DOI QR코드

DOI QR Code

A License Plate Recognition Algorithm using Multi-Stage Neural Network for Automobile Black-Box Image

다단계 신경 회로망을 이용한 블랙박스 영상용 차량 번호판 인식 알고리즘

  • Kim, Jin-young (Department of Electronic and Electrical Engineering, Hongik University) ;
  • Heo, Seo-weon (Department of Electronic and Electrical Engineering, Hongik University) ;
  • Lim, Jong-tae (Department of Electronic and Electrical Engineering, Hongik University)
  • Received : 2017.08.30
  • Accepted : 2017.10.12
  • Published : 2018.01.31

Abstract

This paper proposes a license-plate recognition algorithm for automobile black-box image which is obtained from the camera moving with the automobile. The algorithm intends to increase the overall recognition-rate of the license-plate by increasing the Korean character recognition-rate using multi-stage neural network for automobile black-box image where there are many movements of the camera and variations of light intensity. The proposed algorithm separately recognizes the vowel and consonant of Korean characters of automobile license-plate. First, the first-stage neural network recognizes the vowels, and the recognized vowels are classified as vertical-vowels('ㅏ','ㅓ') and horizontal-vowels('ㅗ','ㅜ'). Then the consonant is classified by the second-stage neural networks for each vowel group. The simulation for automobile license-plate recognition is performed for the image obtained by a real black-box system, and the simulation results show the proposed algorithm provides the higher recognition-rate than the existing algorithms using a neural network.

본 논문은 차량과 함께 카메라의 위치가 이동하는 블랙박스 영상을 위한 차량 번호판 인식 알고리즘을 제안한다. 카메라의 흔들림이나 빛의 변화가 많은 블랙박스 영상에서 다단계 신경 회로망을 사용하여 한글 문자의 인식률을 높여 전체적인 차량 번호판의 인식률을 높이고자 한다. 제안한 알고리즘은 차량 번호판의 한글 문자의 모음과 자음을 분리하여 인식한다. 먼저, 1차 신경 회로망으로 모음을 인식하고, 종모음('ㅏ','ㅓ')과 횡모음('ㅗ','ㅜ')로 구분한 뒤 각각의 모음군에 2차 신경 신경회로망을 이용하여 자음을 구분한다. 실제 블랙박스 영상을 획득하여 차량 번호판 인식 시뮬레이션을 수행하였으며, 그 결과 제안한 인식 시스템이 기존의 신경 회로망 기법을 사용한 차량 번호판 인식 시스템보다 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)," Review of 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," Proceedings of The 2016 Korea Institute of Intelligent Transport Systems Conference, pp.334-335, April 2016.
  3. H. N. Oh and E. G. R, "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. N. W. Kim and C. W. Hur, "Study on Performance Evaluation of Automatic license plate recognition program using Emgu CV," Journal of the Korea Institute of Information and Communication Engineering, vol. 20, no. 6, pp. 1209-1214, June 2016. https://doi.org/10.6109/jkiice.2016.20.6.1209
  5. M. Y. Jin, J. B. Park, D. S. Lee and D. S. Park, "Real-Time Vehicle License Plate Recognition System Using Adaptive Heuristic Segmentation Algorithm," Korean Information Processing Society transactions on software and data engineering , vol. 3, no. 9, pp. 361-368, September 2014.
  6. S. H. Park and S. W. Cho, "A Vehicle License Plate Recognition Using the Feature Vectors based on Mesh and Thinning," Journal of Korean Institute of Intelligent Systems, vol. 21, no. 6, pp. 705-711, December 2011. https://doi.org/10.5391/JKIIS.2011.21.6.705
  7. D. H. Park, J. G. Seo, J. H. Kim, S. S. Jin, J. H. Lee, T. S. Yun, H. Lee, B. Xu and Y. W. Lim, "A Study on Environmentally Adaptive Real-Time Lane Recognition Using Car Black Box Video Images," Proceedings of the Korean Society of Computer and Information Conference, vol. 23, no. 2, pp. 187-190, July 2015.
  8. S. J. Han, H. I. Chung and H. S. Hahn, "Vehicle Detection Scheme Based on the Symmetry of Horizontal and Vertical Edge Features," Proceedings of the Korean Institute of Electrical Engineers Conference, pp. 1851-1852, July 2009.
  9. D. H. Kim, H. Y. Jung, H. Cho and E. Y. Cha, "An Effective Binarization Method for Character Image," The Journal of the Korea Institute of Maritime Information & Communication Sciences, vol. 10, no. 10, pp. 1877-1884, June 2006.
  10. 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.
  11. Y. M. Bae and S. K. Kim "Analysis of Improve on Korea License Plates Design," Proceedings of the Korea Society of Design Science Conference, pp. 56-57, October 2007.
  12. M. S. Kim and Y. H. Kong "A Study on the Effective Feature Extracting for a Plate Recognition," Journal of Advanced Information Technology and Convergence, vol. 5, no. 2, pp. 128-136, June 2007.
  13. M. S. Yang, H. S. Choi, Y. S. Kim, G. H. Kim and O. B. Jang "Grapheme Segmentation of Handwritten Korean Character by Structural Pattern," Journal of Korean Institute of Information Scientists and Engineers, vol. 21, no. 2, pp. 419-422, October 1994.