A university in Singapore has developed a bone conduction headphone and a micro camera that captures the wearer’s field-of-vision, translating the data using artificial intelligence (AI).
Associate professor of the information and analytics department of the National University of Singapore Computing (NUS), Suranga Nanayakkara is hoping that interaction with AiSee can be seamless between a user and the world around them.
”With AiSee, we aim to empower users with more natural interaction. By following a human-centered design process, we found reasons to question the typical approach of using glasses augmented with a camera,” the professor said of the new technology.
[embedded content]
AiSee’s Vision Engine
The ‘vision engine’, is the informational capture software that can scan for data such as text, logos and labels from the objects in the camera’s eye line. A bone conduction headphone is also a core part of AiSee that allows the wearer to hear the world around them, but also receive information from the device.
Using text-to-speech and speech-to-text recognition the device interacts with the user who has an object of interest they wish to scan. This scanning tool allows for the cloud-based algorithms, which is an information repository used by AI similar to that of an OpenAI, to compose and answer to queries posed by the wearer.
NUS student Mark Myers took part in the testing of the device as a visually impaired user, saying “I think AiSee is a good balance. Both visually impaired and blind people could get a lot of benefits from this.”
Nanayakkara hopes to make the technology available to everyone in his home nation, saying the people of Singapore “do not have access to assistive AI technology of this level of sophistication. Therefore, we believe that AiSee has the potential to empower visually impaired people to independently accomplish tasks that currently require assistance.”
The NUS is working with a disability care provider SG Enable in Singapore to conduct further testing with visually impaired users to collect more data to refine the offering AiSee can provide those with impairments.
”Our next step is to make AiSee affordable and accessible to the masses. To achieve this, we are making further enhancements, including a more ergonomic design and a faster processing unit,” Nanayakkara concludes.
Image: NUS.
Source: ReadWriteWeb
