Today we’re going to show you how to build a prototype trash sorter using AWS DeepLens, AWS’s deep learning-enabled video camera designed for developers to learn machine learning in a fun, hands-on way. This prototype trash sorter project teaches you how to train image classification models with custom data. Image classification is a powerful machine learning technique where a machine learning model learns how to distinguish between many different objects inside images by observing many examples. You can apply techniques learned in this tutorial to solve problems that require sorting objects into different bins based on imagery (such as sorting fruits by size or grade) or detecting the existence of an object in an image (such as recognizing the type of object at self-checkout).
This tutorial was inspired by the smart recycle arm project created for the AWS Public Sector Builders Fair. For more information, see Demonstration: Automatic Recycling on YouTube.
This walkthrough includes the following steps:
The following diagram illustrates the solution architecture.
To complete this walkthrough, you must have the following prerequisites: