Image processing based Feature extraction of Bangladeshi banknotes

Counterfeit currency is a burning question throughout the world. The counterfeiters are becoming harder to track down because of their rapid adoption of and adaptation with highly advanced technology. One of the most effective methods to stop counterfeiting can be the widespread use of counterfeit detection tools/software that are easily available and are efficient in terms of cost, reliability and accuracy. This paper presents a core software system to build a robust automated counterfeit currency detection tool for Bangladeshi bank notes. The software detects fake currency by extracting existing features of banknotes such as micro-printing, optically variable ink (OVI), water-mark, iridescent ink, security thread and ultraviolet lines using OCR (Optical Character recognition), Contour Analysis, Face Recognition, Speeded UP Robust Features (SURF) and Canny Edge & Hough transformation algorithm of OpenCV. The success rate of this software can be measured in terms of accuracy and speed. This paper also focuses on the pros and cons of implementation details that may degrade the performance of image processing based paper currency authentication systems.