. Rosenfeld, “Some Experiments on Variable Thresholding,” Pattern Recognition, Vol. 11, No. 3, pp. 191-204, 1979.

[Qin 06] Z. Qin, S. Shi, J. Xu, and H. Fu, “Method of License Plate Location Based on Corner Feature,” IEEE Congress on World Congress on Intelligent Control and Automation, pp. 8645-8649, Jun. 2006.

[Ree 09] T. Reenskaug, J. Colipen, “The DCI Architecture: A New Vision of Object-Oriented Programming,” Mar. 2009.

[Tan 05] S. T. Tang and W. J. Li, “Number and Letter Character Recognition of Vehicle License Plate Based on Edge Hausdorff Distance,” IEEE 6th Int’l Conf. on Parallel and Distributed Computing, pp. 850-852, Dec. 2005.

[Tsa 85] W.-H. Tsai, S.-S. Yu, “Attributed String Matching with Merging for Shape Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 2, pp. 180-185, Jul. 1993.

[Wei 04] J. Wei, “Markov Edit Distance”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 26, No. 3, pp. 311-321, Mar. 2004.

[Zha 06] H. Zhang and W. Jia, “A Fast Algorithm for License Plate Detection in Various Conditions,” IEEE Int’l Conf. on Systems, Man, and Cybernetics, pp. 2420-2425, Oct. 2006.

[Zhe 05] D. Zheng, Y. Zhao, and J. Wang, “An Efficient Method of License Plate Location,”Vol. 26, pp. 2431-2438, Nov. 2005.

[Zhe 11] G.C. Zheng, W.D. He, and T.Y. Huang, “License Plate Database Query System Based on Cloud Computing Services,” Jul. 2011.

[Ref 01] WeOCR Project Home, URL: http://weocr.ocrgrid.org/

[Ref 02] Java Servlet of Wikipedia, URL: http://zh.wikipedia.org/wiki/Java_Servlet