A Physical Device to Help the Visually Impaired Read Money Using AI/Machine Learning in Third World Countries

Abstract

There are over 285 million blind people in the world, with approximately 87% of them living in developing countries. However, in the third world countries, there is currently very little technology to help the visually impaired, especially with financial independence. In this article we present the machine learning algorithms used to develop the device to help visually impaired distinguish between different forms of currency. Using the various currency images, we form a data set that is used to train the transfer learning model. Experimental results show over 94% accuracy with transfer learning model. The device is designed to be portable and hand-held. The device can distinguish between 1, 5, 10, and 20 dollar currency bills. Additionally, the model can work offline. Overall, the device is cost effective, portable, and can be used in the absence of internet connectivity.