An automatic translator for sign language and a glove that can help teach Braille could be set to revolutionise life for sight and hearing impaired people.
International research published in the Institution of Engineering and Technology’s Journal of Engineering has outlined an Automatic Sign Language Translator (ASLT) concept which uses technology to capture, interpret and translate sign language into ‘readable language’.
Researchers from Malaysia and New Zealand have developed the theoretical fundamentals of sign language interpretation based on image processing and pattern recognition, which they believe will result in a ‘portable, efficient and affordable ASLT for a wide variety of sign and written languages’.
The system was tested on gestures and signs representing both isolated words and continuous sentences of sign language, and is said to have achieved ‘a high degree of recognition accuracy and speed’.
“We developed a novel approach, leading to efficient detection and tracking of face, hands and upper body trajectories of a signer,” said Professor Rini Akmeliawati, a researcher at IIUM University in Malaysia.
“By combining it with our tools for artificial intelligence-based matching between these sign trajectories and elements of a large database of images and video recordings of native signers, we have achieved a fast and flexible automatic sign language translation system.
“The system’s potential lies in its technologically advanced algorithms and structure, which can be adapted to a multitude of the world’s sign languages.”
Meanwhile, Georgia Institute of Technology researchers have created a technology-enhanced glove to help people learn how to read and write Braille, even if they’re not paying attention.
“The process is based on passive haptic learning,” explained Thad Starner, a professor at Georgia Tech.
“We’ve learned that people can acquire motor skills through vibrations without devoting active attention to their hands.”
In a study conducted by Starner and PhD student Caitlyn Seim, participants wore a pair of gloves with tiny vibrating motors stitched into the knuckles.
The motors vibrated in a sequence that corresponded with the typing pattern of a pre-determined phrase in Braille, before audio cues notified the users of the Braille letters produced by typing that sequence.
Afterwards, all participants tried to type the phrase, without the cues or vibrations, on a keyboard.
The sequences were then repeated during a distraction task. Participants played a game for 30 minutes and were told to ignore the gloves. When the game was over, participants tried to type the phrase without wearing the gloves.
“We found that people could transfer knowledge learned from typing Braille to reading Braille,” said Seim.
“After the typing test, passive learners were able to read and recognize more than 70 per cent of the phrase’s letters.”