Browse > Article
http://dx.doi.org/10.17662/ksdim.2022.18.4.001

Detecting Numeric and Character Areas of Low-quality License Plate Images using YOLOv4 Algorithm  

Lee, Jeonghwan (안동대학교 전자공학과)
Publication Information
Journal of Korea Society of Digital Industry and Information Management / v.18, no.4, 2022 , pp. 1-11 More about this Journal
Abstract
Recently, research on license plate recognition, which is a core technology of an intelligent transportation system(ITS), is being actively conducted. In this paper, we propose a method to extract numbers and characters from low-quality license plate images by applying the YOLOv4 algorithm. YOLOv4 is a one-stage object detection method using convolution neural network including BACKBONE, NECK, and HEAD parts. It is a method of detecting objects in real time rather than the previous two-stage object detection method such as the faster R-CNN. In this paper, we studied a method to directly extract number and character regions from low-quality license plate images without additional edge detection and image segmentation processes. In order to evaluate the performance of the proposed method we experimented with 500 license plate images. In this experiment, 350 images were used for training and the remaining 150 images were used for the testing process. Computer simulations show that the mean average precision of detecting number and character regions on vehicle license plates was about 93.8%.
Keywords
Deep Learning; YOLOv4; Convolution Neural Network(CNN); Vehicle License Plate; Image Recognition;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Q.. Kashif and A.. Hanan., "A Survey on Intelligent Transportation Systems," MiddleEast Journal of Scientific Research. 15. 2013, pp. 629-642.
2 J. Shashirangana, H. Padmasiri, D. Meedeniya, and C. Perera, "Automated License Plate Recognition: A Survey on Methods and Techniques," IEEE Access, Vol. 9, 2021, pp. 11203-11225.   DOI
3 M. A. Lalimi, S. Ghofrani, and D. McLernon, "A Vehicle License Plate Detection Method Using Region and Edge Based Methods," Computers & Electrical Engineering, Vol. 39, No. 3, 2013, pp. 834-845.   DOI
4 Lubna, N. Mufti, and S.A.A. Shah. "Automatic Number Plate Recognition:A Detailed Survey of Relevant Algorithms," Sensors. Vol. 21, No. 9, 2021.
5 김진호, "LPR시스템트리거 신호 생성을 위한 딥러닝 슬라이딩 윈도우 방식의 객체 탐지 및 추적," 디지털산업정보학회논문지, 제17권, 제4호, 2021년, pp. 85-94.   DOI
6 임광용.변혜란.최영우, "도로주행 영상에서의 차량 번호판 검출," 정보과학회논문지, 제43권, 제3호, 2016년, pp. 186-195.
7 R. Chen and Y. Luo. "An Improved License Plate Location Method Based on Edge Detection," Proceeding of International Conference on Applied Physics and Industrial Engineering, 2012, pp. 1350-1356.
8 H. Li, P. Wang, M, You, and C. Shen, "Reading Car License Plates using Deep Neural Networks," Image and Vision Computing, Vol. 72, 2018, pp. 14-23.   DOI
9 정윤주.이스라필 안사리.심재창.이정환, "딥 컨볼루션 신경망을 이용한 자동차 번호판 영역 검출 시스템," 한국멀티미디어학회논문지, 제20권, 제8호, 2017, pp. 1166-1174.   DOI
10 Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, "A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects," IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021. 3084827.   DOI
11 김정환.임준홍, "딥러닝을 이용한 번호판 검출과 인식 알고리즘," 전기전자학회논문지, 제23권 제2호, 2019년, pp. 642-651.   DOI
12 A. Bochkovskiy, C. Wang, and H. Y. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," 2020, ArXiv, abs/2004.10934.
13 S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis & Machine Intelligence, Vol. 39, No. 06, 2017, pp. 1137-1149.   DOI
14 공용해.권춘기.김명숙, "차량 번호판 인식 효율향상을 위한 연구," 한국산학기술학회논문지, 제10권, 제8호, 2009년, pp. 1947-1954.   DOI
15 정일식.박구만, "인조 번호판을 이용한 자동차 번호인식 성능 향상 기법," 방송공학회논문지, 제26권, 제4호, 2021년, pp. 453-462.   DOI
16 자동차 등록번호판 등의 기준에 관한 고시(국토교통부고시 제2022-89호), https://www.law.go.kr/
17 대한민국의 차량 번호판, https://ko.wikipedia.org/wiki/
18 J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788.
19 Getting Started with YOLO v4, https://kr.mathworks.com/help/vision/ug/getting-started-with-yolo-v4.html
20 C. Wang, A. Bochkovskiy, and H. M. Liao, "Scaled-YOLOv4: Scaling Cross Stage Partial Network," 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 13024-13033.
21 Kim, J., J. K. Lee, and K. M. Lee. "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, pp. 1646-1654.
22 김진호, "딥러닝 신경망을 이용한 문자 및 단어단위의 영문 차량 번호판 인식," 디지털산업정보학회논문지, 제16권, 제4호, 2020, pp.19-28.   DOI