Checkout+

Checkout+ is an add-on system for self-checkout machines which uses machine learning and computer vision to detect barcode-less produce items, reducing the produce entry time from 15 seconds to less than 3 seconds. This means faster, safer, and easier grocery store trips during these stressful times.

Created by Ronald Gayowsky, Erin Grant, Jeffrey Langballe, and Mark Rakov for their Mechatronics Engineering Capstone project.

Home: Welcome

rcgayows

Mar 23, 20211 min read

Systems Software Design

The software integrating the scale, vision, and camera has been designed and implemented. The scale software controls the state of the...

rakovmark

Feb 24, 20212 min read

Constructing the Cabinetry

After a successful implementation of the design assembly in Solidworks what could possibly go wrong? Well, it turns out sometimes you...

jnlangba

Feb 16, 20212 min read

Taking pictures from the dev screen

We are not frontend experts nor are we UI experts. To work around this and to get things up and running faster, we decided that the first...

eringrant774

Feb 8, 20212 min read

Preliminary Network Training Results

The preliminary results of network training on Mark's computer are shown below. This graph shows the accuracy of the networks compared to...

eringrant774

Feb 8, 20212 min read

The Importance of Hardware In Training An Image Classifier

The main advantage of this checkout system is its ability to recognize and classify produce, which we decided early on would be done by a...

rcgayows

Feb 2, 20211 min read

Scale v.0.1

Build update for the scale: Not deterred by the provincial lockdown, production of the scale has continued. Unorthodox materials have...

jnlangba

Jan 19, 20211 min read

Starting point

To recap, Checkout+ is an add-on system for existing self-checkout machines. It will be powered by a Raspberry Pi 3B+ and a Coral USB...

Home: Blog2