Automatic Indian New Fake Currency Detection Using Deep Learning

Abstract

In India,’ currency’ is the means of Transaction so there is more value for currency in our social and economic development. Here, currency exists in the form of coins, banknotes and electronic data. Fake money or counterfeit notes is the dangerous or acute problem in front of whole world, and India is also a part of this fake currency. Modernization in the financial system is a milestone in protecting the economic development and now a days Indian government has become conscious about this so demonetization of Rs 1000 and Rs 500 notes is the latest example of it. But again we have Rs 2000 as a new currency in market. so as the highest value note there is a chance that corrupt people will try to make it as a counterfeit. we have used our dataset with real and fake currency notes and then trained InceptionV3, VGG16, Resnet50 and Custom CNN on that dataset. After training VGG16 and Custom CNN giving more than 90% validation accuracy and InceptionV3 and Resnet50 shown poor performance. We have coded this project using JUPYTER notebook.