Abstract
Currency identification is the application of systematic methods to determine authenticity of questioned currency. However, identification analysis is a difficult task requiring specially trained examiners, the most important challenge is automating the analysis process reducing human labor and time. In this study, an empirical approach for automated currency identification is formulated and a prototype is developed. A two parts feature vector is defined comprised of color features and texture features. Finally the banknote in question is classified by a Feedforward Neural Network (FNN) and a measurement of the similarity between existing samples and suspect banknote is output.
