Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

A High Performance License Plate Recognition System

고속처리 자동차 번호판 인식시스템

  • Published : 2002.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

This Paper describes algorithm to extract license plates in vehicle images. Conventional methods perform preprocessing on the entire vehicle image to produce the edge image and binarize it. Hough transform is applied to the binary image to find horizontal and vertical lines, and the license plate area is extracted using the characteristics of license plates. Problems with this approach are that real-time processing is not feasible due to long processing time and that the license plate area is not extracted when lighting is irregular such as at night or when the plate boundary does not show up in the image. This research uses the gray level transition characteristics of license plates to verify the digit area by examining the digit width and the level difference between the background area the digit area, and then extracts the plate area by testing the distance between the verified digits. This research solves the problem of failure in extracting the license plates due to degraded plate boundary as in the conventional methods and resolves the problem of the time requirement by processing the real time such that practical application is possible. This paper Presents a power automated license plate recognition system, which is able to read license numbers of cars, even under circumstances, which are far from ideal. In a real-life test, the percentage of rejected plates wan 13%, whereas 0.4% of the plates were misclassified. Suggestions for further improvements are given.

본 논문에서는 차량의 후면에서 촬영한 영상을 이용하여 효과적으로 번호판을 추출하고, 그 안에 표기된 문자를 인식하는 방법을 제안한다. 기존의 연구방법은 전체영상에 대하여 전처리를 수행하여 에지(edge)영상을 구하여 이진화한다. 이진화된 영상에서 허프(Hough)변환을 수행하여 수평, 수직선을 구하고, 번호판의 특징을 이용하여 번호판 영역을 추출한다 이 방법의 문제점은 처리시간이 많이 소요되므로 실시간 처리가 곤란하다는 점과 야간관 같이 명암상태가 불규칙하고 영상에서 번호판 테두리가 나타나지 않으면 번호판 영역추출을 할 수 없다는 점이다. 또한 차량의 후면에서 촬영한 영상에서 번호판 영역의 명암값 변화의 특성을 이용하여 번호판 영역에서 숫자폭, 배경영역과 숫자영역의 명암차를 조사하여 숫자영역임을 확인하고, 확인된 숫자와 숫자사이의 거리를 조사하여 번호판 영역을 추출한다. 본 연구는 기존방법의 번호판 테두리 훼손에 따른 번호판 영역추출 실패의 문제점을 해결하고 시간 소요의 문제를 실시간 안에 처리함으로써 실용적 응용이 가능하다. 실험 결과 100장의 샘플영상으로 실험한 결과 멀리 있는 자동차 영상에서도 자동으로 번호판을 판독할 수 있었으며, 번호판 추출에 실패한 영상은 13%를 나타내었고, 문자 인식에 실패한 영상은 0.4%의 결과를 나타내었다

Keywords

References

  1. D.W. Tindall, 　Deployment of automatic licenseplaterecognition systems in multinational environments, European Conference on Security and Detection 1997, pp. 28-30
  2. S. Draghici, 　A neural network based artificial vision system for license plate recognition, Int. J. on Neural Systems. Feb. 1997, Vol.8, Iss, I, pp.113-126 https://doi.org/10.1142/S0129065797000148
  3. T. Sato, H. Sato, S. Ozawa, M. Komatsu, A. Kobayashi and M. Sato, 　Motion blur correction of license plate images on running vehicle, Trans. IEE Japan, June 1997, Vol.117-C, Iss.6, pp.777-784
  4. Y.T. Cui and Q. Huang, 　Character extraction of license plates from video, proc. IEEE Computer Society Conf. On Computer Vision and pattern Recognition 17-19 June 1997, pp.502-507
  5. H. Fujiyoshi, T. Umezaki, T. Imamura and T. Kanade, 　Area extraction of the license plate using artificial neural netwotk, Trans. Of the Instirue of Electronics, Information and Communication Engineers D-II, June 1997, Vol. J80D-II, Iss.6. pp.1627-1634
  6. T. Hori, Traffic camera system development, proc. SPIE Feb.1997, Vol.3028, pp.81-90 https://doi.org/10.1117/12.270334
  7. T. Agui, H.J. Choi and M. Nakajima, Method of extracting car number plates by image processing, Systems and Computers in Japan, 1998, Vol.19, no.3, pp.46-52 https://doi.org/10.1002/scj.4690190305
  8. M.H ter Brugge, J.H. Stevens, J.A.G. Nijhuis, L. Spaanenburg, License plate recognition using DTCNNs, proc CNNA 1998, pp.212-217
  9. R.J De Ia Haye,　A license plate recognition system, Eindhoven Univ, of Technology, 1998, Master Thesis
  10. Philips Centre for Manufacturing Technology, Kenteken verwerking (KENER)(processing of license plates, in Dutch), design documentation, 1993
  11. R.C Gonzalez, and R.E. woods, Digital image processing, first edition, Addisson-Wesley publishing Company, 1993, ISBN 0-201- 50803-6
  12. B. Fukunaga, Introduction to statistical pattern recognition, Academic London, 1990