한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

다중퍼셉트론을 이용한 자동차 번호판의 최적 입출력 노드의 비율 결정에 관한 연구

Recognition of characters on car number plate and best recognition ratio among their layers using Multi-layer Perceptron

  • 투고 : 2015.12.21
  • 심사 : 2016.01.24
  • 발행 : 2016.01.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

자동차 번호판 인식은 뺑소니차량의 추적이나 교통량의 측정, 교통사고의 조사 및 차량의 증가에 따른 차량범죄의 추적에 이용되고 있다. 실제 적용되는 교통 환경에서는 눈이나 비 그리고 주야간의 조명 변화에 따라서 입력되는 영상에 외란의 영향을 받기 쉬우며, 또한 영상을 촬영하는 순간의 차량의 직진방향과 카메라가 보는 방향에 따라서 동일한 번호판에 대해서도 기하학적으로 변형된 영상이 입력되게 된다. 본 연구에서는 이러한 카메라를 이용한 번호판 인식 환경의 문제를 해결하는 방법으로 호모그래피를 이용하여 기하학적으로 변형된 영상을 원래의 영상으로 변환하는 방법과 투영 히스토그램을 이용한 문자의 분리 방법을 제안하였다. 분리된 영상은 다중 퍼셉트론방법을 이용하여 문자와 숫자를 인식하였고 특히 최적한 입력, 은닉, 출력 층의 비율을 실험을 통하여 도출 하였다.

The Car License Plate Recognition(: CLPR) is required in searching the hit-and-run car, measuring the traffic density, investigating the traffic accidents as well as in pursuing vehicle crimes according to the increasing in number of vehicles. The captured images on the real environment of the CLPR is contaminated not only by snow and rain, illumination changes, but also by the geometrical distortion due to the pose changes between camera and car at the moment of image capturing. We propose homographic transformation and intensity histogram of vertical image projection so as to transform the distorted input to the original image and cluster the character and number, respectively. Especially, in this paper, the Multilayer Perceptron Algorithm(: MLP) in the CLPR is used to not only recognize the charcters and car license plate, but also determine the optimized ratio among the number of input, hidden and output layers by the real experimental result.

키워드

참고문헌

  1. H. Kim, P. Lee, and Y. Kim, "Development of Image processing algorithm on recognition of kind of car and position as well as recognition of car number plate," ICROS, Proc. of the 12th KACC, Phoenix, USA, Oct. 1977, pp. 1718-1721.
  2. D. Kim, S. Lee, M. Kim, and E. Cha, "A study on extraction and recognition of car number plate," Korean Institute of Scientists and Engineers Conf. Proc. Wuhan, China, Oct. 2000, pp. 338-340.
  3. K, Kim and J. Jo, " Recognition of Car Licence Plate Using Fuzzy Networks,," J. of the Korea Society of Computer and Information, vol. 12 no. 5 2007, pp. 313-319
  4. J. Lee and J. Kim, "Recognition of a New Car Plate using Color Information and Error Back-propagation Neural Network Algorithms," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 5, 2010, pp.471-476.
  5. E. Lee, B. Shun, and W. Lee, "Comparative analysis of vehicle license plate recognition algorithm," 2013 Conf. on Information and Control Systems, New Orleans, USA, Nov., 2009, pp. 249-250.
  6. E. Lee, B. Shung, and W. Lee, "A study on Car License Plate Recognition using Multiplayer Perceptron," 29th Institute of Control, Robottics and System Conf., Phoenix, USA, Apr., 2001, pp. 249-250.
  7. S. Jung, "An Efficient Car Management System based on an Object-Oriented Modeling using Car Number Recognition and Smart Phone," J. of the Korea Institute of Electronic Communication Sciences, vol. 5, no. 5, 2012, pp. 471-476.
  8. J. Cho, "Enhanced Fuzzy Binarization Method for Car License Plate Binarization," J. of the Korea Institute of Electronic Communication Sciences, vol. 6, no. 2, 2011, pp. 231-236.
  9. W. Lee and H. Lee, "Error Minimized Laser Beam Point Detection Using Mono-Camera," J. of the Korea Society of Computer and Information, vol. 12, no. 6, 2007, pp. 69-76.
  10. J. Ha, D. Kang, M. Jung, and W. Lee, "Robust segmentation of characters marked on surface." Intelligent Computing in Signal Processing and Pattern Recognition. Springer Berlin Heidelberg, 2006. pp. 478-487.
  11. K. Chong and S. Zak, An introduction to Optimization. 2nd Ed., Wiley, 2001.