Everyone wants to know what's inside their food, but there's no easy way to do it so we made HealthyEaterBuddy.
What it does
The user is able to take a picture of their food and then they will receive nutritional facts about it.
How we built it
We used the metamind api to train a convolutional neural net on a large database of pictures of food that we amassed. We then used this classifier to identify what is contained within pictures of food. This output was fed into the wolfram api to get information on nutritional facts.
Challenges we ran into
Difficulties getting the app set up
Accomplishments that we're proud of
It actually works well
What we learned
Learned about different machine learning techniques, iOS programming, RESTful APIs
What's next for Healthy Eater Buddy
We hope to make our database bigger so we can more accurately classify different types of food. We would also like to be able to figure out how to get the amount of food that is present in a picture.