Computer Vision Applications and AWS AI/ML Services Overview
In the past decade, the field of computer vision (CV) has rapidly advanced. Research in deep learning (DL) techniques has helped computers mimic human brains to “see” content in videos and images and transform it into actionable insights. There are examples of the wide variety of applications of CV all around us, including self-driving cars, text and handwriting detection, classifying different types of skin cancer in images, industrial equipment inspection, and detecting faces and objects in videos. Despite recent advancements, the availability of vast amounts of data from disparate sources has posed challenges in creating scalable CV solutions that achieve high-quality results. Automating a production CV pipeline is a cumbersome task requiring many steps. You may be asking, “How do I get started?” and “What are the best practices?”.
If you are a machine learning (ML) engineer or data scientist or want to better understand how to build and implement comprehensive CV solutions on Amazon Web Services (AWS), this book is for you. We provide practical code examples, tips, and step-by-step explanations to help you quickly deploy and automate production CV models. We assume that you have intermediate-level knowledge of artificial intelligence (AI) and ML concepts. In this first chapter, we will introduce CV and address implementation challenges, discuss the prevalence of CV across a variety of use cases, and learn about AWS AI/ML services.
In this chapter, we will cover the following:
- Understanding CV
- Solving business challenges with CV
- Exploring AWS AI/ML services
- Setting up your AWS environment