Getting started

Amazon Lookout for Vision enables you to find visual defects in industrial products, accurately and at scale. It uses computer vision to identify missing components in an industrial product, damage to vehicles or structures, irregularities in production lines, and even minuscule defects in silicon wafers — or any other physical item where quality is important such as a missing capacitor on printed circuit boards.

 

Developer Guide

Describes all Amazon Lookout for Vision concepts and provides instructions on using the various features with the console, command line interface, and the AWS SDK.

HTML | PDF

API Reference

Describes all the API operations for Amazon Lookout for Vision in detail.

HTML | PDF

Video Presentations

AWS re:Invent 2020: Amazon Lookout for Vision
AWS re:Invent 2020: AWS for Industrial with Matt Wood (15:27)

Overview videos

What is Amazon Lookout for Vision?
Create a Lookout For Vision Dataset Using Images in Amazon S3 (5:12)
Adding and Labeling Images to the Lookout For Vision Dataset (5:16)
Training a Lookout for Vision Model (5:23)
Evaluating and Improving the Lookout for Vision Model (6:23)
Deploying and Running Inference on the Lookout For Vision Model (6:01)

AWS Online Tech Talks

Get Started with Computer Vision for Quality Inspection, with Amazon Lookout for Vision

Watch the Video »

Blog posts and articles

Build, train, and deploy Amazon Lookout for Vision models using the Python SDK 
by Michael Wallner, Bandana Das, Shreyas Subramanian, and Weizhou "Wei" Sun
April 7, 2021

Read the blog »

Amazon Lookout for Vision – New ML Service Simplifies Defect Detection for Manufacturing 
by Marcia Villalba
December 1, 2020

Read the blog »

Check out the Amazon Lookout for Vision partners

Visit the Amazon Lookout for Vision partners page to learn more about our partners.

Learn more 
Sign up for a free account

Instantly get access to the AWS Free Tier. 

Sign up 
Start building in the console

Get started building with Amazon Lookout for Vision in the AWS Management Console.

Sign in