Evann Sun
8th Grade, Juan Cabrillo Middle School
Santa Clara, CA
Visionary: AI Glasses for Real-Time Text-to-Audio Transcription To Help Visually Impaired Students
View Poster
Project Background
When Evann’s teammate Akhil Nagori visited his grandfather in India, he saw how much he struggled to read Braille as part of his work. He told his teammates Evann and Lucas Yen, and “together we decided to focus on a project that would support individuals with visual impairments,” Evann says. The team decided to focus on school materials for the visually impaired. “Every student, regardless of visual ability, deserves equal opportunities,” he says, and that means being able to read the textbook.
Tactics and Results
The team wanted to teach an AI model to “read” different fonts and layouts of text and translate them to speech. They started with a dataset of 800 classroom text images from books, worksheets and other class materials, to train the AI on colorful backgrounds and fonts. Evann oversaw designing the frame, a pair of 3D-printed glasses that would contain a Raspberry Pi, a tiny camera, a battery, and a small pair of speakers. The glasses were programmed to take pictures, extract the text from them, and used an eSpeak library to convert the text to speech, which is played through the speakers mounted on the glasses’ frame. The team tested their glasses in high, low, and medium light with tough to read text. Their glasses successfully read the text aloud 92 percent of the time.
Beyond the Project
Evann loves basketball. “It’s an incredibly fun and engaging game that not only builds skills you can use on the court, but also valuable life skills off the court,” he says. He’s been interested in technology for as long as he can remember. When his parents laid out objects for him to choose from on his first birthday, “out of everything, I reached for a flip phone.” He’d like to become a mechanical engineer. “Your work can have a meaningful impact on millions of lives,” he says.
