DOI QR코드

DOI QR Code

A license plate detection method based on contour extraction that adapts to environmental changes

주변 환경 변화에 적응하는 윤곽선 추출 기반의 자동차 번호판 검출 기법

  • 표성국 (광운대학교 플라즈마 바이오 디스플레이학과) ;
  • 이강성 (광운대학교 인제니움학부대학) ;
  • 박영수 (광운대학교 인제니움학부대학) ;
  • 이상훈 (광운대학교 인제니움학부대학)
  • Received : 2018.06.28
  • Accepted : 2018.09.20
  • Published : 2018.09.28

Abstract

In this paper, we proposed a license plate detection method based on contour extraction that adapts to environmental changes. The proposed method extracts contour lines using DoG (Difference of Gaussian) to remove unnecessary noise parts in the contour extraction process. Binarization was applied in ugly outline images, and erosion and dilation operations were used to emphasize the contour of the character part. Then, only the outline of the ratio of the characters of the plate was extracted through the ratio of the width and height of the characters. And the case where the outline is the longest is estimated by estimating the characters of the license plate. For the experiment, we applied 130 image data to license plate on the front of the vehicle, oblique environment, and environment images with various backgrounds. I also experimented with motorcycle images of different license plate patterns. Experimental results showed that the detection rate of the oblique image was 93% and that of the various background environment was 70% in the motorcycle image but 98% in the front image.

본 논문에서는 차량 주변 환경의 변화에서도 번호판 영역을 검출하는 연구를 하였다. 그래서 주변 환경 변화에 적응하는 윤곽선 추출 기반의 자동차 번호판 검출 방법을 제안하였다 제안하는 방법은 윤곽선 추출 과정에서 불필요한 잡음 부분을 제거하기 위해 DoG(Difference of Gaussian)을 이용하여 윤곽선을 추출 하였다. 추출한 윤곽선 영상를 이진화하여 Mophology operation을 사용하여 문자부분 윤곽선을 강조시켰다. 그리고 문자의 종횡비를 판별하여 번호판의 문자와 유사한 비율의 윤곽선을 추출하였다. 그리고 윤곽이 가장 길게 이어진 경우를 차량 번호판으로 추정하여 검출 하였다. 본 연구에서는 차량 정면 뿐 아니라 기울어져 있는 차량의 번호판, 차량 주변 환경의 변화를 가지는 차량 번호판 등 다양한 130개의 차량 영상 데이터를 사용하였다. 그리고 번호판의 패턴이 다른 오토바이 영상에서도 실험 하였다. 실험 결과 기울어져 있는 영상은 93%, 다양한 배경 환경에서는 90% 오토바이영상에서는 70%의 검출률을 나타냈으나 정면의 영상에서 98%의 검출률을 나타내었다.

Keywords

References

  1. S. L. Chang, L. S. Chen & Y. C. Chung. (2004). Automatic license plate recognition. IEEE Transactions on Intelligent Transportation Systems, 5(1), 42-53. DOI: 10.1109/TITS.2004.825086
  2. P. Sahare & S. B. Dhok (2018). Multilingual Character Segmentation and Recognition Schemes for Indian Document Images. IEEE Access, 6, 10603 - 10617 DOI: 10.1109/ACCESS.2018.2795104
  3. Amir Hossein Ashtari, Md. Jan Mordin & Mahmood Fathy. An Iranian License Plate Recognition System Based on Color Features, IEEE Transactions on Intelligent Transportation Systems, 15(4), 1690-1705. DOI: 10.1109/TITS.2014.2304515
  4. A. Dev. (2015). A Novel Approach for Car License Plate Detection Based on Vertical Edges. 2015 Fifth International Conference on Advances in Computing and Communications (ICACC). (pp.391-394). Kochi : India
  5. A. Mayan, K. A. Deep & M. Kumar. (2017.). Number Plate Recognition using Template Comparison for various fonts in MATLAB, 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Chennai : India
  6. Lele Xie, Tasweer Ahmad & Lianwen Jin. (2018). A New CNN-Based Method for Multi-Directional Car License Plate Detection, IEEE Transactions on Intelligent Transportation Systems, 19(2). 507-517. DOI: 10.1109/TITS.2017.2784093
  7. Lu Min & Zheng Ling Xiang. (2007, Dec). Contour Detection based on Gabor filter and directional DoG filter, 2007 14th International Conference on Mechatronics and Machine Vision in Practice, (pp.185-190). Xiamen : China
  8. Jing-Ming Guo & Yun-Fu Liu. (2008). License Plate Localization and Character Segmentation With Feedback Self-Learning and Hybrid Binarization Techniques, IEEE Transactions on Vehicular Technology, 57(3). 1417-1424. DOI: 10.1109/TVT.2007.909284
  9. Gibreal-Elamin Abo-Samra. (2018). Application independent localisation of vehicle plate number using multi-window-size binarisation and semi-hybrid genetic algorithm, The Journal of Engineering, 2018(2). 104-116. DOI:10.1049/joe.2017.0815
  10. Abbas M. Al-Ghaili, Syamsiah Mashohor & Abdul Rahman Ramli. (2013). Vertical-Edge-Based Car- License-Plate Detection Method, IEEE Transactions on Vehicular Technology, 62(1). 26-38. DOI: 10.1109/TVT.2012.2222454
  11. Yirui Wu, Palaiahnakote Shivakumara & Tong Lu, (2016). Contour Restoration of Text Components for Recognition in Video/Scene Images, IEEE Transactions on Image Processing, 25(12). 5622-5634. DOI: 10.1109/TIP.2016.2607426
  12. M. Wafy & Ahmed M.M. Madbouly. (2016). Efficient method for vehicle license plate identification based on learning a morphological feature, IET Intelligent Transport Systems, 10(6). 389-395. DOI: 10.1049/iet-its.2015.0064
  13. J. Yepez & S. B. Ko. (2018). Improved license plate localisation algorithm based on morphological operations, IET Intelligent Transport Systems, 12(6). 542-549. DOI: 10.1049/iet-its.2017.0224
  14. L. Xuan & Z. Hong. (2017). An Improved Canny Edge Detection Algorithm, 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), (pp.275-278) Beijing : China
  15. J.Dun, S.Zhang, X. Ye & Y. Zhang. (2015). Chinese License Plate Localization in Multi-Lane with Complex Background Based on Concomitant Colors. IEEE Intelligent Transportation Systems Magazine, 7(3), 51-61. DOI: 10.1109/MITS.2015.2412146