臺灣博碩士論文加值系統

　　本論文研究以半自動化的方式來執行車牌辨識系統，先以人工方式拍攝車牌影像，再將影像配合電腦和車牌辨識系統進行車牌辨識。整個系統包含了車牌定位、字元切割和字元辨識。
　　車牌定位部份，先將RGB彩色車牌影像首先轉換成灰階影像，再以Prewitt遮罩處理，找出影像內明顯的垂直邊緣點，再經過二值化處理，為了消除雜訊使用中值濾波器處理，之後對影像做型態學處理(膨脹與侵蝕)，再使用物件聯通法標籤影像裡白色區塊，最後設定條件篩選含有車牌的區塊，將車牌定位並且擷取。
字元切割與辨識都是以二值化影像為前提處理，本文以投影法切割取得車牌字元，辨識部分先將字元正規化統一規格，再對字元影像做細線化處理，以金字塔模型為概念取得特徵值進行模板比對，以達到辨識效果。實驗結果顯示，本方法有不錯的辨識結果。

　　In this thesis, we study a semi-automated license plate recognition system. First shoot plate image by artificially, then we can use the computer and the license plate recognition system to identify the car as the license plate. The proposed system consists of three stages: license plate location, character segmentation and character recognition.
　　License plate location achieved by the color transformation, Prewitt mask, binarization, median filter and morphology operations. The 8-connected label and threshold are applied to select the license plate.
　　Character segmentation and recognition are based on binary image. The license plate character segmentation achieved by the projection scheme. Character recognition schemes include normalization, thinning and the Pyramid model. The characteristic values by the Pyramid model are applied to match the character in the template pool. Experiments show that the proposed scheme has good result on plate recognition.

中文摘要 iii
ABSTRACT iv
誌謝 v
目錄 vi
圖目錄 ix
表目錄 xi

第一章 簡介 1
1.1 究背景與動機 1
1.2 研究架構 1
第二章 文獻探討 2
2.1 灰階化 2
2.2 邊緣偵測 2
2.3 二值化 5
2.4 型態學 6
2.4.1 膨脹 6
2.4.2 侵蝕 7
2.5 車牌定位 9
2.6 字元切割 9
2.7 字元辨識 10
2.7.1 模板比對法 10
2.7.2 類神經網路 11
第三章 系統設計與架構 12
3.1 系統設計與架構 12
3.2 前處理 13
3.2.1 灰階化 13
3.2.2 Prewitt遮罩 14
3.2.3 二值化 15
3.2.4 中值濾波器 16
3.2.5 膨脹與侵蝕 17
3.3 標籤化與車牌定位 19
3.4 字元切割 20
3.5 字元辨識 23
3.5.1 正規化 23
3.5.2 細線化 24
3.5.3 字元辨識 26
3.5.4 混淆字元辨識 29
第四章 實驗結果 31
4.1 實驗環境 31
4.2 實驗結果 34
4.2.1 車牌定位 34
4.2.2 字元切割 38
4.2.3 字元辨識 39
4.3 結果討論 42
第五章 結論與未來展望 46
參考文獻 47

[1]V. D. Mai, D. Miao, R. Wang, H. Zhang,“ An Improved Method for Vietnam License Plate Location, Segmentation and Recognition”, in Proc. of IEEE Int. Conf. on International Conference on Computational and Information Sciences, pp.212- 215, 2011.
[2]R. C. Gonzalez, R. E. Woods,“ Digital Image Processing (2nd Edition)”, Beijing : Publishing House of Electronics Industry, 2007.
[3]B. R. Dandu, A. Chopra,“ Vehicular Number Plate Recognition Using Edged Etection and Characteristic Analyisis of National Number Plates”, Int. Conf. on International Journal Of Computational Engineering Research, vol.2, pp.795-799, 2012.
[4]N. Otsu,“ A Threshold Selection Method from Gray-Level Histograms”, in Proc. of IEEE Int. Conf. on Systems, Man, and Cybernetics, pp.62-66, 1979.
[5]X. D. Yang, V. Gupta,“ An Improved Threshold Selection Method for Image Segmentation”, in Proc. of IEEE Int. Conf. on Electrical and Computer Engineering, vol.1, pp.531-534, 1993.
[6]H. Negishi, Toyama Univ, J. Kato, H. Hase, T. Watanabe,“ Character Extraction from Noisy Background for An Automatic Reference System”, in Proc. of IEEE Int. Conf. on Document Analysis and Recognition, pp.143-146, 1999.
[7]P. Anishiya, S. Mary Joans,“ Number Plate Recognition for Indian Cars Using Morphological Dilation and Erosion with The Aid of OCRs”, in Proc. of IACSIT Int. Conf. on Information and Network Technology, vol.4, pp.115-119, 2011.
[8]S. H. M. Kasaei, S. M. M. Kasaei, S. A. Monadjemi,“ A Novel Morphological Method for Detection and Recognition of Vehicle License Plates”, Int. Conf. on American Journal of Applied Sciences vol.6, pp.2066-2070, 2009.
[9]L. F. He, Y. Y. Chao, K. Suzuki,“ An Algorithm for Connected-Component Labeling, Hole Labeling and Euler Number Computing”, Int. Conf. on Journal of Computer Science and Technology, vol.28, pp.468-478, 2013.
[10]R. Parisi, E. D. Di Claudio, G. Lucarelli, G. Orlandi,“ Car Plate Recognition by Neural Networks and Image Processing”, in Proc. of IEEE Int. Conf. on Circuits and Systems, Vol.3, pp.195-198, 1998.
[11]H. C. Wu, C. S. Tsai, C. H. Lai,“ A License Plate Recognition System in e-Government”, in Proc. of ISN Int. Conf. on e-Government and Security of Information, vol.15, no.2, pp.199-210, 2004.
[12]X. G. He, L. H. Zheng, Q. Wu, W. J. Jia, B. J. Samali and M. Palaniswami,“ Segmentation of Characters on Car License Plates”, in Proc. of IEEE Int. Conf. on Multimedia Signal Processing, pp.399-402, 2008.
[13]P. Comelli, P. Ferragina, M. N. Granieri, F. Stabile,“ Optical Recognition of Motor Vehicle License Plates”, in Proc. of IEEE Int. Conf. on Vehicular Technology , vol.44, no.4, pp.790-799, 1995.
[14]T. Naito, T. Tsukada, K. Yamada, K. Kozuka, S. Yamamoto,“ Robust License-Plate Recognition Method for Passing Vehicles Under Outside Environment”, in Proc. of IEEE Int. Conf. on Vehicular Technology, vol.49, no.6, pp. 2309-2319, 2000.
[15]R. Juntanasub and N. Sureerattanan,“ Car License Plate Recognition Through Hausdorff Distance Technique”, in Proc. of IEEE 17th Int. Conf. on Tools with Artificial Intelligence, Hong Kong, pp.647-651, 2005.
[16]B. Hussain and M. R. Kabuka,“ A Novel Feature Recognition Neural Network and Its Application to Character Recognition”, in Proc. of IEEE Int. Conf. on Pattern Analysis and Machine Intelligence, vol.16, pp.94-106, 1994.
[17]Q. Gao, X. Wang, G. Xie,“ License Plate Recognition Based on Prior Knowledge”, in Proc. of IEEE Int. Conf. on Automation Logistics, Shandong, China, pp.2964-2968, 2007.
[18]鐘國亮，影像處理與電腦視覺(第五版) ，台灣東華書局股份有限公司，2012年3月。
[19]S. Lazebnik, C. Schmid, J. Ponce,“ Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories”, IEEE Trans. on Computer Vision and Pattern Recognition, vol.2, pp.2169-2178, 2006.
[20]洪健詠，車牌辨識系統，立德管理學院，2004年。