International Journal of Control, Automation, and Systems

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Distinctive Point Extraction and Recognition Algorithm for Various Kinds of Euro Banknotes

  • Lee, Jae-Kang (Department of Electrical and Electrical and Computer Engineering, Kangwon National University) ;
  • Jeon, Seong-Goo (Department of Electrical and Electrical and Computer Engineering, Kangwon National University) ;
  • Kim, Il-Hwan (Department of Electrical and Electrical and Computer Engineering, Kangwon National University)
  • Published : 2004.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Counters for the various kinds of banknotes require high-speed distinctive point extraction and recognition. In this paper we propose a new point extraction and recognition algorithm for Euro banknotes. For distinctive point extraction we use a coordinate data extraction method from specific parts of a banknote representing the same color. To recognize banknotes, we trained 5 neural networks. One is used for inserting direction and the others are used for face value. The algorithm is designed to minimize recognition time by using a minimal amount of recognition data. The simulated results show a high recognition rate and a low training period. The proposed method can be applied to high speed banknote counting machines.

Keywords

References

  1. IEEE Trans. on Neural Networks v.7 no.6 A neural network-based model for paper currency recognition and verification A. Frosini;M. Gori;P. Priami https://doi.org/10.1109/72.548175
  2. T. IEE japan v.120-C A proposal of structure method for multi-currency simultaneous recognition using networks F. Takeda;T. Nishikage
  3. IEEE Trans. on Neural Networks v.6 no.1 High-speed paper currency recognition y neural network F. Takeda;S. Omatu https://doi.org/10.1109/72.363448
  4. Journal of Prod. Tech. Res. Center. Daegu v.2 Learning and recognition of bank notes by neural network J.-W. Lee;J.-H. Lee
  5. Fuzzy-Control System S. Lee
  6. Master thesis, Chosun Univ. Recognition of the paper money based on edge clustering I. Kim
  7. Master thesis, Kangwon National Univ. A character recognition using BPN neural network and wavelet K.-S. Yoo
  8. Neural Network Design M. T. Hagan;H. B. Demuth;M. Beale