Extracting Lucky Charms Marshmallows From the Cereal With an AI Machine Taught to Sort Objects

Creative Technologists Lucas Ochoa and Gautam Bose of Google Creative Lab conducted a yummy experiment with an AI sorting machine that separated the marshmallows parts of Lucky Charms cereal from the cereal itself.

Marshmallow Cereal Sorting Machine

This fun experiment was also a demonstration of how Google’s Teachable Machine paired with the Coral USB Accelerator can be used to create a machine that can be taught to recognize and sort objects using custom machine learning models.

This project shows you how to build a machine to classify and sort objects. It leverages Teachable Machine, a web-based tool that lets you easily train your own image classification model without writing any code, and then uses the Coral USB Accelerator for inferencing based on that model to classify and sort objects.

Lucky Charms Marshmallow Sorter

Coral Diagram

via The Awesomer

Lori Dorn
Lori Dorn

Lori is a Laughing Squid Contributing Editor based in New York City who has been writing blog posts for over a decade. She also enjoys making jewelry, playing guitar, taking photos and mixing craft cocktails.