The world's largest database of user-labeled waste images



How did it happen?

In 2020, when everyone was forced to self-isolate at home, we invited users to photo and label the most popular packages. Through environmental crowdsourcing, we managed to collect a giant database of marked waste and train the neural network.

1. Database of user-labeled waste photos

Labeling was made with dounding box on images inside TrashBack mobile application. Then all lebels were validated by our employee. We pay Ecoins for valid markup

2. A neural network that automatically identifies waste in a photo or video

The tagged data is used to train a convolutional neural network that finds waste in the image, identifies it and localizes it

3. Reverse vending machine with artificial intelligence

For the neural network to be of practical use, we have designed and manufactured devices that accept waste from residents, recognize it, and pay Ecoins for the recyclable materials they have returned.

TrashBack mobile application

5

waste classes

packaging types were selected based on popularity, recyclability and recyclability

159894

markup

more than 800 people regularly mark waste in the app

66668

photos from users

users photographed the packaging before throwing it away