With the advancement in imaging technologies for scanning and printing, production of counterfeit banknotes has become cheaper, easier, and more common. The proliferation of counterfeit banknotes causes loss to banks, traders, and individuals involved in financial transactions. Hence, it is inevitably needed that efficient and reliable techniques for detection of counterfeit banknotes should be developed. With the availability of powerful smartphones, it has become possible to perform complex computations and image processing related tasks on these phones. In addition to this, smartphone users have increased greatly and numbers continue to increase. This is a great motivating factor for researchers and developers to propose innovative mobile-based solutions. In this study, a novel technique for verification of Pakistani banknotes is developed, targeting smartphones with android platform. The proposed technique is based on statistical features, and surface roughness of a banknote, representing different properties of the banknote, such as paper material, printing ink, paper quality, and surface roughness. The selection of these features is motivated by the X-ray Diffraction (XRD) and Scanning Electron Microscopy (SEM) analysis of genuine and counterfeit banknotes. In this regard, two important areas of the banknote, i.e., serial number and flag portions were considered since these portions showed the maximum difference between genuine and counterfeit banknote. The analysis confirmed that genuine and counterfeit banknotes are very different in terms of the printing process, the ingredients used in preparation of banknotes, and the quality of the paper. After extracting the discriminative set of features, support vector machine is used for classification. The experimental results confirm the high accuracy of the proposed technique.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited