臺灣博碩士論文加值系統

隨著城市的發展，人們對於車輛的需求增加，車輛的數量持續的增加，近年來許多研究人員相繼提出車輛管理相關技術，其中車牌辨識系統不僅能夠取代人力也能避免人為疏失，在台灣停車場管理系統採用領取磁卡或者車牌辨識系統，傳統的領取磁卡系統因不方便且不環保所以逐漸淘汰，商用車牌辨識系統卻容易受到角度、光線、距離與速度等限制條件且處理時間較久。
本文提出了一款基於YOLOv4的車牌辨識系統，透過自行蒐集台灣各車種資料集進行訓練，最後在國立高雄科技大學第一校區門口進行測試，所提系統平均車牌偵測率為99.9%，字元識別率為92.7%，可處理角度達正負60°，識別距離可達753cm。所提系統的識別距離與角度都比商用車牌辨識系統更加強大，可運用在停車場出入系統或車輛管理系統。

With the development of city, people increased in demand for vehicle, so the number of vehicles continue to increase, many researchers have proposed various solutions to address vehicle management. For example, Automatic License Plate Recognition (ALPR) not only can replace human workers but also prevent human error. In Taiwan, parking lot toll system use traditional take ticket or ALPR, but traditional system is eliminated in time because of inconvenient and not eco-friendly, then commercial license plate recognition system is limited by angle, light, distance, speed and long process time.
This paper proposes a ALPR system based on YOLOv4. First, we collect various Taiwanese vehicle as training data. Second, targeting a more realistic scenario, we test at our school gate. Finally, Our system achieve license plate detection rate of 99.9%, recognition rate of 92.7%, max correction angle reach 60°and recognition range reach 753cm. Compared with commercial system, our system is more robust and can using in parking lot toll or driveway security gates.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 前言 1
1.2 研究動機 1
1.3 研究目的 2
1.4 論文架構 2
第二章 文獻探討 3
2.1 傳統車牌辨識系統 3
2.1.1 傳統車牌偵測 3
2.1.2 傳統字元分割 4
2.1.3 傳統字元識別 5
2.1.4 車牌視角校正 5
2.2 基於 YOLO之車牌辨識系統 6
第三章 訓練資料集建立 7
3.1 車牌偵測資料集 7
3.2 字元識別資料集 9
3.3 資料集標記說明 10
第四章 研究內容與方法 13
4.1 物件偵測演算法 14
4.1.1 YOLO 14
4.1.2 YOLOv4 17
4.2 Perspective correction 19
4.2.1 Grayscale mean pixel 19
4.2.2 Image contrast 21
4.2.3 Edge detection 22
4.2.4 Hough lines transform 24
4.2.5 Compensated hough line 29
4.2.6 Homography 31
4.3 字元識別 33
第五章 實驗結果 34
5.1 系統開發環境 34
5.2 測試資料說明 35
5.3 測試結果 40
第六章 結論 45
參考文獻 46

[1]中華民國交通部公路總局. "中華民國交通部公路總局." [online]. Available: https://www.thb.gov.tw/.
[2]A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "Yolov4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020.
[3]S. S. Omran and J. A. Jarallah, "Iraqi Car License Plate Recognition Using OCR," in 2017 annual conference on new trends in information & communications technology applications (NTICT), pp. 298-303.
[4]S. Rasheed, A. Naeem, and O. Ishaq, "Automated Number Plate Recognition Using Hough Lines and Template Matching," in Proceedings of the world congress on engineering and computer science, 2012, vol. 1, pp. 24-26.
[5]X. He, L. Zheng, W. Qiang, J. Wenjing, S. Bijan, and M. Palaniswami, "Segmentation of Characters on Car License Plates," in 2008 IEEE 10th Workshop on Multimedia Signal Processing, pp. 399-402.
[6]C. T. Nguyen, T. B. Nguyen, and S. T. Chung, "Reliable Detection and Skew Correction Method of License Plate for PTZ camera-based License Plate Recognition System," in 2015 International Conference on Information and Communication Technology Convergence (ICTC), pp. 1013-1018.
[7]L. Hsi-Jian, C. Si-Yuan, and W. Shen-Zheng, "Extraction and Recognition of License Plates of Motorcycles and Vehicles on Highways," in Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 4, pp. 356-359, 2004.
[8]S. J. Yang, C. C. Ho, J. Y. Chen, and C. Y. Chang, "Practical Homography-Based Perspective Correction Method for License Plate Recognition," in 2012 International Conference on Information Security and Intelligent Control, 14-16, pp. 198-201.
[9]R. Laroca et al., "A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector," in 2018 international joint conference on neural networks (ijcnn), pp. 1-10.
[10]W. Thumthong, P. Meesud, and P. Jarupunphol, "Automatic Detection and Recognition of Thai Vehicle License Plate from CCTV Images," in 2021 13th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 143-146.
[11]R. Smith, "An Overview of the Tesseract OCR Engine," in Ninth International Conference on Document Analysis and Recognition (ICDAR), vol. 2, pp. 629-633, 2007.
[1]中華民國交通部公路總局. "中華民國交通部公路總局." [online]. Available: https://www.thb.gov.tw/.
[2]A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "Yolov4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020.
[3]S. S. Omran and J. A. Jarallah, "Iraqi Car License Plate Recognition Using OCR," in 2017 annual conference on new trends in information & communications technology applications (NTICT), pp. 298-303.
[4]S. Rasheed, A. Naeem, and O. Ishaq, "Automated Number Plate Recognition Using Hough Lines and Template Matching," in Proceedings of the world congress on engineering and computer science, 2012, vol. 1, pp. 24-26.
[5]X. He, L. Zheng, W. Qiang, J. Wenjing, S. Bijan, and M. Palaniswami, "Segmentation of Characters on Car License Plates," in 2008 IEEE 10th Workshop on Multimedia Signal Processing, pp. 399-402.
[6]C. T. Nguyen, T. B. Nguyen, and S. T. Chung, "Reliable Detection and Skew Correction Method of License Plate for PTZ camera-based License Plate Recognition System," in 2015 International Conference on Information and Communication Technology Convergence (ICTC), pp. 1013-1018.
[7]L. Hsi-Jian, C. Si-Yuan, and W. Shen-Zheng, "Extraction and Recognition of License Plates of Motorcycles and Vehicles on Highways," in Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 4, pp. 356-359, 2004.
[8]S. J. Yang, C. C. Ho, J. Y. Chen, and C. Y. Chang, "Practical Homography-Based Perspective Correction Method for License Plate Recognition," in 2012 International Conference on Information Security and Intelligent Control, 14-16, pp. 198-201.
[9]R. Laroca et al., "A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector," in 2018 international joint conference on neural networks (ijcnn), pp. 1-10.
[10]W. Thumthong, P. Meesud, and P. Jarupunphol, "Automatic Detection and Recognition of Thai Vehicle License Plate from CCTV Images," in 2021 13th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 143-146.
[11]R. Smith, "An Overview of the Tesseract OCR Engine," in Ninth International Conference on Document Analysis and Recognition (ICDAR), vol. 2, pp. 629-633, 2007.
[12]A. Tourani, A. Shahbahrami, S. Soroori, S. Khazaee, and C. Y. Suen, "A Robust Deep Learning Approach for Automatic Iranian Vehicle License Plate Detection and Recognition for Surveillance Systems," IEEE Access, vol. 8, pp. 201317-201330, 2020.
[13]G. Hsu, J. Chen, and Y. Chung, "Application-Oriented License Plate Recognition," IEEE Transactions on Vehicular Technology, vol. 62, no. 2, pp. 552-561, 2013.
[14]Tzutalin. "LabelImg." [online]. Available: https://github.com/tzutalin/labelImg.
[15]R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580-587.
[16]R. Girshick, "Fast R-CNN," in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440-1448.
[17]W. Liu et al., "SSD: Single Shot Multibox Detector," in European conference on computer vision, 2016, pp. 21-37.
[18]J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.
[19]K. He, X. Zhang, S. Ren, and J. Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 9, pp. 1904-1916, 2015.
[20]S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, "Path Aggregation Network for Instance Segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8759-8768.
[21]S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, "Cutmix: Regularization Strategy to Train Strong Classifiers with Localizable Features," in Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6023-6032.
[22]J. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679-698, 1986.