Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents and goes beyond optical character recognition (OCR) to identify, understand, and extract data from forms and tables.
In this Getting Started course, you will learn about the benefits, features, typical use cases, technical concepts, and costs of Amazon Textract.
You will review the architecture for a text-extraction solution using Amazon Textract that you can further adapt to your use case. Through a guided tutorial, you will also try the service in your own Amazon Web Services (AWS) account.
- Course level: Fundamental
- Duration: 90 minutes
This course includes presentations, graphics, and a step-by-step tutorial to follow.
Course objectives
In this course, you will do the following:
- Understand how Amazon Textract works.
- Familiarize yourself with basic concepts of Amazon Textract.
- Recognize the benefits of Amazon Textract.
- List typical use cases for Amazon Textract.
- Describe the typical architectures associated with an Amazon Textract solution.
- Specify what it would take to implement Amazon Textract in a real-world scenario.
- Understand the cost structure of Amazon Textract.
- Implement a demonstration of Amazon Textract in the AWS Management Console.
Prerequisites
We recommend that attendees of this course have completed the following training:
- AWS Technical Essentials
We also recommend that you review the following resources, if you are not already familiar with AWS Step Functions and AWS Cloud Development Kit (CDK):
- Create a Serverless Workflow with AWS Step Functions and AWS Lambda
- Getting started with the AWS CDK Course outline
- Amazon Textract Basics
- How Is Amazon Textract Used to Architect a Solution?
- Amazon Textract Use Cases
- Amazon Textract Guidelines and Best Practices
- Amazon Textract Costs
- Using Amazon Textract to Synchronously and Asynchronously Extract Text from Documents