簡易檢索 / 詳目顯示

回結果列表
研究生： 林聖凱
Lin, Shen-Kai
論文名稱： 基於模板比對與PCA重建技術之低解析度車牌影像辨識
Low-Resolution License Plate Recognition based on Template Matching and PCA Reconstruction
指導教授： 連震杰
Lien, Jenn-Jier
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2012
畢業學年度： 100
語文別： 英文
論文頁數： 66
中文關鍵詞： 多尺寸字元模板 、Otsu二值化 、PCA投影重建
外文關鍵詞： Multi-size character template, Otsu histogram thresholding, PCA reconstruction
相關次數： 點閱：96  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本論文中，我們提出一個基於模板比對與PCA重建技術的低解析度車牌影像辨識系統，藉以直接從低解析度影像中辨識出車牌的正確資訊。我們的系統主要分為三大部份，第一個部份我們將使用多尺寸的低解析度車牌影像模板與Otsu二值化方法增加模板比對的準確率以可信度，辨識車牌影像上的可辨識車牌字元。第二個部份我們將使用PCA重建技術與模板比對方法，藉以辨識車牌影像上的不可辨識車牌字元。最後在第三個部份將綜合針對可辨識車牌字元與不可辨識車牌字元的辨識結果，輸出完整的低解析度車牌辨識結果。

    In this thesis, we proposed a systematic method to perform low-resolution license plate recognition based on template matching and PCA reconstruction, in order to correctly recognize the license number information directly from a single low-resolution license plate image. Our system is consists of 3 main parts. First, we use multi-size template set and Otsu histogram Thresholding to improve the accuracy and credibility of template-matching-based recognition, and to recognize the distinguishable characters on the license plate. Then, we use PCA reconstruction and template matching to recognize the indistinguishable characters on the license plate. Finally, we combine the recognition results of all distinguishable and indistinguishable characters on the license plate and output the final recognition result of the target license plate.

    摘要 IV Abstract V Acknowledgement VI Table of Content VII Table of Figures X Ch.1 Introduction 1 1.1 Motivation 1 1.2 Related Work 2 1.3 System Framework 5 1.4 Chapter Description 11 Ch.2 Low-Resolution Character Segmentation and Distinguishable Character Recognition Using Template-Matching-Based Minimum Distance Curve (MDC) 14 2.1 Image Size and Grayvalue Normalization for Each High-Resolution Character Image 15 2.1.1 High-Resolution Character Image Size Normalization to Three Low-Resolution Character Images Using Bilinear Interpolation 15 2.1.2 Low-Resolution Character Image Grayvalue Normalization Based on Gaussian 20 2.2 Background Noise Reduction Using Otsu Histogram Thresholding for Low-Resolution License Plate Image and Each Low-Resolution Character Template 23 2.2.1 Otsu Histogram Threshold Calculation Based on Low-Resolution Image Histogram 23 2.2.2 Background Noise Reduction Using Otsu Histogram Thresholding 25 2.3 Low-Resolution Character Segmentation Based on Minimum Distance Curve by Template Matching in L1 27 2.3.1 Distance Curves Generation Using Template Matching in L1 27 2.3.2 Low-Resolution Character Position Candidate(s) Detection Using Minimum Distance Curve 29 2.4 Low-Resolution Distinguishable Character Recognition by Ranking L1-Distance 34 Ch.3 Low-Resolution Indistinguishable Character Recognition Based on PCA Reconstruction 37 3.1 Low-Resolution Indistinguishable Character Image Extraction and Size Normalization 38 3.1.1 Low-Resolution Character Image Extraction 38 3.1.2 Low-Resolution Character Image Size Normalization to High-Resolution Size 40 3.2 High-Resolution Indistinguishable Character Image Reconstruction from Each PCA Space 41 3.3 Background Noise Reduction for Each High-Resolution Character Image and Each High-Resolution Reconstructed Indistinguishable Character Image Using Otsu Histogram Thresholding 42 3.4 High-Resolution Indistinguishable Character Recognition Using Template Matching in L1 45 3.4.1 Similarity Measurement Using Template Matching in L1 45 3.4.2 High-Resolution Indistinguishable Character Recognition by Ranking L1-Distance 46 Ch.4 License Plate Recognition Result Ranking 48 4.1 License Plate Type Estimation 48 4.1.1 Two Different Template Sets Estimation Using Minimum Distance Curve (MDC) 49 4.1.2 Character Position Estimation 50 4.2 License Plate Recognition by Ranking L1-Distance 52 Ch.5 Experimental Result 54 5.1 Single Character Recognition Rate by Each Procedure 54 5.2 Single Character and License Plate Recognition Result 58 5.3 Recognition Rate Comparison 60 Ch.6 Conclusion 62 Reference 63

    [1] C. Anagnostopoulos, I. Anagnostopoulos, E. Kayafas, and V. Loumos,“A License Plate Recognition System for Intelligent Transportation System Applications,” IEEE Trans. Intelligent Transportation Systems, vol. 7, no. 3, pp. 377–392, Sep. 2006.
    [2] C. Anagnostopoulos, I. 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, pp. 377–391, 2008.
    [3] H. L. Bai and C. P. Liu, “A Hybrid License Plate Extraction Method Based on Edge Statistics and Morphology,” International Conference on Pattern Recognition, 2004, pp. 831–834.
    [4] J. Barroso, E. Dagless, A. Rafael, and J. Bulas-Cruz, “Number Plate Reading Using Computer Vision,” IEEE International Symposium on, pp. 761–766.
    [5] M. H. ter Brugge, J. H. Stevens, J. A. G. Nijhuis, and L. Spaanenburg, “License Plate Recognition Using DTCNNs,” IEEE International Workshop Cellular NNs Appl., 1998, pp. 212–217.
    [6] G. Cao, J. Chen, and J. Jiang, “An adaptive approach to vehicle license plate localization,” 29th Annu. Conf. IECON, 2003, pp. 1786–1791.
    [7] P. Comelli, P. Ferragina, M. N. Granieri, and F. Stabile, “Optical Recognition of Motor Vehicle License Plates,” IEEE Transactions on Vehicular Technology, vol. 44, no. 4, pp. 790–799, November 1995.
    [8] S. Draghici, “A Neural Network Based Artificial Vision System for License Plate Recognition,” Int. J. Neural Syst., vol. 8, no. 1, pp. 113–126, Feb. 1997.
    [9] W.T. Freeman, E.C. Pasztor, and O.T. Carmichael, “Learning Low-Level Vision”,International Joural of Computer Vision, No. 1, pp. 25-47, 2000.
    [10] W.T. Freeman, Thouis R. Jones, and Egon C. Pasztor, “Example-Based Super-Resolution”, IEEE Computer Graphics and Applications, pp. 56-65, 2002.
    [11] P.L. Hsieh, Y.M. Liang, and H.Y. Mark Liao, “Recognition of Blurred License Plate Images”, IEEE International Workshop on Information Forensics and Security (WIFS), 2010.
    [12] H. Ishida, S. Yanadume, T. Takahashi, I. Ide, Y. Mekada, and H. Murase. “Recognition of Low-Resolution Characters by A Generative Learning Method”, CBDAR2005, pages 45–51, 2005.
    [13] K. K. Kim, K. I. Kim, J. B. Kim, and H. J. Kim, “Learning-based Approach, for License Plate Recognition,” IEEE Signal Process. Soc. Workshop, NNs Signal Process., 2000, vol. 2, pp. 614–623.
    [14] J. Kong, X. Liu, Y. Lu, and X. Zhou, “A Novel License Plate Localization Method Based on Textural Feature Analysis,” IEEE Int. Symp. Signal Process. Inf. Technol., Athens, Greece, 2005, pp. 275–279.
    [15] H.-J. Lee, S.-Y. Chen, and S.-Z. Wang, “Extraction and Recognition of License Plates of Motorcycles and Vehicles on Highways,” ICPR, 2004, pp. 356–359.
    [16] C. Liu, H.Y. Shum, and C.S. Zhang, “A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 192-198, 2001.
    [17] C. Liu, H.Y. Shum, and W. T. Freeman, “Face Hallucination: Theory and Practice”, International Journal of Computer Vision, pp. 115-134, 2007.
    [18] H. Mahini, S. Kasaei, F. Dorri, and F. Dorri, “An Efficient Features–based License Plate Localization Method,” 18th ICPR, Hong Kong, 2006, vol. 2, pp. 841–844.
    [19] X. Shi,W. Zhao, and Y. Shen, “Automatic License Plate Recognition System Based on Color Image Processing, ” vol. 3483, O. Gervasi et al., Ed. New York: Springer-Verlag, 2005, pp. 1159–1168.
    [20] K.V. Suresh, G.M. Kumar, and A.N. Rajagopalan, “Superresolution of License Plates in Real Traffic Videos”, IEEE Tran. Intelligent transportation systems, Vol. 8, No. 2., June 2007
    [21] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms”, IEEE Trans. Sys., Man., Cyber. vol. 9, pp.62-66, 1979.
    [22] T.-H. Wang, F.-C. Ni, K.-T. Li, and Y.-P. Chen, “Robust License Plate Recognition Based on Dynamic Projection Warping,” IEEE Int. Conf. Netw., Sens. Control, 2004, pp. 784–788.
    [23] H.H.P. Wu, H.H. Chen, R.J. Wu, D.F. Shen, “License Plate Extraction in Low Resolution Video”, ICPR, 2006, pp. 824-827.
    [24] J. Yuan, S. Du and X. Zhu, “Fast Super-resolution for License Plate Image Reconstruction”, 19th International Conference on Pattern Recognition (ICPR), Tampa, FL, pp.1-4, Dec. 2008. Page 5.
    [25] Haichao Zhang, Jianchao Yang, Yanning Zhang, and Thomas S. Huang, “Non-local Kernel Regression for Image and Video Restoration”, ECCV, 2010.

    無法下載圖示 校內：2022-12-31公開
    校外：不公開
    電子論文尚未授權公開，紙本請查館藏目錄
    QR CODE