The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

An Implementation of Pattern Recognition Algorithm for Fast Paper Currency Counting

고속 지폐 계수를 위한 패턴 인식 알고리즘 구현

  • Received : 2014.05.21
  • Accepted : 2014.06.19
  • Published : 2014.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we suggest an efficient image processing method for fast paper currency counting with pattern recognition. The patterns are consisted of feature data in each note object extracted from full reflection image of notes and a general contact image sensor(CIS) is used to aggregate the feature images. The proposed pattern recognition algorithm can endure image variation when the paper currency is scanned because it is not sensitive to changes of image resulting in successful note recognition. We tested 100 notes per denomination and currency of several countries including Korea, U.S., China, EU, Britain and Turkey. To ensure the reliability of the result, we tested a total of 10 times per each direction of notes. We can conclude that this algorithm will be applicable to commercial product because of its successful recognition rates. The 100% recognition rates are obtained in almost cases with exceptional case of 99.9% in Euro and 99.8% in Turkish Lira.

본 논문에서는 권종 인식을 위하여 범용 CIS(contact image sensor)를 사용하여 각 권종별로 취득된 지폐 반사 전체 이미지의 특징 데이터(feature data) 성분을 추출하여 권종 인식의 데이터로 사용함으로써 개별 객체의 특색이나 특징들의 집합인 패턴을 이용한 효과적인 이미지 처리 방법을 제안하였다. 본 논문에서 제안한 방법을 통하여 각 권종별 추출된 이미지의 특징 데이터는 이미지 변화에 덜 민감하면서 공간적인 분포를 잘 나타내기 때문에 권종 인식을 하는데 있어서 우수한 방법이 될 수 있다. 제안된 알고리즘의 테스트를 위하여 시료 진폐는 각 국가 및 권종 당 100매씩을 테스트 하였으며, 제한적인 시료로 인한 판정 결과의 신뢰도를 확보하고자 방향별 총 10회씩 투입하였다. 시험 결과 한국 원화는 100% 인식하였으며, 유로화는 5유로의 경우 99.9%, 20유로의 경우 99.8%의 인식률을 보였으며, 터키 리라화는 20리라의 경우 99.8.%, 50리라의 경우 99.8%의 인식률을 보였고, 나머지 미국 달러화, 중국 위안화, 영국 파운드화 등의 권종은 100% 인식되어 제안된 알고리즘이 상용 제품에 적용 가능함을 보였다.

Keywords

References

  1. Y. H. Cho, S. H. Lee, and I. H. Seo, "Development of high-speed paper currency recognition system based on Bayesian rule," in Proc. KIEE Summer Conf., pp. 2474-2476, 2004.
  2. F. Takeda and T. Nishikage, "Multiple kinds of paper currency recognition using neural network and application for euro currency," in Proc. IEEE-INNS-ENNS Int. Joint Conf. Neural Networks (IJCNN 2000), vol. 2, pp. 143-147, Como, Jul. 2000.
  3. E.-H. Zhang, B. Jiang, J.-H. Duan, and Z.-Z. Bian, "Research on paper currency recognition by neural networks," in Proc. Int. Conf. Machine Learning and Cybernetics, vol. 4, pp. 2193-2197, Nov. 2003.
  4. H. Hassanpour, A. Yaseri, and G. Ardeshiri, "Feature extraction for paper currency recognition," in Proc. Int. Symp. Signal Processing and Its Applications, ISSPA 2007, pp. 1-4, Sharjah, Feb. 2007.
  5. S. C. Kim, Banknote recognition and defect detection by edge histogram and mean-variance, Master Dissertation, Hanyang University, 2012
  6. J. W. Lee and J. H. Lee, "Learning and recognition of banknotes by using neural network," J. Research Inst. Production Technol., Kyungsung University, vol. 2, pp. 67-76, Dec. 1995.
  7. Y. C. Park, A study on learning fuzzy controller based on neural networks, Master Dissertation, Chungang University, 2000.
  8. R. E. Neapolitan, Learning Bayesian Networks, Prentice-Hall, 2004.
  9. F. Takeda and S. Omatu, "High speed paper currency recognition by neural networks," IEEE Trans. Neural Netw., vol. 6, no. 1, pp. 73-77, 1995. https://doi.org/10.1109/72.363448
  10. A. Frosini, M. Gori, and P. Priami, "A neural network-based model for paper currency recognition and verification," IEEE Trans. Neural Netw., vol. 7, no. 6, pp. 1482-1490, 1996. https://doi.org/10.1109/72.548175
  11. Martin T. Hagan, Howard B. Demuth, and Mark Beale, Neural Network Design, Boston, PWS Publishing Company, 1995.
  12. S. H. Chae, Y. T. Seo, and S. B. Ban, "The study to distinguish kinds of banknote using color and size elements," in Proc. KIIT Summer Conf., pp. 234-237, 2009.
  13. C. J. Lee, B. H. Son, and H. S. Hong, "Improvement of pattern recognition capacity of the fuzzy ART with the variable learning," J. KICS, vol. 38, no. 12, pp. 954-961, Dec. 2013. https://doi.org/10.7840/kics.2013.38B.12.954
  14. Y. S. Kang and C. S. Bae, "License plates detection using a Gaussian window," J. KICS, vol. 37, no. 9, pp. 780-785, Sept. 2012.
  15. B. H. Song, M. S. Choi, J. W. Kwon, and S. R. Lee, "A design and implementation of digital vessel context diagnosis system based on context aware," J. KICS, vol. 35, no. 6, pp. 859-866, Jun. 2010.
  16. E. W. Cho, E. S. Ahn, J. K. Lee and I. H. Kim, "Feature abstraction and recognition algorithm for various kinds of banknote counting," J. Research Inst. Ind. Technol., Kangwon National University, vol. 22, no. A, pp. 101-105, 2002.