High School Students Build “Atheia” For Visually Impaired During Pandemic

On the left Choi is using the Atheia app on an Iphone along with a prototype of a smart-watch-like bracelet. On the right is what the Atheia application shows when the iPhone camera is pointed at a person (Ravella)

Taking advantage of the abilities of machine learning, a group of bright high school students have created an app called “Atheia” that will not only help detect objects but also describe a scene just as a human would.

The app strives to improve spatial awareness and safety for blind people. According to the source article, it can also identify family and friends through facial recognition, has a built in text reader to read text on objects aloud and can search for objects in the person’s immediate surrounding.

The students, Eugene Choi, Raffu Khondaker, Irfan Nafi, and Pranav Ravella, all seniors at the Thomas Jefferson High School for Science and Technology , in Alexandria, Va, began work on this idea in 2019. The original plan was to create a scanner on a glove that would describe the surroundings to the person. However, with feedback from blind individuals and going through multiple iterations (visor, eyeglass attachment, vibrating box on a belt loop), they decided on a mobile app. Currently, this app is being tested by volunteers at Blind Industries and Services of Maryland , a not for profit organization in Baltimore that provides career related services to visually impaired people.

There is a free version of Atheia on the iOS App Store that you can download and try. The students are expecting to charge maybe $10/month in the future. A few years ago, Microsoft released Seeing AI that has similar features.

Watch the demo video below to see how this app works and definitely read the source article to learn about how this app was built, some pitfalls these students experienced, and other details.

Source: IEEE, Washington Post

Leave a comment

Your email address will not be published.


This site uses Akismet to reduce spam. Learn how your comment data is processed.