An application based on artificial intelligence for translating sign language into text in real time has been developed at Novosibirsk State University (NSU).
The application functions on both computers and mobile devices. Developer Yaroslav Chekanov independently studied Russian Sign Language and collected a large dataset to train the AI. The application reads the image from the video camera and translates gestures into text, which is displayed on the screen.
The main advantage of the solution is the high speed and accuracy of translation compared to analogues. In the future, it is planned to add a reverse translation — from text and voice to gestures. According to the author, this project has important social significance, expanding the possibilities of interaction for people with disabilities.
Read materials on the topic:
Restores fine motor skills: a game platform for rehabilitation has been created in Tomsk
Precise grip: PNIPU scientists have made their bionic hand prostheses more accurate
