Vision AI

• 

  image for predicting.

• 

  output will be audio generated

Inspiration

social community

What it does

Our app aids visually impaired shoppers by providing real-time audio descriptions of scanned products, promoting independence and inclusivity.

How we built it

using machine learning or trained YOLOv8 model and streamlit

Challenges we ran into

time limit and shortage of the datasets

Accomplishments that we're proud of

we are able to tackle most of the challenges with in the given time.

What we learned

image processing using deep learning model.

What's next for Vision AI

1. Continuous prediction with video input is a possibility, offering advantages over analyzing individual image frames.
2. The integration of this application into mobile devices could enhance user experience and accessibility.
3. Currently, our model is tailored to specific products, but we aim to expand its capabilities by training it with a broader range of classes in the future.

Built With

• python