Context:

According to the census conducted by the National Department of Statistics (DANE) in 2018, 7.1\% of the Colombian population has a visual disability. These people face conditions with limited autonomy, such as the handling of money. In this context, there is a need to create tools to enable the inclusion of visually impaired people in the financial sector, allowing them to make payments and withdrawals in a safe and reliable manner.

Method:

This work describes the development of a mobile application called CopReader. This application enables the recognition of coins and banknotes of Colombian currency without an Internet connection, by means of convolutional neural network models. CopReader was developed to be used by visually impaired people. It takes a video or photographs, analyzes the input data, estimates the currency value, and uses audio feedback to communicate the result.

Results:

To validate the functionality of CopReader, integration tests were performed. In addition, precision and recall tests were conducted, considering the YoloV5 and MobileNet architectures, obtaining 95 and 93\% for the former model and 99\% for the latter. Then, field tests were performed with visually impaired people, obtaining accuracy values of 96%. 90% of the users were satisfied with the application’s functionality.

Conclusions:

CopReader is a useful tool for recognizing Colombian currency, helping visually impaired people gain to autonomy in handling money.

        · texto em Inglês     · Inglês ( pdf )