臺灣博碩士論文加值系統

隨著自動化牌照定位與辨識系統日益普及，其準確率的要求也越來越高。大部分的牌照定位系統可分為兩種，ㄧ種是使用影像處理與電腦視覺技術，基於梯度(gradient)計算的索貝爾(Sobel)邊緣偵測方法，尋找紋理密度高的區域當作可能的牌照位置；另一種則是基於哈爾(Haar-like)特徵的自適應性增強(Adaptive Boosting)的機器學習算法，其準確率都接近100%。牌照定位完成後，以投影的方式對偵測到的牌照進行文字切割，最後文字辨識的準確率也都有95%以上。然而幾乎所有的牌照辨識系統都是針對單行車牌做處理，遇上雙行牌照案例的話，便會導致較差的辨識率。為了解決這類雙行牌照的問題，本論文提出基於影像處理的方法，進行歪斜牌照的校正與多行牌照的處理。首先，我們會進行牌照的歪斜校正並判斷是否出現雙行的情況，在經過分行處理與單行文字切割後，便可以套用文字辨識系統。經過實驗，本論文提出的方法確實能夠有效地處理多行牌照的情況。

As automatic license plate (LP) localization and recognition getting popular, the requirement of accuracy is rising, too. Most of LP localization systems can be divided into two categories, one is based on technique of image processing and computer vision using edge detection methods such as Sobel operator for gradient computation and search for areas with high texture density as reasonable LP positions; the other is based on machine learning using adaptive boosting with Haar-like features. The accuracy of both methods is close to 100%. Based on the results of localization, character segmentation can be performed by projection and final license plate recognition (LPR) rate up to 95% can be achieved. However, almost all LPR methods are aimed to handle single-line LPs, and may lead to poor recognition rate for the case of double-line LP. To handle such a problem, we propose an image processing method to handle skewed and double-line LP. The proposed approach first performs skew correction of LP and determines whether it has double lines. After line separation, followed by character segmentation performed for each line, single-line LPR can be applied. Experimental results show that the proposed approach is indeed effective in dealing with the situation of skewed LP which may have single or double lines.

摘要......i
ABSTRACT......ii
CONTENTS......iii
LIST OF FIGURES......iv
LIST OF TABLES......viii
Chapter 1 Introduction......1
1.1 Motivation......1
1.2 Related Work......2
1.2 .1 License Plate Detection......2
1.2.2 License Plate Skew Correction......5
1.2.3 License Plate Character Segmentation......7
1.3 Thesis Organization......8
Chapter 2 LP Detection......9
2.1 Sobel Result......9
2.2 Potential Stroke Analysis......11
2.3 Extraction of LP......13
Chapter 3 LP Skew Correction......17
3.1 Adaptive Thresholding......17
3.2 Sobel Result Sampling......21
3.3 Skew Correction......22
Chapter 4 LP Character Segmentation......27
4.1 Boundary Searching......27
4.2 Double-Line LP......31
4.3 Single-Line LP Character Segmentation......33
Chapter 5 Experimental Result......41
5.1 Detection Results of Single-Line LP and Double-Line LP......42
5.2 Experiments for Different Parameters of Adaptive Thresholding......46
5.3 LP Line Separation and Boundary Searching for LP Detections......49
5.4 Character Segmentation and Recognition......51
Chapter 6 Conclusions and Future Works......53
6.1 Conclusions......53
6.2 Future Works......53
References......54

[1] D. Bradley and G. Roth, “Adaptive Thresholding using the Integral Image,” Journal of Graphics, GPU, and Game Tools, vol 12, 2007
[2] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol 9, 1979
[3] P. Wellner, “Adaptive Thresholding for the Digitaldesk,” EuroPARC Technical Report EPC-93-110, 1993
[4] Y.-T. Chen, J.-H Chuang, W.-C. Teng, H.-H. Lin, and H.-T. Chen, “Robust License Plate Detection in Nighttime Scenes using Multiple Intensity IR-Illuminator,” IEEE International Symposium on Industrial Electronics, p. 893-898, 2012
[5] A. M. Al-Ghaili, S. Mashohor, A. R. Rali, and A. Ismail, “Vertical-Edge-Based Car-License-Plate Detection Method,” IEEE Transactions on Vehicular Technology, vol 62, no 1, 2013
[6] A. M. Al-Ghaili, S. Mashohor, A. Ismail, and A. R. Rali, “A New Vertical Edge Detection Algorithm and its Application,” IEEE Transactions on Vehicular Technology, vol 62, no 1, 2013
[7] Z. Musoromy, Dr. S. Ramalingam, and N. Bekooy, “Edge Detection Comparison for License Plate Detection,” International Conference Control, Automation, Robtics and Vision Singapore, 2010
[8] K. Parasuraman and P. V. Kumar, “An Efficient Method for Indian Vehicle License Plate Extraction and Character Segmentation,” IEEE International Conference on Computational Intelligence and Computing Research, 2010
[9] S. Ozbay and E. Ercelebi, “Automatic Vehicle Identification by Plate Recognition,” International Journal of Electrical, Computer Energetic, Electronic and Communication Engineering, vol 1, no 9, 2007
[10] F. Kahraman, B. Kurt, and M. Gökmen, “License Plate Character Segmentation Based on the Gabor Transform and Vector Quantization,” Lecture Notes in Computer Science, vol 2869, p. 381-388, 2003
[11] R. Azad, B. Azad, and H. R. S. Brojeeni, “Real-Time and Efficient Method for Accuracy Enhancement of Edge Based License Plate Recognition System,” International Conference on computer, Information Technology and Digital Media, 2013
[12] M. Ashoori-Lalimi and S. Ghofrani, “An Efficient Method for Vehicle License Plate Detection in Complex Scenes,” Circuits and Systems, 2011
[13] C. Arth, F. Limberger, and H. Bischof, “Real-Time License Plate Recognition on an Embedded DSP-Platform,” IEEE conference on Computer Vision and Pattern Recognition, p. 1-8, 2007
[14] R. Pan, X. Ma, and L. Wang, “An Efficient Method for Skew Correction of License Plate,” International Workshop on Education Technology and Computer Science, vol 2, p. 90-93, 2010
[15] M.-S. Pan, J.-B. Yan, and Z.-H. Xiao, “Vehicle License Plate Character Segmentation,” International Journal of Automation and Computing, vol 5, p. 425-432, 2008
[16] N. D. Modi, C. K. Modi, C. N. Paunwala, and S. Patnaik, “Skew Correction for Vehicle License Plates using Principal Component of Harris Corner Feature,” International Conference on Communication Systems and Network Technologies, p. 339-343, 2011
[17] M. Wang and G. Wang, “An Optimization Algorithm of Vehicle License Plate Correction Based on Minimum Projection Distance,” International Conference for Young Computer Scientists, p. 1701-1705, 2008
[18] V. Ganapathy and W. L. D. Lui, “A Malaysian Vehicle License Plate Localization and Recognition System,” Journal of Systemics, Cybernetics, and Informatics, vol 6, no 9, p. 13-20, 2008
[19] S. Qiao , Y. Zhu, X. Li, T. Liu, and B. Zhang, “Research of Improving the Accuracy of License Plate Character Segmentation,” International Conference on Frontier of Computer Science and Technology, 2010
[20] Y. Zhang and C. Zhang, “A new Algorithm for Character Segmentation of License Plate,” IEEE Intelligent Vehicles Symposium, p. 106-109, 2003
[21] F. Kahraman, B. Kurt, and M. Gökmen, “License Plate Character Segmentation Based on the Gabor Transform and Vector Quantization,” Lecture Notes in Computer Science, vol 2869, p. 381-388, 2003
[22] Meenakshi and R. B. Dubey, “Vehicle License Plate Recognition System,” International Journal of Advanced Computer Research, vol 2, p. 78-82, 2012
[23] L. Araújo, S. Pio, and D. Menotti, ”Segmenting and Recognizing License Plate Characters,” SIBGRAPH, 2013
[24] V. K. Keyan, R. Sindhu, K. Anusha, and D.S. Vijith, “Vehicle License Plate Character Segmentation – a Study,” International Journal of Computer and Electronics Research, 2013