CalorieSnap

Log all your nutrients with the snap of a photo

Comment

Inspiration

I noticed that existing calorie trackers - whether they relied on barcode scanning or manual logs - were simply too cumbersome. Many people find it challenging to keep up with calorie tracking because it can be time-consuming and requires a lot of effort.

That's why I decided to change the game with CalorieSnap. By allowing users to simply snap a picture of their food, the app makes nutrition tracking incredibly easy and straightforward. This innovative approach to calorie tracking is designed to help people stay motivated and stick to their fitness goals. With CalorieSnap, users can take control of their health without having to spend a lot of time and effort on manual tracking.

What it does

CalorieSnap uses state of the art AI models to accurately interpret images and estimate the calories, carbs, protein and fat content. Then, it automatically logs the extracted data in a nutrition management app, displaying the day's totals and goals on the dashboard.

How we built it

At the heart of the CalorieSnap app is a CRUD (create, read, update, delete) application built with Next.js and Firebase. This provides a solid foundation for our app's functionality, allowing users to easily store and manage their nutrition data. CalorieSnap utilizes cutting-edge technologies to power the image input pipeline. We rely on the new Azure Image Analysis 4.0 platform and the GPT-3 API to accurately interpret images of food and estimate their nutritional content. These powerful tools are combined in a unique way to create a seamless and effective nutrition tracking experience for our users.

Challenges we ran into

Getting the Azure image analysis to function properly proved very difficult. I ended up abandoning the JS wrapper and just hitting the API with fetch

Accomplishments that we're proud of

I am especially proud of the proprietary functionality; I think the image input is actually accurate and many times matches exactly what you'd get from Google when trying to track your calories manually.

Built With

Share this project:

Updates