This is a project developed by Data, an extension group located at University of São Paulo, São Carlos, Brazil.
The main ideia is to transcribe buses destination signs to plain text by using Optical Character Recognition (OCR), Neural Networks and Transformers models. The project was inspired by a Omdena Project named "Helping People with Visual Impairment to Easily Use Buses through Computer Vision".
For scraping bus images, the website used was OnibusBrasil. A shout-out to Valter Silva, the man who made this project possible.