Bangladeshi banknote recognition by neural network with axis symmetrical masks

Automated banknote recognition system can be a very good utility in banking systems and other field of commerce. It can also aid visually impaired people. Although in Bangladesh, bill money recognition machines are not common but it is used in other countries. In this paper, for the first time, we have proposed a Neural Network based recognition scheme for Bangladeshi banknotes. The scheme can efficiently be implemented in cheap hardware which may be very useful in many places. The recognition system takes scanned images of banknotes which are scanned by low cost optoelectronic sensors and then fed into a Multilayer Perceptron, trained by Backpropagation algorithm, for recognition. Axis Symmetric Masks are used in preprocessing stage which reduces the network size and guarantees correct recognition even if the note is flipped. Experimental results are presented which show that this scheme can recognize currently available 8 notes (1, 2, 5, 10, 20, 50, 100 & 500 Taka) successfully with an average accuracy of 98.57%.

[1]  G. J. Suaning,et al.  Bank note recognition for the vision impaired , 2006, Australasian Physics & Engineering Sciences in Medicine.

[2]  Fumiaki Takeda,et al.  Recognition system of US dollars using a neural network with random masks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[3]  Marco Gori,et al.  A neural network-based model for paper currency recognition and verification , 1996, IEEE Trans. Neural Networks.

[4]  Sigeru Omatu,et al.  High speed paper currency recognition by neural networks , 1995, IEEE Trans. Neural Networks.

[5]  Fumiaki Takeda,et al.  Thai Banknote Recognition Using Neural Network and Continues Learning by DSP Unit , 2003, KES.

[6]  Fumiaki Takeda,et al.  Multiple kinds of paper currency recognition using neural network and application for Euro currency , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[7]  Sigeru Omatu,et al.  Bill Money Recognition by a Small Size Neural Network , 1993 .

[8]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[9]  Sigeru Omatu,et al.  Bill Money Recognition Using Neural Network with FFT as Pre-Processor , 1992 .