Scientific Approach of Real Time Fake Currency Note Detection Using Deep Learning

Great technological advancement in printing and scanning industry made counterfeiting problem to
grow more vigorously. As a result, counterfeit currency affects the economy and reduces the value of
original money. Thus it is most needed to detect the fake currency. Most of the former methods are
based on hardware and image processing techniques. Finding counterfeit currencies with these
methods is less efficient and time consuming. To overcome the above problem, we have proposed
the detection of counterfeit currency using a deep convolution neural network. Our work identifies the
fake currency by examining the currency images. The transfer learned convolutional neural network is
trained with two thousand, five hundred, two hundred and fifty Indian currency note data sets to learn
the feature map of the currencies. Once the feature map is learnt the network is ready for identifying
the fake currency in real time. The proposed approach efficiently identifies the forgery currencies of
2000, 500, 200, and 50 with less time consumption.