Nowadays, illegal counterfeit coins are considerably affecting the financial transactions in society. This work proposes an efficient image based fake coin detection, which can be applied to ensure the authenticity of coins. Although several types of fake currency detectors are already existing, fake coin detection still remains as a challenging problem. Image based approach have benefits in terms of cost and ease of usage. The fake coin detection uses a vector space approach, termed as dissimilarity space. It is a vector space constructed by measuring the dissimilarity between the coin image and the prototype. Dissimilarity between the coin images is obtained using the combination of Difference Of Gaussian (DOG) detector and Scale Invariant Feature Transform (SIFT). The proposed system adapts to coin rotation and scaling. In this work, one class learning method is used, so for training the classifier, only genuine Indian coins are needed.

Fake coin, Fake coin detection, One class learning, Dissimilarity space

[1]. B. M. Dobbins and J. E. Vaks, “Method and apparatus for improved coin, bill and other currency acceptance and slug or counterfeit rejection,” U.S. Patent 5 167 313, Dec. 1, 1992.
[2]. T. Nara and T. Ueki, “Coin discriminating apparatus,”U.S. Patent 5 263 566, Nov. 23, 1993.
[3]. Y. Furuya et al., “Method and apparatus for sorting coins utilizing coin-derived signals containing different harmonic components,” U.S. Patent 4 971 187, Nov. 20, 1990.
[4]. K. Okada, “Method and apparatus for discriminating coins or bank notes,” U.S. Patent 4 556 140, Dec. 3, 1985.
[5]. M. Hida, T. Mitsui, and Y. Minami, “Forensic investigation of counterfeit coins, ” Forensic Sci. Int., vol. 89, no. 1, pp. 21–26, 1997.
[6]. M. Hida, H. Sato, H. Sugawara, and T. Mitsui, “Classification of counterfeit coins using multivariate analysis with X-ray diffraction and X-ray fluorescence methods,” Forensic Sci. Int., vol. 115, no. 1, pp. 129–134, 2001.
[7]. Li Liu, Yue Lu, Senior Member, IEEE, and Ching Y. Suen, Life Fellow, IEEE, “An Image-Based Approach to Detection of Fake Coins,” IEEE transactions on information forensics and security, vol. 12, no. 5, may 2017.
[8]. K. Sun et al., “Detection of counterfeit coins based on shape and lettering features,” in Proc. Int. Conf. Comput. Appl. Ind. Eng., 2015, pp. 165–170.
[9]. R. Huber, H. Ramoser, K. Mayer, H. Penz, and M. Rubik, “Classification of coins using an eigenspace approach,” Pattern Recognit. Lett., vol. 26, no. 1, pp. 61–75, 2005.
[10]. D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vis., vol. 60, no. 2, pp. 91–110, Nov. 2004.