-
-
-
Landing page
-
App detecting phone
-
App detecting pen
Inspiration
We noticed there were many people who were either blind or visually impaired. According to the World Health Organization, around 40 million people in the world are blind, while another 250 million have some form of visual impairment. They face various different problems. We decided to solve this issue and came up with an idea - ISight.
What it does
ISight uses the Computer Vision domain of AI to detect objects and identify them. This helps blind or visually impaired people understand the world around them better.
How we built it
We collected various images of everyday items like pen and apple, then we used Google's Teachable machine to train the AI model. We imported the JavaScript boilerplate into our project and used HTML, CSS and a bit of JavaScript to style it.
Challenges we ran into
The main challenge we ran into was collecting data. We had to collect data that was under the Creative Commons Licenses to avoid copyright claim.
Accomplishments that we're proud of
We are very proud of creating a web app that helps blind people perform everyday tasks.
What we learned
We learnt to use Teachable Machine and learnt a bit of JS.
What's next for ISight
In the future, ISight will have text detection, capability to detect more objects, and color detection.
Log in or sign up for Devpost to join the conversation.