Currency Classification System using Deep Learning

In recent years, deep learning has become the most popular research direction. It mainly trains the dataset through neural networks. There are many different models that can be used in this research project. Throughout these models, accuracy of currency recognition can be improved. Obviously, such research methods are in line with our expectations. In this paper, we mainly use transfer learning (MobileNet) model based on deep learning as the framework, Convolutional Neural Network (CNN) model to extract the features of paper currency, so that we can more accurately classify the currency. Our main contribution is through using CNN and MobileNet, the average accuracy of currency classification is up to 99%;

KEYWORDS: Currency image dataset, CNN algorithm, MobileNet, Data Augmentation,

Tensorflow.