Fake Currency Detection using Image Processing and Python Module

India is a country where it consists of different types of currencies and coins. Currencies have their own denomination and using that we can identify currency easily. Now a days a lot of illegal counterfeiting rings manufacture and sell fake Indian currency is printed as well, which has caused great loss and damage to the economy. Thus it is imperative to detect fake currency. We propose a new model to detect fake Indian notes using their digital images. The image of currency is represented in the dissimilarity space, which is a vector space constructed by comparing the image with a set of prototypes. Each dimension measures the dissimilarity between a prototype and the image under consideration. In order to obtain the dissimilarity between two images, the local key points on each image are detected and described. Based on the characteristics of the currency, the matched key points between the two images can be identified in a competent manner. A post processing procedure is further proposed to remove mismatched key points. Support Vector Machine (SVM) is conducted for the detection of fake currency, so only genuine currency is needed to train the classifier.