An intelligent system for paper currency verification using support vector machines

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.