Inspiration
I wanted a smarter, more intuitive way to track fitness progress beyond just numbers on a scale. I have also loved fitness and health and have always been good with computers and wanted to find a way to combine. I set out to build a tool that helps users understand their bodies using simple pieces of data to give them scientifically accurate results and health metrics to help optimize their habits and see where they need to improve. I have been trying to figure out how to use photos to scan bodyfat % for years and finally a tool has been created with an API that I was able to utilize for this.
What it does
Physique Tracker uses AI to analyze user-submitted photos and estimate body fat percentage with high accuracy. It offers visual tracking over time, helping users monitor progress in a clear, engaging way.
How we built it
I built the app using a combination of:
- A front-end interface in React Native for cross-platform use, built by Bolt.New
- A secure backend powered by Supabase
- The BVI AI API to handle photo processing for many of the metrics that are calulated
Challenges we ran into
- Ensuring user privacy while handling sensitive body images
- Balancing accuracy with the wide range of body types and lighting conditions
- Keeping the experience simple and user-friendly
- Creating secure login accounts and implementing a payment method
Accomplishments that we're proud of
- Developing a working prototype that gives consistently accurate results
- Designing a clean, intuitive UI that keeps users engaged
- Successfully integrating AI into a fitness app in a practical, meaningful way
What we learned
- How to handle and store personal health data responsibly
- Real-world applications of websites require strong design thinking and logic understanding, its not as simple as it looks
What's next for Physique Tracker - The AI bodyfat scanner
- Adding more metrics like muscle mass estimation
- Building personalized workout and nutrition suggestions based on body composition
- Launching beta testing to refine the model with more diverse data
- Exploring partnerships with fitness coaches and health apps for integration
- Further optimization for loading times - found firebase is faster to load than supabase
- Fixing some of the user account options
Built With
- bodyvolumeindexapi
- bolt.new
- bvi
- javascript
- stripe
- supabase
Log in or sign up for Devpost to join the conversation.