Abstract
In our previous researches, some kinds of neuro-system using multiplayer feedforward network with the sigmoid function were applied to recognize currencies. Although they are effective on known patterns recognition, they suffer from unknown patterns rejection. In this paper, a new activation function is proposed to improve rejection capabilities of the system on the premise of ensuring the effectiveness on known patterns recognition. The simulation shows the effectiveness of this activation function on aspects of rejection for unknown patterns and recognition for known patterns compared with the commonly used sigmoid function.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Takeda, F., Omatu, S.: High Speed Paper Currency Recognition by Neural Networks. IEEE Trans. on Neural Networks 6(1), 73–77 (1995)
Takeda, F., Omatu, S., Onami, S.: Recognition System of US Dollars Using a Neural Network with Random Masks. In: Proceedings of the International Joint Conference on Neural Networks, vol. 2, pp. 2033–2036 (1993)
Takeda, F., Omatu, S.: A Neuro-Paper Currency Recognition Method Using Optimized Masks by Genetic Algorithm. In: Proceedings of IEEE International Conference on Systems, Man and Cybernetics, vol. 5, pp. 4367–4371 (1995)
Takeda, F., Omatu, S., Matsumoto, Y.: Development of High Speed Neuro-Recognition Unit and Application for Paper Curency. In: The International Workshop on Signal Processing Application and Technology, pp. 49–56 (1998)
Takeda, F., Nishikage, T., Matsumoto, Y.: Characteristic Extraction of Paper Currency using Symmetrical Masks Optimized by GA and Neuro-Recognition of Multi-National Paper Currency. In: Proceedings of IEEE World Congress on Computation Intelligence, vol. 1, pp. 634–639 (1998)
Takeda, F., Nishikage, T., Omatu, S.: Banknote Recognition by Means of Optimized Masks, Neural Network, and Genetic Algorithm. Engineering Applications of Artificial Intelligence 12, 175–184 (1999)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)
Takeda, F., Nishikage, T.: Development of a neuro-templates matching recognition method for banknotes. Trans. IEE of Japan 121-C(1), 196–205 (2001)
Takeda, F., Tanaka, M.: A Rejecting Method of Non-objective Currencies using Multi-dimensional Gaussian PDF for Neuro-Multi National Currency Recognition. Trans. IEE of Japan 118-D(12), 1361–1369 (1998)
Bishop, C.M.: Neural Network for Patter n Recognition. Oxford University Press, New York (1995)
Widrow, B., Winter, R.G., Baxter, R.A.: Layered Neural Nets for Pattern Recognition. IEEE Transaction Acoustic, Speech & signal Preprocessing 36(7), 1109–1118 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sun, B., Takeda, F. (2004). Proposal of Neural Recognition with Gaussian Function and Discussion for Rejection Capabilities to Unknown Currencies. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3213. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30132-5_116
Download citation
DOI: https://doi.org/10.1007/978-3-540-30132-5_116
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23318-3
Online ISBN: 978-3-540-30132-5
eBook Packages: Springer Book Archive