Inspiration
Building something that can have a real-world impact really inspired us to make a web app that people can use to detect possible skin disease.
What it does
The user can upload an image of their skin and a deep learning algorithm will detect the likelihood of skin cancer. The website also has other useful features like recommendations for different skin conditions (dry, oily, etc.) and a locator that users can use to find dermatology clinics based on skin condition and desired location.
How we built it
The Streamlit Python library, utilizing TensorFlow for deep learning and the Google Maps API for an embedded Google Map.
Challenges we ran into
We ran into some issues with the deep learning aspect of this project. Training the data and handling large amounts of it led to issues with how to organize and store it inside and outside of the repo.
Accomplishments that we're proud of
Implementing deep learning into our project with image analysis and learning about a new and exciting library.
What we learned
Gained more experience with Git/GitHub, learning about deep learning tools and techniques for image analysis.
What's next for DermaScan
Expand functionality by adding additional user-friendly features.
Built With
- python
- streamlit
- tensorflow
Log in or sign up for Devpost to join the conversation.