Welcome to Open Science
Contact Us
Home Books Journals Submission Open Science Join Us News
Deep Learning Approach for Ethiopian Banknote Denomination Classification and Fake Detection System
Current Issue
Volume 7, 2019
Issue 4 (August)
Pages: 30-37   |   Vol. 7, No. 4, August 2019   |   Follow on         
Paper in PDF Downloads: 107   Since Jan. 10, 2020 Views: 1076   Since Jan. 10, 2020
Asfaw Alene Shefraw Alene Shefraw, Bahir Dar Institute of Fashion and Textile Technology, Bahir University, BahirDar, Ethiopia.
Currently, in banks and the financial institution in Ethiopia, it is most commonly observed to use self-serving devices to outreach their services and also to make payment through for their ordinary customers. But they are unable to fully utilizing their self-serving devices to its fullest capacity. As a result of the automatic software-based fake banknote recognition system, it causes a number of counterfeit banknotes to be flooded in the market. Nevertheless, banks have not yet utilized a reliable recognition system to identify forged banknotes. This calls for the development of a better authenticity verification system. In this study, we have examined the convolutional neural network as a feature extraction technique and feed-forward artificial neural network as a classifier to design the Ethiopian banknote recognition system. This article presents a robust and efficient system for Ethiopian banknote recognition. A high banknote recognition and classification rate were achieved using FFANN as a classifier convolutional neural network as a classifier with real scene images taken from the scanner. From the experimental results, the study observed an average accuracy of 99.4% for classifying the banknote denomination and 96% accuracy for fake currency detection. We, therefore, recommend that a further investigation on the CNN model using advanced architecture like Google Net and ResNet with the larger dataset to study the banknote classification and verification system.
Convolutional Neural Network, Ethiopian Banknote Classification System, Ethiopian Paper Currency Recognition System
Sarfraz and Muhammad. (2015). An intelligent paper currency recognition system. Science Direct /International Conference on Communication, Management and Information Technology.
Sushma R, Nandeesha K, Shreeharsha S, Srinidhi G, and Vijay Raj Gopal R. 2016. Indian Currency Note Denomination Recognition and Validation. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, vol. 5, no. 6.
Soo-Hyeon Lee, and Hae-Yeoun Lee. (2018). Counterfeit Bill Detection Algorithm using Deep Learning. International Journal of Applied Engineering Research, 3.
Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition; Proceedings of the International Conference on Learning Representations; San Diego, CA, USA. 7–9 May 2015; pp. 1–14 [Google Scholar].
Karen Simonyan, Andrew Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2014.
Keto [nurias. (2018, January 10, 2018 10). An-intuitive-explanation-of-whybatchnormalization-really-works-normalization-in-deep-learning-part1. Retrieved from mlexplained.com: http://mlexplained.com/2018/01/10/an-intuitive-explanation-ofwhy-batch-normalization-really-works-normalization-in-deep-learning-part-1/
Jegnaw Fentahun Zeggeye, Yaregal Assabie, "Automatic Recognition and Counterfeit Detection of Ethiopian Paper Currency," I. J. Image, Graphics and Signal Processing, 2016.
Proceedings. Los Alamitos, CA: IEEE Conference on Computer Vision and pattern recognition.
Neetu Sharma, and Kiran Narang. (2017). A review paper on Currency Recognition System. International Journal for Research in Applied Science and Engineering technology.
R. B. H. H. H. a. B. M. K. S. Keerthana Prasad, "Feature extraction using traditional image processing and convolutional neural network methods to classify white blood cells: a study," Australasian Physical & Engineering Sciences in Medicine, vol. 42, no. 2, p. 627–638, 2019.
Thomas, A., & Sreekumar, K. (2014). A survey on image feature descriptors-color, shape and texture. International Journal of Computer Science and Information Technologies, 5 (6), 7847–7850.
Parmar, Ravindra. (2018, Sep 11). Deep Learning Enthusiast. An active member of https. Retrieved from https://towardsdatascience.com/training-deep-neuralnetworks-9fdb1964b964.
Maram. G Alaslani, and Lamiaa A. Elrefaei. (2018). Convolutional neural network-based feature extraction for IRIS recognition. International Journal of Computer Science & Information Technology, 10 (2).
Krizhevsky A., Sutskever I., Hinton G. E. ImageNet classification with deep convolutional neural networks; Proceedings of the Advances in Neural Information Processing Systems; Lake Tahoe, NV, USA. 3–8 December 2012 [Google Scholar].
Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014; 15: 1929–1958 [Google Scholar].
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2019). A Survey of the Recent Architectures of Deep Convolutional Neural Networks. 1–62. Retrieved from http://arxiv.org/abs/1901.06032.
Debasish Biswas, Amitava Nag, Soumadip Ghosh, Arindrajit Pal, Sushanta Biswas, and Snehasish Banerjee, "NOVEL GRAY SCALE CONVERSION TECHNIQUES BASED ON PIXEL DEPTH," Journal of Global Research in Computer Science , vol. 2, no. 6, 2011.
Open Science Scholarly Journals
Open Science is a peer-reviewed platform, the journals of which cover a wide range of academic disciplines and serve the world's research and scholarly communities. Upon acceptance, Open Science Journals will be immediately and permanently free for everyone to read and download.
Office Address:
228 Park Ave., S#45956, New York, NY 10003
Phone: +(001)(347)535 0661
Copyright © 2013-, Open Science Publishers - All Rights Reserved