臺灣博碩士論文加值系統

在車牌辨識系統中，車牌偵測與二值化處理(Binarization)都是非常關鍵的影像處理步驟，然而無論是在室內或室外的場景環境中，車牌場景影像都有可能發生陰影遮蔽問題而干擾車牌偵測與二值化處理的正確性。尤其是在手持式或固定式車牌辨識系統的多元化應用場景中，都會需要克服不均勻亮度環境所造成的陰影遮蔽影響。因此本論文提出二種陰影消除方法來分別地解決車牌偵測與二值化處理被陰影干擾的問題。
本論文提出基於伽瑪校正(Gamma Correction)的精簡動態範圍最佳化(Simplified Dynamic Range Optimization, SDRO)方法，以淡化車牌偵測階段的陰影遮蔽問題，並且提出邊緣密度分區域二值化(Edge-Density-Partitioned Binarization, EDPB)陰影消除方法來消除二值化處理階段的陰影干擾問題。實驗結果顯示，本論文所提出的精簡動態範圍最佳化方法與邊緣密度分區域二值化陰影消除方法，可以分別最佳地提升有陰影干擾的室內外汽車與機車車牌場景資料庫的車牌偵測率與字元辨識率，而且本論文所提出的二個方法的執行時間成本都相對地很少。
另一方面，本論文實作「手持式與固定式兩用之自動電子車牌辨識裝置」，並整合自建的「特定應用服務的後台車牌資料庫」，來實現「贓車查緝」應用或「得來速隨車商務」應用。這個嵌入式系統實作可以驗證與擴大車牌辨識技術的可靠度與實用性。

In License Plate Recognition (LPR) system, License Plate Detection (LPD) and binarization are both key image processing steps. But, under indoor or outdoor scene environments, LPD and binarization are both error-prone to the shadow interference caused by the shadow occlusion on the license plate scene images. Especially for diverse applications of potable and fixed LPR systems, shadow occlusion and interference issue resulting from uneven lighting condition is always necessary to be overcome. So this thesis proposes two shadow removal methods to solve the shadow interference issues on LPD and binarization, respectively.
This thesis not only proposes Simplified Dynamic Range Optimization (SDRO) method based on Gamma Correction to fade the shadow occlusion issue at the stage of LPD, but also proposes Edge-Density-Partitioned Binarization (EDPB) shadow removal method to eliminate the shadow interference issue at the stage of binarization. Experimental results show that the proposed SDRO and EDPB shadow removal methods can perform the best improvement on the LPD rate and optical character recognition (OCR) rate, respectively, for shadowed indoor and outdoor vehicle, automobiles and motorcycles, license plate scene database. Besides, two proposed methods both take relatively less computational time.
On the other hand, this thesis implements “portable and fixed electronic license plate recognition device”, and integrates it with a self-built “application-specific remote license plate database” for accomplishment of stolen vehicle investigation application or drive-through commercial service. The embedded implementation can verify and enlarge the reliability and practicability of LPR technology.

中文摘要 I
ABSTRACT II
誌謝 III
目錄 IV
表目錄 VI
圖目錄 VII
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 3
1.3 車牌辨識流程 6
1.4 論文架構 7
第二章 傳統車牌陰影消除的相關研究 8
2.1 傳統針對車牌偵測的陰影消除方法 8
2.1.1 基於Muti-Scale Retinex (MSR) 8
2.1.2 基於低通濾波器來實現Homomorphic Filter 10
2.1.3 基於Gamma Correction的Dynamic Range Optimization (DRO) 12
2.2 傳統針對二值化處理的陰影消除方法 14
2.2.1 基於Horizontal Sub-region Segmentation with Otsu’s method 15
2.2.2 基於Bernsen Algorithm 17
2.2.3 基於Niblack Algorithm 19
第三章 精簡動態範圍最佳化與邊緣密度分區域二值化的陰影消除方法 21
第四章 實驗分析 27
4.1 實驗架構 27
4.2 實驗步驟 29
4.3 實驗結果 30
第五章 ANDROID電子車牌辨識裝置實作 34
5.1 平台選擇因素 39
5.2 ANDROID嵌入式系統平台的軟體架構 41
5.3 實作流程與技術說明 46
5.3.1 實用功能描述 46
5.3.2 車牌影像辨識技術 47
5.3.3 系統架構與程式流程設計 55
5.3.4 贓車查緝應用設計 55
5.3.5 得來速隨車商務應用設計 58
5.3.4 應用的開放原始碼軟體專案 62
5.4 手持式與固定式兩用之自動電子車牌辨識裝置實作成果展示 63
5.4.1 贓車查緝應用的成果展示 63
5.4.2得來速隨車商務應用的成果展示 65
第六章 結論與未來展望 68
參考文獻 69

參考文獻
[1]G. Ma, J. Yang, “Shadow removal using Retinex theory,” Proceedings of 3rd Chinese Conference on Intelligent Visual Surveillance, pp. 25–28, Dec., 2011.
[2]Li Xu Feihu Qi Renjie Jiang , “Shadow Removal from a Single Image,” IEEE Sixth International Conference on Intelligent Systems Design and Applications, Vol. 2, pp. 1049-1054 , 2006.
[3]V.J.D Tsai, “A comparative study on shadow compensation of color aerial images in invariant color models,” Proceedings of IEEE Transactions on Geoscience and Remote Sensing, volume 44, no. 6, pp. 1661-1671, 2006.
[4]E. Salvador, A. Cavallaro, and T. Ebrahimi, “Cast shadow segmentation using invariant color features,” Proceedings of Computer Vision and Image Understanding , pp. 238–259, 2004.
[5]Chan Young Jang, Jae Hwan Lim, Young Hwan Kim “A fast Multi-scale Retinex algorithm using dominant SSR in weights selection,” Proceedings of IEEE International on SoC Design Conference , pp. 37-40 , 2012.
[6]Z. Ruibo , H. Yali , Z. Zhen “A Ultrasound Liver Image Enhancement Algorithm Based on Multi-Scale Retinex Theory,” Proceedings of IEEE International Conference on Bioinformatics and Biomedical Engineering , pp. 1-3, May , 2012.
[7]D. J. Jobson, Z. Rahman, and G. A. Woodell, “Properties and performance of a center/surround retinex,” Proceedings of IEEE Transactions on Image Processing, vol. 6 , pp. 451–462, Mar. 1997.
[8]Z. Rahman, “Properties of a center/surround retinex, part 1: Signal processing design,” Proceedings of NASA Contractor Rep. 198194 , Aug. , 1995.
[9]D. J. Jobson and G. A. Woodell, “Properties of a center/surround retinex, part 2: Surround design,” Proceedings of NASA Tech. Memo. 110188 , Aug. , 1995.
[10]M. Stella, “Homomorphic Filtering using a Low Pass Filter,” [Online]. Available: http://www.cs.sfu.ca/~stella/papers/blairthesis/main/node37.htm
[11]L. Albert, “Illumination and Reflection,” Proceedings of Computer Science 294-13: Advanced Computer Graphics Lecture 2, Sep. , 2009.
[12]C. Gonzales, E. Woods, “Digital Image Processing,” third edition, 2002.
[13]A. Capra , S. Corchs, F. Gasparini, and R. Schettini, “Dynamic Range Optimization by Local Contrast Correction and Histogram Image Analysis,” Proceedings of IEEE International Conference on Consumer Electronics, pp. 309-310 , 2006.
[14]N. Moroney, “Local color correction using non-linear masking,” Proceedings of the 8th Color Imaging Conference, Scottsdale, pp. 108–111 , 2000,.
[15]B. George, “Thresholding,” [Online]. Available:
http://www.cse.unr.edu/~bebis/CS791E/Notes/Thresholding.pdf
[16]N. Otsu, “A threshold selection method from gray-level histograms,” Proceedings of IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-9, no. 1, pp. 62–66, Jan. 1979.
[17]J. Bernsen, “Dynamic thresholding of grey-level images,” Proceedings of 18th International Conference on Pattern Recognition , pp. 1251-1255 , 1986.
[18]W. Ying , L. Yue , Y. Jingqi , Z. Zhenyu , K.M. von Deneen , and S. Pengfei, “An Algorithm for License Plate Recognition Applied to Intelligent Transportation System,” Proceedings of IEEE Transactions on Intelligent Transportation Systems, vol. 12, pp. 830-845, 2011.
[19]W. Niblack, “An Introduction to Digital Image Processing,” Englewood Cliffs , pp.115-116, 1986.
[20]W. Yi , F. Bin. , L. Li-Jun , L. Hui-Wu , and T. Yuan-Yan, “Adaptive Binarization: A New Approach to License Plate Characters Segmentation,” Proceedings of International Conference on Wavelet Analysis and Pattern Recognition ,pp. 91-99 , July 2012.
[21]H. Chia-Shaud , C. Yen-Hsiang , C. Yi-Fan, and R. Shanq-Jang, “An efficient thresholding algorithm for license plate recognition based on intelligent block detection,” Proceedings of IEEE International Conference on Industrial Electronics and Applications , pp 236-240 , May 2009.
[22]S. Krishna Kant , P. Kirat and M. J. Nigam, “Shadow Detection and Removal from Remote Sensing Images Using NDI and Morphological Operators,” Proceedings of International Journal Computer Applications (0975 – 8887), Volume 42– No.10, March , 2012.
[23]Google, “Android Developers,” [Online]. Available:
http://developer.android.com/index.html.
[24]Edwards Research Group, “Android JNI,” [Online]. Available:
http://blog.edwards-research.com/2012/04/tutorial-android-jni/
[25]Sasken, “Android Opencore Framework,” [Online]. Available:
http://www.scribd.com/doc/82285048/11-Android-Opencore-Framework
[26]Google, “Android Kernel Source Code,” [Online]. Available:
https://android.googlesource.com/kernel/common/+/android-2.6.39/
[27]V. Lars, “Android Camera API,” [Online]. Available:
http://www.vogella.com/articles/AndroidCamera/article.html
[28]M. Jim, “Using the Android Camera,” [Online]. Available:
http://p2p.wrox.com/book-professional-android-application-development-isbn-978-0-470-34471-2/72528-article-using-android-camera.html
[29]WorkWithColor, “Color Converter,” [Online]. Available:
http://www.workwithcolor.com/color-converter-01.htm
[30]HunterLab, “Hunter L,a,b Versus CIE 1976 L*a*b*,” [Online]. Available:
http://www.hunterlab.com/appnotes/an02_01.pdf
[31]R. Smith, “An Overview of the Tesseract OCR Engine,” Proceedings of Ninth International Conference on Document Analysis and Recognition , vol. 2 , pp. 629-633 , 2007.
[32]Google code, “Tesseract OCR Engine,” [Online]. Available:
http://code.google.com/intl/zh-TW/
[33]Johnny, “使用HTTP的POST方式和網頁表單溝通,” [Online]. Available:
http://j796160836.pixnet.net/blog/post/28994669
[34]PHP, “PHP:Mysql-Manual,” [Online]. Available:
http://php.net/manual/en/book.mysql.php