進階搜尋


下載電子全文  
系統識別號 U0026-1207201111521800
論文名稱(中文) 低成本嵌入式即時車牌辨識系統之設計與實現
論文名稱(英文) Design and Implementation of Real-Time License Plate Recognition with Low Cost Based on Embedded System
校院名稱 成功大學
系所名稱(中) 工程科學系碩博士班
系所名稱(英) Department of Engineering Science
學年度 99
學期 2
出版年 100
研究生(中文) 陳威穎
研究生(英文) Wei-Ying Chen
學號 n96984016
學位類別 碩士
語文別 英文
論文頁數 57頁
口試委員 指導教授-廖德祿
召集委員-顏錦柱
口試委員-林瑞昇
中文關鍵字 嵌入式系統  賈伯濾波器 
英文關鍵字 Embedded System  Gabor Filter 
學科別分類
中文摘要 隨著科技進步和經濟起飛,開始使用車輛來代替步行的人越來越多。而在台灣地小人口又密集的情況下,發生了車位嚴重不足的情況。為了提高生活品質,很多人購買了相當高級的車種,也使得盜竊率往上攀升。因此,使監控系統能獲取即時資訊的議題探討受到相當大的重視。因此,本論文主要目的在於實現即時的車牌辨識系並驗證其結果。當中利用嵌入式系統與車牌辨識系統做結合,來達到即時性與低成本。內容分成硬體架構以及軟體演算法部分:硬體部分利用嵌入式系統來獲取影像來源和演算法運算。軟體演算法部分:車牌辨識系統主要分為車牌定位、字元切割、字元辨識等三大步驟。在車牌定位方面,本論文利用Gabor filter的特性來做影像增強,達到突顯車牌垂直邊緣的效果。在車牌測試方面,使用50張影像來源進行實驗,車牌定位率平均結果達98%,字元切割率平均結果達95%,字元辨識率平均結果達92%。
英文摘要 With the rapid development of technology and economy to take off,more and more people uses Vehicles to replace walking. There are small land and concentrated population in Taiwan, situation which parking are serious shortage happen. In order to improve quality of life, many people buy very advanced vehicles, render average accuracy of theft is ascent. Therefore, the questions which monitoring system can be captured real-time information suffer considerable attention. Therefore, the main purpose of this thesis is to achieve real-time license plate recognition system and verify the results. This thesis use embedded system to do with license plate recognition which achieves real-time and low cost. In this thesis, the system can be divided into hardware architecture and the software algorithm. In hardware, an embedded system is used to capture the image. In the software algorithm, three major steps in the license plate recognition system are addressed. First, license plate positioning, second, character segmentation, and third, character recognition. In license plate positioning, this thesis used features of the Gabor filter to carry out image enhancement based on the perpendicular edges, so that the positioning rate can be increased. In testing of license plate, we use the 50 source of image for the testing, the average accuracy of license plate positioning is 98%, the average accuracy of character segmentation is 95%, and the average accuracy of character recognition is 92%.
論文目次 摘要 I
Abstract II
誌謝 IV
Contents V
List of Figures VIII
List of Tables X
CHAPTER 1 INTRODUCTION 1
1.1 Motivation and Objectives 1
1.2 Thesis Organization 2
CHAPTER 2 RELATED WORK 3
2.1 Introduction of Embedded Systems 3
2.2 Morphological Processing 4
2.2.1 Dilation 4
2.2.2 Erosion 6
2.3 Research of License Plate Positioning 8
2.4 Character Segmentation and Recognition Research 9
CHAPTER 3 ARCHITECTURE and DESIGN 10
3.1 Architecture of License Plate Recognition System 10
3.2 License Plate Positioning 12
3.2.1 Image Pre-processing 13
3.2.1.1 Gray-scale Processing 13
3.2.1.2 Enhancement 13
3.2.1.3 Edge Detection 16
3.2.1.3.1 Algorithm of Sobel Edge Detection 16
3.2.1.4 Image Binarization 19
3.2.2 License Plate Search 21
3.2.2.1 Morphological Processing 21
3.2.2.1.1 Closing 22
3.2.2.1.2 Opening 23
3.2.2.2 Block Labeling 24
3.2.3 License Plate positioning 26
3.2.3.1 Block Screening 26
3.3 Character Segmentation 27
3.3.1 License Plate Binarization 27
3.3.2 Thinning 31
3.3.3 Segmentation Boundary 34
3.3.4 Character Segmentation 37
3.4 Character Recognition 39
3.4.1 Character Normalization 39
3.4.2 Character Encoding 41
3.4.3 Template Matching 45
CHAPTER 4 EXPERIMENT RESULTS 46
4.1 Organization of License Plate Recognition System 46
4.2 Result of License Plate Recognition System 47
4.2.1 Result of License Plate Positioning 47
4.2.2 Result of Character Segmentation 51
4.2.3 Result of Character Recognition 52
CHPATER 5 CONCLUSIONS 54
References 55
參考文獻 [1] Cavusoglu A., Gorgunoglu S., “A fast fingerprint image enhancement algorithm using a parabolic mask”, Computers and Electrical Engineering, 2008.
[2] Gao D.S., and Zhou J., “Car License Plate Detection from Complex Scene”, Tsinghua Universtiy, Department of Automation P. R. China, pp. 1409-1414, 2000.
[3] Hong L., Jain A., Pankanti S., Bolle R., “Fingerprint enhancement.”, In: Proceedings of the 3rd IEEE workshop on applications of computer vision, Sarasota, pp. 202–7, 1996.
[4] Kim D.H., Park R.H.,” Fingerprint binarization using convex threshold.”, In: Proceedings of the sixth IASTED international conference on computer graphics and imaging, Honolulu, Hawaii, USA., pp. 224–7 , 2003.
[5] Lin H., Wan Y., and Jain A., “Fingerprint Image Enhancement: Algorithm and Performance Evaluation”, Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing, MI 48824.
[6] Yu M., and Kim Y.D., “An Approach to Korean License Plate Recongition Based on Vertical Edge Matching”, Ajou University, Suwon, Korea, 2000
[7] Rafael C. Gonzalez, Richard E. Woods and Steven L. Eddins, “Digital Image processing using MATLAB”, Upper Saddle River, N. J. :Pearson Prentice Hall, 2004.
[8] Sharat C., Alexander N., Cartwright V.G., ” Fingerprint enhancement using STFT analysis”, Pattern Recognition, Vol.40 pp. 198 – 211, 2007 .
[9] Yu S.H., Hsieh J.W, and Chen Y.S., “Morphology-based License Plate Detection from Complex Scenes”, IEEE Proc. of International Conference on Pattern Recognition (CD-ROM), Quebec City Convention Center, Canada, (August 11-15, 2002), Vol. III, pp. 176-179, 2002.
[10] Kim S., Kim D., Ryu Y., and Kim G., “ A Robust License-Plate Extraction Method under Complex Image Conditions”, Sogang University, Dept. of Electronic Engineering, Korea, pp. 216-219, 2002.
[11] Lee S.U., Chung S.Y., and Park R.H., “A comparative performance study of several global thrsesholding techniques for segmentation”, Comput. Vis. Graph. Image processing, Vol. 22, pp. 171-190, 1990.
[12] Zhang T.Y., Suen C.Y., “A fast parallel algorithm for thinning digital patterns”, Communications of the ACM, 1984.
[13] Wu C., Shi Z., Govindaraju V., “Fingerprint image enhancement method using directional median filter”, In: Proceedings of the SPIE, Vol. 5404. pp. 66–75, 2004.
[14] Zhang X., Liu X., and Jiang H., “A hybrid approach to license plate segmentation under complex conditions”, The 3rd International Conference on Natural Computation, pp. 68-73, August 2007.
[15] Jia X., Wang X., Li W., and Wang H., “A novel algorithm for character segmentation of degraded license plate based on prior knowledge”, 2007 IEEE International Conference on Automation and Logistics, pp. 249-253, August 2007.
[16] Chil X., Dong J., Liu A., and Zhou H., “A simple method for Chinese license plate recognition based on support vector machine”, 2006 International Conference on Communications, Circuits and Systems Proceedings, Vol. 3, pp. 2141-2145, June 2006.
[17] Hasan Y.M.Y., Karam L.J., “Morphological text extraction from images”, IEEE Transactions on Image Processing, Vol. 9, pp. 1978-1983, 2000.
[18] Zhang Y., and Zhang C., “A new algorithm for character segmentation of license plate”, 2003. Proceedings. IEEE Intelligent Vehicles Symposium, pp. 106-109, June 2003.
[19] 王振興,“多標的汽車車牌辨識系統之研究” ,元智大學資訊管理學系碩士論文,2003年.
[20] 王精忠,“車牌辨識系統之研究” ,大同大學資訊工程研究所碩士論文,2005年.
[21] 張唐祐,“改良式投影演算法於車牌辨認之應用” ,國立成功大學電腦與通信工程研究所碩士論文,2008年.
[22] 陳翔傑,“自動化車牌辨識系統設計” ,國立中央大學電機工程研究所碩士論文,2005年.
[23] 黃琇靖,“應用於道路監視器之自動車牌辨識系統” ,朝陽科技大學資訊工程系碩士論文,2007年.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2016-07-20起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2016-07-20起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw