Counterfeit currency varies from low quality color scanner/printer-based notes to high quality counterfeits whose production is sponsored by hostile states. Due to their harmful effect on the economy, detecting counterfeit currency notes is a task of national importance. However, automated approaches for counterfeit currency detection are effective only for low quality counterfeits; manual examination is required to detect high quality counterfeits. Furthermore, no automatic method exists for the more complex – and important – problem of identifying the source of counterfeit notes. This paper describes an efficient automatic framework for detecting counterfeit currency notes. Also, it presents a classification framework for linking genuine notes to their source printing presses. Experimental results demonstrate that the detection and classification frameworks have a high degree of accuracy. Moreover, the approach can be used to link high quality fake Indian currency notes to their unauthorized sources.