臺灣博碩士論文加值系統

車牌辨識技術的相關研究與應用已經行之有年，然而在實際應用上，由於複雜的背景、光影與偏角等外在因素的干擾，往往會使車牌辨識系統的偵測率下降，更遑論後續的字元辨識率了。這也就是為什麼許多車牌辨識系統必須建立在特定的環境之下，具體地說，車牌辨識流程中最關鍵的步驟是車牌定位。。
一般來說，車牌區域的偵測往往都是利用車牌字元所具備的強烈垂直邊緣這項特徵，然而外在的環境往往會有許多背景與車牌一樣擁有強烈的垂直邊緣特徵。本論文聚焦於提高車牌區域與非車牌區域在垂直邊緣特徵上的差異化。也就是將車牌區域的垂直邊緣強化，而非車牌區域的垂直邊緣弱化，例如：水箱罩密集的垂直邊緣就必須弱化。因此提出了Wiener deconvolution去模糊化方法來強化且增加車牌區域的垂直邊緣特徵，然後再利用二階二維離散小波轉換來進行垂直邊緣的投影統計，並配合Otsu最佳閥值分割、數學型態學以及邊緣密度驗證法來偵測車牌的位置。從實驗結果可以發現，經由Wiener deconvolution垂直邊緣強化後，可以提升車牌區域垂直邊緣的密度與強度，並且大幅地提升車牌偵測的準確率。一旦把車牌候選區域擷取出來後，就可以利用Tesseract OCR字元辨識軟體來辨識車牌字元。另一方面，本論文也實作了具備Wiener-like簡化版垂直邊緣強化方法的車牌辨識系統於Android嵌入式平台上。實作結果證明Wiener-like簡化版垂直邊緣強化方法是有效且可行的。

Related researches and applications of License Plate Recognition (LPR) have been proceeding for decades. But, in practice, the license plate detection rate is usually error-prone to various backgrounds, illuminations, or skews. So is the subsequent character recognition rate. This is why most of the license plate recognition system just can work well under specific circumstances. Specifically, License plate detection is the fundamental step in LPR.
In general, the license plate region is usually detected by the strong vertical edge feature of its interior characters. However, in the external environment, many backgrounds always have strong vertical edges as the license plate. This paper focuses on enlarging the vertical edge differentation between the license plate region and the non-plate region, that is, focuses on enhancing the vertical edge density and strength of the license plate region and weakening those of the non-plate region, e.g. weakening those of the grille. Therefore, the deblurred method of Wiener deconvolution is proposed to enhance and increase the vertical edges of the license plate. Then, 2-level 2D Discrete Wavelet Transform (DWT) is adopted to run the projection histogram of vertical edges. Furthermore, with the first-order local recursive Otsu segmentation, mathematical morphology, and edge density verification method, the license plate region can be detected smoothly. Experimental results show LPD system based on the proposed Wiener-deconvolution vertical edge enhancement method and 2-level 2D DWT, can achieve a much higher hit rate. After extracting the license plate region smoothly, the optical character recognition library of Tesseract OCR can be applied to recognize the license plate characters. On the other hand, this thesis implements a LPR with the Wiener-like vertical edge enhancement method onto Android embedded platform. The implementation result also verifies the Wiener-like vertical edge enhancement method is effective and feasible.

摘 要 i
ABSTRACT iii
誌謝 v
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 論文架構 5
第二章 車牌偵測常見的邊緣強化方法 7
2.1 基於傳統Sobel邊緣強化方法 7
2.2 其他傳統邊緣強化的濾波器方法 11
2.3 基於去模糊化之邊緣強化方法 14
第三章 應用於車牌定位的Wiener Deconvolution 垂直邊緣強化方法 19
3.1 系統架構 19
3.2 Wiener Deconvolution 22
3.3 車牌偵測系統 28
第四章 實驗分析 30
4.1 實驗架構 30
4.2 實驗步驟 31
4.3 實驗結果 33
4.4 Tesseract OCR字元辨識 40
第五章 Android嵌入式系統平台實作 42
5.1 平台選擇因素 42
5.2 Android作業系統架構 44
5.3 Wiener-like垂直邊緣強化技術 55
5.4 車牌偵測實作結果與字元辨識 60
第六章 結論與未來展望 67
參考文獻 68

[1]S. K. Kim, D. W. Kim, and H. J. Kim, “A recognition of vehicle license plate using a genetic algorithm based segmentation,” Proceedings of IEEE International Conference on Image Processing, vol. 2, pp. 661–664, Sep. 1996.
[2]W. Wei, X. Huang, and M. Wang, “An automatic system of vehicle number-plate recognition based on neural networks,” Journal of Systems Engineering and Electronics, vol. 12, pp. 63–72, 2001.
[3]S. H. Park, K. I. Kim, K. Jung, and H. J. Kim, “Locating car license plates using neural networks,” IEE Electronics Letters, vol. 35, pp. 1475–1477, Aug. 1999.
[4]T. D. Duan, D. A. Duc, and T. L. H. Du, “Combining Hough transform and contour algorithm for detecting vehicle’s license-plates,” Proceedings of International Symposium on Intelligent Multimedia, Video and Speech Processing, pp. 747–750, Oct. 2004.
[5]H. Bai, J. Zhu, and C. Liu, “A fast license plate extraction method on complex background,” Proceedings of IEEE Intelligent Transportation Systems, vol. 2, pp. 12–15, Oct. 2003.
[6]H. Zhang, W. Jia, X. He, and Q. Wu, “A fast algorithm for license plate detection in various conditions,” Proceedings of IEEE International Conference on Systems, Man and Cybernetics, vol. 3, pp. 2420–2425, Oct. 2006.
[7]X. Xu, Z. Wang, Y. Zhang, and Y. Liang, “A method of multi-view vehicle license plates location based on rectangle features,” Proceedings of International Conference on Signal Processing, vol. 3, pp. 16-20, 2006.
[8]F. Faradji, A. H. Rezaie, M. Ziaratban, “A morphological-based license plate location,” IEEE International Conference on Image processing, pp. 57–60, Sep. 2007.
[9]Christos-Nikolaos E., Ioannis E., Vassili Loumos, Ioannis D. Psoroulas and Eleftherios Kayafas, “License Plate Recognition From Still Images and Video Sequences: A Survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 9, pp. 377–391, 2008.
[10]Jing-Ming Guo, Yun-Fu Liu, “License Plate Localization and Character Segmentation With Feedback Self-Learning and Hybrid Binarization Techniques,” IEEE Transactions on Vehicular Technology, vol. 57, pp. 1417–1424, May. 2008.
[11]Jianxia Wang, Guilong Gao, and Huili Yang, “Research and implementation of license plate location based on histogram division method,” Proceedings of International Conference on Electronic Measurement & Instruments, pp.230–233, Feb. 2009.
[12]Zhang Chaoyang, Liao Guangjun, and Qi Qifeng, “On PSF for lined motion blurred image,” Proceedings of Chinese Control Conference, pp. 357–360, Jul. 2008.
[13]Banham, M.R.,and Katsaggelos, A.K., “Spatially Adaptive Wavelet-Based Multiscale Image Restoration,” IEEE Transactions on Image Processing, vol. 5, pp.619–634, Apr. 1996.
[14]Yiping Wang, Xinsheng Huang, Yuzhuang Yan, and Yongbin Zhen, “A New Method for Motion-Blurred Image Blind Restoration Based on Huber Markov Random Field,” Proceedings of International Conference on Image and Graphics, pp. 51–56, Sept. 2009.
[15]Sun Qi, Hongzhi Wang, and Lu Wei, “An Iterative Blind Deconvolution Image Restoration Algorithm Based on Adaptive Selection of Regularization Parameter,” Third International Symposium on Intelligent Information Technology Application, pp.112–115, Dec. 2009.
[16]Ming-Kan Wu, Jing-Siang Wei, Hao-Chung Shih, and Chian C. Ho, “License plate detection based on 2-level 2D Haar Wavelet transform and edge density verification,” Proceedings of IEEE International Symposium on Industrial Electronics, pp. 1699 – 1704, Jul. 2009.
[17]Hau-San Wong and Ling Guan, “Application of Evolutionary Programming to Adaptive Regularization in Image Restoration,” IEEE Transactions on Evolutionary Computation, vol. 4, pp. 309–326, Nov. 2000.
[18]Wikipedia, “Point spread function,” [Online]. Available:
http://en.wikipedia.org/wiki/Point_spread_function
[19]Google, “What is Android,” [Online]. Available:
http://code.google.com/android/what-is-android.html
[20]Wikipedia, “Android (operating system),” [Online]. Available:
http://en.wikipedia.org/wiki/Android_(operating_system)
[21]Google, “Installing the SDK,” [Online]. Available: http://code.google.com/android/intro/installing.html
[22]Google, “Download Android 2.1 SDK, Revision 2,” [Online]. Available:
http:// developer.android.com/sdk/android-2.1.html