Glasses Connected to Google Vision that Inform Blind People about what is in Front of Them

• Autores: Cabanillas-Carbonell, Michael, Aguilar-Chávez, Alexander, Banda Barrientos, Jeshua
• Formato: artículo
• Fecha de Publicación: 2020
• Institución: Universidad Autónoma del Perú
• Repositorio: AUTONOMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.autonoma.edu.pe:20.500.13067/1694
• Enlace del recurso: https://hdl.handle.net/20.500.13067/1694; https://doi.org/10.1109/EHB50910.2020.9280268
• Nivel de acceso: acceso restringido
• Materia: Internet; Prototypes; Blindness; Lenses; Visualization; Cameras; Wireless fidelity; https://purl.org/pe-repo/ocde/ford#2.02.04

More than a billion people around the world have vision problems for different reasons, and these numbers are increasing every year. This leads us to make different innovations in the field of computer vision, with the aim of providing a better quality of life for these people. In this document we present as a resource, the development of an intelligent lens, which incorporates a Raspberry Pi ZW connected to the Google Cloud Vision API through the Wifi of the user's mobile phone, where at the touch of a button, the Raspberry camera, captures the image, processes it in a few seconds and retrieves its main features, obtaining important information for mobilization such as: pedestrian crossings, bus stop sign, vehicles, green light, etc. 150 people from the National Union of the Blind of Peru (NUBP) were evaluated with different degrees of blindness, obtaining a 40.5% increase of independence for their mobilization.