臺灣博碩士論文加值系統

本論文著重於將車牌辨識運用於室內停車場系統中，為了讓車主使用此系統時避免等待時間過久，提出快速車牌辨識的方法。車牌辨識步驟中車牌定位和字元切割最耗時間，因此本文提出快速車牌定位和字元切割方法。先將車牌影像縮小灰階化減少運算量，用底帽轉換的加強低頻影像，以找出可疑車牌位置，運用區域平均二值化將車牌字元和車牌背景分離。字元切割部分，利用垂直投影法將字元切割，切割後的影像使用字元特徵方式辨識。
為驗證系統的可行性，本論文將所提出快速車牌定位和字元切割方法實作於本校停車場的管理系統，實驗結果發現車牌辨識的處理時間低於500ms的商用車牌辨識系統規範，且辨識成功率維持90%。

The purpose of this thesis is to explain how the indoor parking system uses the license plate recognition to shorten the user''s waiting time. License plate locating and segmentation of the plate characters are quite time consuming in license plate recognition. So this thesis presents high-speed License plate locating and segmentation of the plate characters methods. First, decrease and gray the license plate image which will decrease the operational volume. Then use Bottom hat transform to indicate the bottom value of the original image and locate the license plate. Use local average threshold to separate the license plate characters and license plate back ground. In the segmentation of the plate characters use vertical projection method to divide characters, then use character features to recognize each character.
In order to verify the system feasibility. This thesis presents high-speed License plate locating and segmentation of the plate characters methods and implements the system at the NTUT underground parking system. The experimental results measuring up to less than the 500ms complete the license plate recognition norms of business, and the percentage of literacy rate is 90%.

摘　要 i
ABSTRACT ii
誌 謝 iv
目 錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 研究目的 2
1.4 章節概要 2
第二章 相關理論與文獻回顧 3
2.1 影像處理方法 3
2.1.1 影像縮放 3
2.1.2 灰階化 4
2.1.3 二值化 5
2.1.4 形態學 7
2.2 文獻回顧 12
第三章 車牌辨識系統 14
3.1 車牌定位 14
3.1.1 前處理 17
3.1.2 特徵抽取及辨識 19
3.1.3 車牌定位特色 21
3.2 字元切割 23
3.2.1 前處理 24
3.2.2 文字分離 25
3.3 字元辨識 26
第四章 實驗結果 28
4.1 停車場系統運作流程 28
4.2 硬體架構 30
4.3 樣本來源 31
4.4 實驗平台介紹 33
4.5 實驗結果及數據 34
第五章 結論與未來研究方向 40
5.1 結論 40
5.2 未來研究方向 40
參考文獻 41

[1] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on System, Man, and Cybernetics, vol. 9, 1979, pp. 62-66.
[2] 林家緯，以統計數據為基礎的車牌影像處理與辨識方式，碩士論文，中山大學機械與機電工程學系，高雄，2006。
[3] 陳翔傑，自動化車牌辨識系統設計，碩士論文，中央大學電機工程研究所，桃園，2005。
[4] W. Doyle, "Operations Useful for Similarity-Invariant Pattern Recognition," Journal of the ACM, vol. 9, no. 2, 1962, pp. 259-267.
[5] R. C. Gonzalez and R. E. Woods, Digital Image Processing Second Edition, New Jersey: Pearson Education, 2008
[6] J. Serra, Image Analysis and Mathematical Morphology, USA, New York: Academic Press, 1982.
[7] G. Matheron, Random Sets and Integral Geometry, New York: John Wiley, 1975.
[8] L. Vincent, "Morphological grayscale reconstruction in image analysis: application and efficient algorithms," IEEE Transactions on Image Processing, vol. 2, no. 2, 1993, pp. 176-201.
[9] P. G. Hou, J Zhao and M Liu, "A License Plate Locating Method Based on Tophat-bothat Changing and Line Scanning," International Symposium on Instrumentation Science and Technology, 2006, pp. 431-436.
[10] M. D. Saleh, Herminiawati, H. Mellah, N. D. Salih, "Comparison of contrast enhancement techniques in license plate recognition," International Symposium on Information Technology, vol. 2, 2008, pp. 1-4.
[11] Y. T. Hsiao, C. L. Chuang, J. A. Jiang and C. C. Chien, "A contour based image segmentation algorithm using morphological edge detection," IEEE International Conference on Systems, Man and Cybernetics, Nevada, USA, vol. 3, 2005, pp. 2962-2967.
[12] C. N. E. Anagnostopoulos, I. E. Anagnostopoulos, I. D. Psoroulas, V. Loumos and E. Kayafas, "License Plate Recognition From Still Images and Video Sequences: A Survey," IEEE Transactions on Intelligent Transportation Systems, vol. 9, no.3, 2008, pp. 337-391.
[13] C. Wu, L. C. On, C. H. Weng, T. S. Kuan and K. Ng, "A Macao license plate recognition system," Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, China, 2005, pp.4506-4510.
[14] B. Hongliang and L. Changping, "A hybrid license plate extraction method based on edge statistics and morphology," Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK, 2004, pp. 831–834.
[15] H. J. Lee, S. Y. Chen and S. Z. Wang, "Extraction and recognition of license plates of motorcycles and vehicles on highways," Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK, 2004, pp. 356–359.
[16] J. M. Guo and Y. F. Liu, "License Plate Localization and Character Segmentation With Feedback Self-Learning and Hybrid Binarization Techniques," IEEE Transactions on vehicular technology, vol. 57, no. 3, 2008, pp. 1417-1424.
[17] G. Cao, J. Chen and J. Jiang, “An adaptive approach to vehicle license plate localization," The 29th Annual Conference of the IEEE Industrial Electronics Society, Virginia, USA, 2003, pp.1786-1791.
[18] Q. Wu, H. Zhang, W. Jia, X. He, J. Yang and T. Hintz, "Car plate detection using cascaded tree-style learner based on hybrid object features," IEEE Congress on Evolutionary Computation, Sydney, Australia, 2006, pp.15-20.
[19] S. Z. Wang and H. J. Lee, "A cascade framework for a real-time statistical plate recognition system," IEEE Transactions on Information Forensics and Security, vol. 2, no.2, 2007, pp. 267-282.
[20] 林仲芬，影像辨認技術，台北：全華科技，1995。