Captar-Libras [en]

Communication between deaf patients and health professionals, who are not fluent in sign language, requires a human interpreter to translate the conversation. The Captar-Libras is a research and development project that seeks to facilitate communication between deaf people and health professionals without needing a human interpreter. This task is of great importance all over the world since there are millions of people in the world who use different variations of sign language to communicate. Therefore, Computer Vision, Artificial Intelligence, and Human-Computer Interface techniques are applied to develop a system capable of translating communication in both directions, focused on Brazilian Sign Language (Libras). As a result, the system will be able to convert videos of sign language speakers to text, as well as convert text to video in sign language, generating a photorealistic avatar that simulates a human interpreter.