Inspiration
One of our group members grandparents have Cataracts disease, which is one sparked the idea of making a recognition software.
What it does
Uses a trained database and facial recognition to identify if someone has Cataracts disease(97% accuracy with good ocular picture)
How we built it
We used Tkinter for the gui, powered with cv2 and torchvision.
Challenges we ran into
We initially wanted to make a website, but using fetch request and Flask Cors to transfer data between Javscript and Flask files made it really difficult, which is why we reverted to Tkinter and the complexity of the CNN
Accomplishments that we're proud of
This was our first time working with image recognition and creating datasets, so we're really proud that we were able to succesfully use these high level programming concepts in our project.
What we learned
We learnt a lot about machine learning and image recognition, as well as how to show resilience when met with hard problems.
What's next for CataDetect
We plan to migrate to a website, improve the GUI, and allow people to take images directly from our site.
Built With
- python
- tkinter
- torch
Log in or sign up for Devpost to join the conversation.