Book Image

Computer Vision on AWS

By : Lauren Mullennex, Nate Bachmeier, Jay Rao
Book Image

Computer Vision on AWS

By: Lauren Mullennex, Nate Bachmeier, Jay Rao

Overview of this book

Computer vision (CV) is a field of artificial intelligence that helps transform visual data into actionable insights to solve a wide range of business challenges. This book provides prescriptive guidance to anyone looking to learn how to approach CV problems for quickly building and deploying production-ready models. You’ll begin by exploring the applications of CV and the features of Amazon Rekognition and Amazon Lookout for Vision. The book will then walk you through real-world use cases such as identity verification, real-time video analysis, content moderation, and detecting manufacturing defects that’ll enable you to understand how to implement AWS AI/ML services. As you make progress, you'll also use Amazon SageMaker for data annotation, training, and deploying CV models. In the concluding chapters, you'll work with practical code examples, and discover best practices and design principles for scaling, reducing cost, improving the security posture, and mitigating bias of CV workloads. By the end of this AWS book, you'll be able to accelerate your business outcomes by building and implementing CV into your production environments with the help of AWS AI/ML services.
Table of Contents (21 chapters)
1
Part 1: Introduction to CV on AWS and Amazon Rekognition
5
Part 2: Applying CV to Real-World Use Cases
9
Part 3: CV at the edge
12
Part 4: Building CV Solutions with Amazon SageMaker
15
Part 5: Best Practices for Production-Ready CV Workloads

Introducing Amazon Rekognition Custom Labels

Developing a custom ML model to analyze images is a significant undertaking that requires tremendous time, ML expertise, and resources. Additionally, it generally requires thousands of hand-labeled images to provide the model with enough data to accurately make decisions. It would take months to gather this data and typically requires large teams of human labelers to prepare it for use in ML.

With Amazon Rekognition Custom Labels, you can offload this heavy lifting to the service. Custom Labels builds off of Amazon Rekognition’s existing capabilities (as explained in Chapter 2), using transfer learning (TL). Instead of you needing to provide thousands of images, you can take a small set of images (typically around 100-200 images) for each label to train a model. If your images are already labeled, you can directly import them into Custom Labels. If not, you can use Custom Labels’ built-in labeling interface or use SageMaker...