臺灣博碩士論文加值系統

本論文是以設計傾斜車牌定位以及辨識系統為考量，所以選用運算複雜度較低的影像處理技術或演算法，盡可能利用簡單的數學運算減少運算時間，以降低系統負擔。影像處理程序分成定位處理階段、前置處理階段。定位處理階段的工作就是擷取車牌的部份。前置處理階段的目的是輔助提升字元分割正確率。本論文採用100 張未設限環境影像進行驗證，將影像依其車牌亮度、影像複雜度、車牌拍攝距離、車牌拍攝角度、車牌傾斜角度及車牌周圍色調等特性加以分類。評估系統效能並且提供影像處理步驟或演算法修改前後比較的基準。利用分析結果找出系統在設限環境的屬性、探討未設限環境對系統造成的影響及針對可能面臨的問題找出可行的解決方案。以期在未設限環境中增加系統應用領域或實用性，使其更符合實際應用。

In this thesis, a method for the localization and recognition of inclined license plates is proposed. Our algorithm requires only simple mathematical operations and thus, its computational burden is reduced. The proposed method consists of two parts: localization and preprocessing. Localization is to find probable position of the considered vehicle license plate. Preprocessing on the plate image is to increase character partition accuracy. 100 images in uncontrolled environment are considered to test the effectiveness of our method. These images have different illumination conditions, different resolutions, different distances, different shooting angles, different inclined angles of license plates, and different colors of license plates background. Besides, the efficiency of each step in our algorithm is analyzed. It provides us with information about the critical steps.

摘要 i
Abstract ii
致謝 iii
Contents iv
List of Tables vi
List of Figures vii
Chapter 1 Introduction
1.1 Motivation 1
1.2 Directions 2
Chapter 2 The Traditional License Plate Image Processing Method
2.1 Color Converts and Binarization Image 4
2.2 Edge Detection 5
2.3 Position License Plate in Images 7
Chapter 3 Image Processing
3.1 Program the Essentials 9
3.2 Strengthens the Image Contrast Degree 12
3.3 The Edge Detections 14
3.4 The Characteristic Density Judgment 17
3.5 Position License Plate and Binarization 19
3.6 Inclined Plate Estimates 23
3.7 Inclined License Corrects 27
3.8 Removal of Useless Images in Plates 28
3.9 Plate Partition 29
Chapter 4 Experience result
4.1 Experiment the environment 31
4.2 Images in Uncontrolled Environment 31
4.3 Various ability analyzes and experiments as a result 37
Chapter 5 Conclusions and Future Work
5.1 Conclusions 44
5.2 Future Work 45
Reference 46
作者簡介 48



















List of Tables
4.1 Experiment the environment 25
4.2 The anti- noise ability and the experiment data analysis 31
4.3 The inclined Plate Estimates experiment data analysis 34
4.4 The biggest inclined angle analysis 36





















List of Figures
1-1 The license plate under a normal angle 3
1-2 The license plate under an inclined angle 3
2-1 The gray image and the binarization image 5
2-2 The mask of the Laplactian filter 6
2-3 The result of using the Laplacian filter 6
2-4 The masks of the Sobel filter 7
2-5 The result of using the Sobel filter 7
2-6 The license plate position under normal angle 8
2-7 The license plate position under sloping angle 8
3-1 The image preprocessing stage of the proposed system 10
3-2 The plate processing stage of the proposed system 11 3-3 The result of the program performance 1 11
3-4 The result of the program performance 2 12
3-5 The gray scale keeps a diagram scope extension 13
3-6 The gray scale transformation curve 14
3-7 The result of strengthening the image contrast degree (a) the original image (b) the image after contrast strengthening 14
3-8 The experimental results of applying edge detection algorithms 16
3-9 The density judgment process 18
3-10 The density judgment process for noisy image 19
3-11 Experimental comparison of adaptive binarization methods 22
3-12 The result of applying the binarization method 23
3-13 estimate the shape of the license plate top and bottom boundary 23
3-14 inclined plate estimates 26
3-15 The coefficient comparison for inclined plate estimates 26
3-16 [19] after correct of the diagram 27
3-17 indicate geometry change 28
3-18 included the original image, the license plate four directions to estimate and correct the result 28
3-19 clean dash 29
3-20 looking for partition point 30
3-21 included the original image, inclined plate estimates and correct the result and the character partition 30
4-1 images in uncontrolled environment (a) 32
4-2 images in uncontrolled environment (b) 32
4-3 images in uncontrolled environment (c) 33
4-4 images in uncontrolled environment (d) 33
4-5 images in uncontrolled environment (e) 34
4-6 images in uncontrolled environment (f) 34
4-7 images in uncontrolled environment (g) 35
4-8 images in uncontrolled environment (h) 35
4-9 images in uncontrolled environment (i) 36
4-10 images in uncontrolled environment (j) 36
4-11 successful identification of the plate location under noise—Case 1 38
4-12 successful identification of the plate location under noise—Case 2 38
4-13 successful identification of the plate location under noise—Case 3 39
4-14 A failure case of the plate location identification under noise 39
4-15 inclined plate estimates result 41
4-16 inclined plate estimates result 42

[1]J. Duan and G. Qiu,“Novel histogram processing for colour image enhancement,” International Conference on Image and Graphics, pp.55-58, 2004.
[2]H. L. Bai, J. M. Zhu, and C. P. Liu, “A fast license plate extraction method on complex background,” IEEE on Intelligent Transportation Systems, vol.2, pp.985-987, 2003.
[3]B. Enyedi, L. Konyha, C. Szombathy and K. Fazekas, “Strategies for fast license plate number localization,” International Symposium Electronics in Marine, pp.579-584, 2004.
[4]O. D. Trier and A. K. Jain, “Goal-directed evaluation of binarization methods,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.17, pp.1191-1201, 1995.
[5]Bihai Hong and Chenhui Yang, “An Approach to License Plate Locating in Intelligent Transportation System,” proceeding of conference IEEE on Pervasive computing and Applications, pp 319-322, 2007.
[6]M. H. Ter Brugge, J. H. Stevens, J. A. G. Nijhuis and L. Spaanenburg, “License plate recognition using DTCNNs,” IEEE International Workshop on Cellular Neural Networks, pp.212-217, 1998.
[7]J. Serra, Image “Analysis and Mathematical Morphology”, Academic Press, 1982.
[8]Feng Yang, Zheng Ma, and Mei Xie, “A Novel Binarization Approach for License Plate,” proceeding of conference IEEE on industrial Electronics and Applications, pp.1-4, 2006.
[9]L.G. Shapiro and G.C. Stockman, “Computer Vision”, New Jersey, Prentice-Hall, 2001.
[10]T. Y. Zhang and C. Y. Suen,“A fast parallel algorithm for thinning digital patterns,”Communications of the ACM, vol. 27, pp.236-239, 1984.
[11]H. J. Lee, D. H. Kim, D. J. Kim, and S. Y. Bang,“Real-time automatic vehicle management system using vehicle tracking and car plate number identification,”International Conference on Multimedia and Expo, vol.2, pp.353-356, 2003.
[12]鍾國亮，“影像處理與電腦視覺”，台北，東華書局，民國九十五年。
[13]黃文吉，“C++ Builder與影像處理”，台北，儒林書局，民國九十四年。
[14]林丕靜，“數值分析”，台北，儒林書局，民國七十九年。
[15]連國珍，“數位影像處理”，台北，儒林書局，民國九十三年。
[16]吳上立，“C語言數位影像處理”，台北，全華，民國九十五年。
[17]官宗保，“利用數位訊號處理器實現車牌字元辨識系統”，國立台灣大學，電機工程學研究所碩士論文，民國九十年六月。
[18]陳麗奾，“在未設限的環境下車牌的定位與辨識”，國立師範大學，資訊教育研究所碩士論文，民國八十九年六月。
[19]侯宜穎，“邊界切割法在車牌辨識系統之應用”，國立交通大學，電機與控制工程學研究所碩士論文，民國九十五年6月。
[20]陳朕寬，“彩色車牌的自動偵測方法”，國立中山大學，機械與機電工程學研究所碩士論文，民國九十四年七月。