The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)

Korea Information Electronic Communication Technology (한국정보전자통신기술학회)
권호 표지
DOI QR코드

DOI QR Code

Area Extraction of License Plates Using an Artificial Neural Network

  • Kim, Hyun-Yul (Information and Communication Engineering of Catholic Kwan-Dong University) ;
  • Lee, Seung-Kyu (Information and Communication Engineering of Catholic Kwan-Dong University) ;
  • Lee, Geon-Wha (Information and Communication Engineering of Catholic Kwan-Dong University) ;
  • Park, Young-rok (Information and Communication Engineering of Catholic Kwan-Dong University)
  • Received : 2014.11.05
  • Accepted : 2014.12.03
  • Published : 2014.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In the current study, the authors propose a method for extracting license plate regions by means of a neural network trained to output the plate's center of gravity. The method is shown to be effective. Since the learning pattern presentation positions are defined by random numbers, a different pattern is submitted to the neural network for learning each time, which enables it to form a neural network with high universality of coverage. The article discusses issues of the optimal learning surface for a license plate covered by the learning pattern, the effect of suppression learning of the number and pattern enlargement/reduction and of concentration value conversion. Results of evaluation tests based on pictures of 595 vehicles taken at an under-ground parking garage demonstrated detection rates of 98.5%, 98.7%, and 100%, respectively.

Keywords

References

  1. H. Takahashi, E. Maeda, A. Shio, and K. Ishii. Image recognition techniques for automation of parking garage supervision. NTT R&D, 41, No. 4, pp.4930500,1992.
  2. Y. Handa et al. Development and applications of fast image processing devices. Mitsuvisshi Heavy Industries Review, 27, No. 1, pp. 76-80,1993.
  3. M. Deguchi, K. Kato, G. Miya, And M. Hinenoya. Development of a number plate reading device for computing the travel time. Sumitomo Elctrical Indstries, No. 139, pp. 8-13,1994.
  4. H. Kato et al. Nunber plate recognition techniques. Mitsuvishi Electric Industries Review, 62, No. 2, pp.8-12, 2000.
  5. T. Sai, T. Agui, and M. Nakajima. Nunber Plate region extraction method using adaptive parameter Flat area-restricted half conversion. I.E.I.C.E.(D-II), 72, NO. 4, 99.597-604,2003.
  6. H. Onoue and M. Shiono. Character recognition tests for entire numver plate including Japanese character section. Trans. I.E.I.C.E., PRU92-47(1992).
  7. T. Mishima et al. stuby of car number recognition devices for image proceddion. Trans. I.E.I.C.E., PRU86-94, 2005.
  8. K. Imai, K. Gohara, and Y. Uchigawa. Recognition of laterally written character lines using a 3-layered model. Trans. I.E.I.C.E., PRU91-3 2008.
  9. J. Nishimura and N. Koyama. Learning capability vs input pattern resolution in back prapagation method. Trans. Inst. Proc. Eng. Jpn., 35, No. 11, pp. 2331-2337, 2009.
  10. D.E. Rumdlhart and J.L. McClelland. Parallel Distributed processing, The MIT Press, Vol. 11,2010.