Indian Currency Recognition and Authentication
Rohit Gupta · International Journal for Research in Applied Science and Engineering Technology · 2021
It is very difficult for blind people to recognize or classify the Indian Currency into 10, 20, 50, 100, 200, 500 and 2000 rupees, therefore this project aims to classify the image into respective class of currency note.This is done using TensorFlow object detection which not only classify the image but also helps to localize/detect the currency in image provided by the user.Thus, the recognition part is done using object detection.Furthermore, the project also aims to authenticate the Indian currency means it helps to classify the image into real currency or fake currency.This is very much helpful because it helps to detect the fake currency and stop the flow of the same in market.Indian Currency Authentication is done using deep learning that is using Image Classification and Mobilenet model of image classification is used.The authentication is done using the watermark of Mahatma Gandhi which is present in each and every currency notes.So, each part is implemented using somewhat different approach.