車牌辨識系統在車輛監控與管理的應用上已非常廣泛，其中車牌定位系統是一個非常重要且關鍵的系統。目前大多數的車牌定位系統只適用於無歪斜情況發生的車牌影像，而在處理具有歪斜情況發生的車牌影像時，由於車牌歪斜角度所造成車牌長寬比例的改變，使得目前以車牌外型為基礎的車牌定位系統無法正確定位出車牌或是造成定位失敗的情況。
快速廣義霍夫轉換法(Fast generalized Hough transform)使用投票程序，可偵測影像平面中任意形狀之物件的縮放、旋轉參數與位置參數，本論文應用快速廣義霍夫轉換法並結合三維空間座標轉換法，使快速廣義霍夫轉換法具備偵測歪斜角度參數的能力，並正確偵測出歪斜車牌於影像平面中的長寬比例(水平與垂直方向之縮放倍率參數)與車牌位置(水平與垂直方向之位置參數)，利用前述的參數，可以定位出歪斜車牌。實驗結果顯示，在水平掃描時，可以同時掃瞄到車牌左緣及右緣的情況下，本論文研究可正確偵測車牌於影像平面中的歪斜角度，並獲得其長寬比例，以達到定位歪斜車牌之目的。

License plate locate system plays an important role in the intelligent transportation systems. Most of license plate locate systems can deal with the situation when the license plate image is taken from license plate’s front. However, if the license plate has a skew angle in the image, the shape of license plate will change. This kind of change brought most of license plate locate systems can not locate the license plate correctly.
Fast generalized Hough transform apply the voting process to detect arbitrary shape’s scale, rotation, and shift parameters in the image. This paper combine the fast generalized Hough transform with 3D coordinate transformation to detect the skew angle of the plate, the ratio of the shape-changed plate (in vertical and horizontal direction), and the location of the plate. The effectiveness of the propose method has been confirmed by some actual images taken by a normal digital camera.

[1]Zheng, D., Zhao, Y., Wang, J., “An efficient method of license plate location,” Pattern Recognition Letters, Vol. 26, No. 15, pp. 2431-2438 (2005).
[2]Zhang, H., Jia, W., He, X., Wu, Q., “A fast algorithm for license plate detection in various conditions,” Conference Proceedings - IEEE International Conference on Systems, Taipei, Taiwan, pp. 2420-2425 (2007).
[3]Qin, Z., Shi, S., Xu, J., Fu, H., “Method of license plate location based on corner feature,” Proceedings of the World Congress on Intelligent Control and Automation (WCICA), Dalian, China, pp. 8645-8649 (2006).
[4]Haibin, H., Guangfu, M., Yufei, Z., “Vehicle license plate location based on Harris corner detection,” Proceedings of the International Joint Conference on Neural Networks, Harbin, China, pp. 352-355 (2008).
[5]陳翔傑，「自動化車牌辨識系統設計」，碩士論文，國立中央大學，桃園(2005)。
[6]林泰良，「智慧型車牌定位與字串分割」，碩士論文，國立台灣大學，台北(2000)。
[7]吳孟聰，「車輛牌照自動辨識系統」，碩士論文，淡江大學，台北(1998)。
[8]林欣平，「車牌字元粹取」，碩士論文，國立交通大學，新竹(1999)。
[9]周俊男，「車輛牌照影像辨識系統」，碩士論文，國立中山大學，高雄(1995)。
[10]Jung, C.R., Schramm, R., “Rectangle detection based on a windowed Hough transform,” Brazilian Symposium of Computer Graphic and Image Processing, Brazil, pp. 113-120 (2004).
[11]Duda, R. O., Hart, P.E., “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Comm. ACM, Vol. 15, pp. 11-15 (1972).
[12]賴幼仙，「任意角度車牌之辨認」，碩士論文，國立交通大學，新竹(1992)。
[13]Hough, P. V. C., “A method and means for recognizing complex patterns,” U.S. Patent 3969654, (1962).
[14]Ballard, D. H., “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, Vol. 13, No. 2, pp. 111-122 (1981).
[15]Aguado, A. S., Montiel, E. and Nixon, M. S., “Invariant characterization of the Hough transform for pose estimation of arbitrary shapes,” Pattern Recognition, Vol. 35, No. 5, pp. 1083-1097 (2002).
[16]Ping Fu, F., Wing Sze, L., “Randomized Generalized Hough Transform for 2-D grayscale object detection,” International Conference of Pattern Recognition, Vienna, Austria, pp. 511-515 (1996).
[17]Chau, C. P. and Siu, W. C., “Generalized dual-point Hough transform for object recognition,” IEEE International Conference on Image Processing, Kobe, Jpn, pp. 560-564 (1999).
[18]Chau, C. P. and Siu, W. C., “Adaptive dual-point Hough transform for object recognition,” Computer Vision and Image Understanding, Vol. 96, No. 1, pp. 1-16 (2004).
[19]Suetake, N., Uchino, E., “Generalized fuzzy Hough transform for detecting arbitrary shapes in a vague and noisy image,” Soft Computing, Vol. 10, No. 12, pp. 1161-1168 (2006).
[20]鍾國亮，影像處理與電腦視覺，東華書局，台北，(2002)。
[21]Otsu, N., “A threshold selection method from gray level Histogram,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 62-66 (1978).
[22]Cherist, M., Said, J. N., and Suen, C. Y., “A recursive thresholding technique for image segmentation,” IEEE Trans. on Image Processing, Vol. 7, No. 6, pp. 918-921 (1998).
[23]Du, Y., Chang, C. I., and Thouin, P. D., “An unsupervised approach to color video thresholding,” Proc. of International Conference on Multimedia and Expo, Hong Kong, Vol. 3, pp. 337-340 (2003).
[24]Jain, R., Kasturi, R. and Schunck, B. G., Machine Vision, McGRAW-HILL Internation Editions, New York, (1995).
[25]Gonzalez, R. C. and Woods, R. E., Digital Image Processing, Addison Wesley, New York, (1992).
[26]Rosenfeld, A. and Kak, A. C., Digital Picture Processing, Vol.2, 2nd Edition, Academic Press, New York, (1983).
[27]Wen, C. Y., Yu, C. C., Hun, Z. D., “A 3-D transformation to improve the legibility of license plate numbers,” Journal of Forensic Sciences, Vol. 47, No. 3, pp. 578-585 (2002).
[28]Kimura, A., Watanabe, T., “Fast generalized Hough transform : rotation, scale and translation invariant detection of arbitrary shapes,” Trans IEICE, Vol. J81-D-II,N0. 4, pp. 726-734 (1998).
[29]Berthouex, P. M. and Brown, L. C., Statistics for Environmental Engineers, LEWIS Lublishers, New York, (2002).