Deep Learning Approach for Fake Currency Recognition

Abstract

In this method, the Automatic fake Currency Recognition System is used to identify fake paper money and determine if it is genuine or not. The current counterfeit issue brought on by demonetization has an impact on the financial system as well as other sectors. This strategy, which is comparatively superior to earlier image processing methods, examines a novel Convolution Neural Network approach for the identification of fake money notes through their images. This approach is based on Deep Learning, which has recently shown outstanding results in image categorization problems. Through the use of an image of the fake money note, this approach can assist both humans and machines in instantly recognizing the note. In this system original and fake notes images are used to perform training and classification operation. The proposed system achieved an accuracy of 99.46% and loss of 0.0033 using CNN algorithm.