An intelligent system for paper currency verification using support vector machines

Document Type : Article

Authors

1 Department of Information Science, Kuwait University, Adailiya Campus, P.O. Box 5969, Safat 13060, Kuwait

2 Department of Computer Science, COMSATS University Islamabad, Lahore Campus, 1.5 KM Defence Road, Off Raiwind Road, Lahore, Pakistan

3 Department of Computer Science, COMSATS University Islamabad, Abbottabad Campus, Tobe Camp, Abbottabad-22060, Pakistan

Abstract

In recent years, with the advent of digital imaging technology such as color printers and color scanners, it has become easier for counterfeiters to produce fake banknotes. The spread of counterfeit money causes loss to everyone involved in financial transactions. Therefore, an effective and reliable   verification technique is necessary for successful and reliable financial transactions. This paper presents a cognitive computation based technique for paper currency verification. In this regard, Scanning Electron Microscopy (SEM) and X-ray Diffraction (XRD) analysis of counterfeit and genuine banknotes are performed. This experimentation confirmed that, material used in preparation of genuine and counterfeit banknotes is totally different from each other. Based on these findings, a set of discriminative and robust features is proposed to reflect these differences in currency images. The proposed features represent the material of the banknote such as printing ink, chemical composition, and surface coarseness of the banknotes. With these robust features, Support Vector Machines (SVMs) is employed for classification. In order to evaluate the performance of proposed technique, experimentations are performed on a self-constructed dataset of Pakistani banknotes, comprised of 195 currency images, including 35 counterfeit banknotes. The results confirm that proposed system achieves 98.57% verification ability on properly captured images.
 

Keywords

Main Subjects


1. Czubenko, M., Kowalczuk, Z., and Ordys, A. Autonomous driver based on an intelligent system of decision-making", Cognitive Computation, 7(5), pp. 569-581 (2015). 2. Yin, Z., Niu, X., Zhou, Z., Tang, J., and Luo, B. Improved reversible image authentication scheme", Cognitive Computation, 8(5), pp. 890-899 (2016). 3. Spratling, M.W. A hierarchical predictive coding model of object recognition in natural images", Cognitive Computation, 9(2), pp. 151-167 (2017).
4. Tu, Z., Abel, A., Zhang, L., Luo, B., and Hussain, A. A new spatio-temporal saliency-based video object segmentation", Cognitive Computation, 8(4), pp. 629- 647 (2016). 5. Vila, A., Ferrer, N., Mantecon, J., Breton, D., and Garcia, J.F. Development of a fast and nondestructive procedure for characterizing and distinguishing original and fake euro notes", Analytica Chimica Acta, 559(2), pp. 257-263 (2006). 6. Chang, C.C., Yu, T.X., and Yen, H.Y. Paper currency veri cation with support vector machines", Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, SITIS'07., pp. 860-865 (2007). 7. Yeh, C.Y., Su, W.P., and Lee, S.J. Employing multiple-kernel support vector machines for counterfeit banknote recognition", Applied Soft Computing, 11(1), pp. 1439-1447 (2011). 8. Spagnolo, G.S., Cozzella, L., and Simonetti, C. Currency veri cation by a 2D infrared barcode", Measurement Science and Technology, 21(10), p. 107002 (2010). 9. Xie, J., Qin, C., Liu, T., He, Y., and Xu, M. A new method to identify the authenticity of banknotes
based on the texture roughness", IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1268-1271 (2009). 10. Yoshida, K., Kamruzzaman, M., Jewel, F.A., and Sajal, R.F. Design and implementation of a machine vision based but low cost stand-alone system for real 70 M. Sarfraz et al./Scientia Iranica, Special Issue on: Socio-Cognitive  Engineering 26 (2019) 59{71 time counterfeit Bangladeshi bank notes detection", 10th International Conference on Computer and Information Technology (iccit), pp. 1-5 (2007). 11. Frosini, A., Gori, M., and Priami, P. A neural
network-based model for paper currency recognition and veri cation", IEEE Transactions on Neural Networks,
7(6), pp. 1482-1490 (1996). 12. Sargano, A.B., Sarfraz, M., and Haq, N. An intelligent system for paper currency recognition with robust features", Journal of Intelligent & Fuzzy Systems, 27(4), pp. 1905-1913 (2014). 13. Yadav, B.P., Patil, C.S., Karhe, R.R., and Patil, P.H., Indian currency recognition and veri cation system using image processing", International Journal of Engineering Science and Innovative Technology (IJESIT), ISSN: 2319-5967 ISO 9001: 2008 Certi ed,
3(4), pp. 943-947 (2014). 14. Lavanya, K. and Reddy, T.B. An hidden security features for the recognition of fake currency", International Journal of Advanced Research in Computer Science, 9(2), pp. 292-299 (2018). 15. Annual Report of the Central Bank of the Russian Federation (2010). 16. Hassanpour, H. and Farahabadi, P.M. Using hidden Markov models for paper currency recognition", Expert Systems with Applications, 36(6), pp. 10105-10111 (2009). 17. Gonzalez, R.C. and Woods, R.E., Digital Image Processing, Pearson Education (2009). 18. Tang, C.H. Techniques of discriminating machine for RMB banknotes [j]", Instrumentation Technology, 4, pp. 80-81 (2005). 19. Akbari, A.A., Fard, A.M., and Chegini, A.G. An e ective image based surface roughness estimation approach using neural network", World Automation
Congress, WAC'06, pp. 1-6 (2006). 20. Rosenfeld, A. and Troy, E.B., Visual Texture Analysis, No. TR-70-116, ORO-3662-10, Maryland Univ., College Park (USA), Computer Science Center (1970). 21. Jain, A.K. and Karu, K. Learning texture discrimination masks", IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(2), pp. 195-205 (1996).
22. Sun, X. Research on image content retrieval", The Doctor Degree Paper of Najing University of Science & Technology, China, pp. 40-62 (2001). 23. Vapnik, V., Statistical Learning Theory, Wiley, New York (1998). 24. Pham, T.D., Kim, K.W., Kang, J.S., and Park, K.R. Banknote recognition based on optimization of discriminative regions by genetic algorithm with onedimensional visible-light line sensor", Pattern Recognition, 72, pp. 27-43 (2017). 25. Dittimi, T.V., Hmood, A.K., and Suen, C.Y. Multiclass SVM based gradient feature for banknote recognition", IEEE International Conference on Industrial Technology (ICIT), pp. 1030-1035 (2017). 26. Murthy, S., Kurumathur, J., and Reddy, B.R. Design
and implementation of paper currency recognition with counterfeit detection", IEEE International Conference on Green Engineering and Technologies (IC-GET), pp. 1-6 (2016). 27. Hlaing, K.N.N. and Gopalakrishnan, A.K. Myanmar
paper currency recognition using GLCM and k-NN", IEEE Second Asian Conference on Defence Technology (ACDT), pp. 67-72 (2016). 28. Zeggeye, J.F. and Assabie, Y. Automatic recognition and counterfeit detection of Ethiopian paper
currency", International Journal of Image, Graphics & Signal Processing, 8(2), pp. 28-36 (2016). 29. Yan, W.Q., Chambers, J., and Garhwal, A. An empirical approach for currency identi cation", Multimedia Tools and Applications, 74(13), pp. 4723-4733 (2015). 30. Singh, S., Choudhury, S., Vishal, K., and Jawahar, C.V. Currency recognition on mobile phones", IEEE
22nd International Conference on Pattern Recognition (ICPR), pp. 2661-2666 (2014). 31. Garca-Lamont, F., Cervantes, J., and Lopez, A. Recognition of Mexican banknotes via their color and texture features", Expert Systems with Applications,
39(10), pp. 9651-9660 (2012).