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

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

DOI QR Code

A License-Plate Image Binarization Algorithm Based on Least Squares Method for License-Plate Recognition of Automobile Black-Box Image

블랙박스 영상용 자동차 번호판 인식을 위한 최소 자승법 기반의 번호판 영상 이진화 알고리즘

  • Kim, Jin-young (School of Electronic and Electrical Engineering, Hongik University) ;
  • Lim, Jongtae (School of Electronic and Electrical Engineering, Hongik University) ;
  • Heo, Seo Weon (School of Electronic and Electrical Engineering, Hongik University)
  • Received : 2018.01.25
  • Accepted : 2018.04.17
  • Published : 2018.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

In the license-plate recognition systems for automobile black Image, the license-plate image frequently has a shadow due to outdoor environments which are frequently changing. Such a shadow makes unpredictable errors in the segmentation process of individual characters and numbers of the license plate image, and reduces the overall recognition rate. In this paper, to improve the recognition rate in these circumstance, a license-plate image binarization algorithm is proposed removing the shadow effectively. The propose algorithm splits the license-plate image into the regions with the shadow and without. To find out the boundary of two regions, the algorithm estimates the curve for shadow boundary using the least-squares method. The simulation is performed for the license-plate image having its shadow, and the results show much higher recognition rate than the previous algorithm.

자동차 블랙박스 영상용 자동차 번호판 인식 시스템에서는 수시로 변하는 도로 주변의 외부 환경에 의해 자동차 번호판에 그림자가 존재하는 경우가 많이 발생한다. 이러한 그림자는 번호판의 문자와 숫자의 개별 문자 분할 과정에서 예상하지 않은 오류를 발생시키게 되고, 그 결과 전체적인 자동차 번호판 인식률을 저하시킨다. 본 논문에서는 이러한 환경에서 번호판 인식률을 높이고자, 번호판의 그림자를 효과적으로 제거하는 번호판 영상 이진화 알고리즘을 제안한다. 제안한 방법에서는 그림자의 경계를 기준으로 그림자가 드리운 영역과 드리우지 않은 영역으로 분할하는데, 그림자의 경계를 찾기 위해 최소 자승법을 사용하여 그림자 경계선에 대한 곡선을 추정한다. 그림자가 존재하는 자동차 번호판의 영상에 대해 시뮬레이션을 수행하였으며, 그 결과 기존 알고리즘 보다 훨씬 높은 인식률을 보임을 확인하였다.

Keywords

References

  1. S. M. Park and J. Kwak, "The current state of domestic and foreign countries and major security standardization trend of Cooperative Intelligent Transport Systems(C-ITS)," Journal of the Korea Institute of Information Security and Cryptology, vol. 25, no. 5, pp. 53-59, October 2015.
  2. S. G. Jin, "The Next Generation ITS based on IOT," Proceeding of the 2016 Korea Institute of Intelligent Transport Systems Conference, pp.334-335, April 2016.
  3. H. N. Oh and E. G. Rhee, "Enhancement of Car License Plate Recognition Rate and Security with Rotation Algorithm," Journal of Security Engineering, vol.13, no.2, pp. 83-90, April 2016. https://doi.org/10.14257/jse.2016.04.01
  4. J. Y. Kim, S. W. Heo and J. Lim, "A License Plate Recognition Algorithm using Multi-Stage Neural Network for Automobile Black-Box Image," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 1, January 2018.
  5. K. I. Kim, "Binary Connected-component Labelling with Block-based Labels and a Pixel-based Scan Mask," Journal of the Institute of Electronics Engineers of Korea, vol. 50, no. 5, pp. 287-294, May 2013.
  6. S. H. Park and S. W. Cho, "A Vehicle License Plate Recognition Using the Haar-like Feature and CLNF Algorithm," Smart Media Journal, vol. 5, no. 1, pp. 15-23, March 2016.
  7. N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Journals & Magazines, vol. 9, no. 1, pp. 62-66, January 1979.
  8. J. H. Kim and G. B. Kim, "A Binarization Technique using Histogram Matching for License Plate with a Shadow," Journal of Broadcast Engineering, vol. 19, no. 1, pp. 56-63, January 2014. https://doi.org/10.5909/JBE.2014.19.1.56
  9. B. H. Seo, B. M. Kim, C. B. Moon and Y. S. Shin, "Binarization of Number Plate Image with a Shadow," Journal of the Korea Industrial Information Systems Society, vol. 13, no. 4, pp. 1-13, December 2008.