Skip to content
A hand holds a phone over a bowl of salad with salmon and avocado, with floating cards for each ingredient.
#ai

Kiweat

Nutrition from a photo of your plate

> for sunny side up studiosai · 2016
01· the project
> A project for Sunny Side Up Studios.

One photo, and you know what you are eating.

Kiweat was a nutrition app: point the phone at a plate and get back what is on it, how many calories it has, its nutrients and a food score, with a note on what that dish is good or bad for.

We built the recognition behind it in 2016, in three phases. First on Google Vision, then with our own neural network trained on a catalogue of 500 dishes, with Vision as the fallback and Nutritionix to fill in what the catalogue lacked. Every correction a user made went back as feedback for the next training round. The back end is Python, with Django, TensorFlow and MongoDB.

> cat /works/kiweat.md
TYPEAI
CLIENTSUNNY SIDE UP STUDIOS
YEAR2016
built with
  • Django
  • Python
  • TensorFlow
  • MongoDB
  • Google Cloud
  • Nutritionix
#ai
02· in numbers
500> dishes the network tells apart
3> phases, May to June 2016
2> recognisers: our network, with Google Vision as fallback
03· how it works
01

Photograph

The user takes a picture of the plate.

02

Recognise

Our network names the dish; Google Vision steps in when it cannot.

03

Score

Calories, nutrients and a food score come from the nutrition data.

04

Learn

The user's correction goes back as feedback for retraining.

04· credits
for sunny side up studios. AI. 2016

Working on something like this? Tell us what you need.

05· next project
> cd /works/map-of-history
Map of History> AR adventure game
> navbar collapsed · scroll to the end
Crowtec