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