Extracting Text and Data with Amazon Textract
This course will teach you how to use and work with Amazon Textract, which extracts text and data from scanned documents, going beyond traditional OCR.
What you'll learn
Businesses are moving to an instantaneous and digital world, but we will still need physical documents for quite some time. In this course, Extracting Text and Data with Amazon Textract, you will learn to use OCR technology to extract text, and key-value pairs of data from scanned documents. First, you will explore how to detect printed text and numbers in a scan or rendering of a document. Next, you will discover how to detect key-value pairs in document images automatically so that they can retain the inherent context of the document without any manual intervention. Finally, you will learn how to preserve the composition of data stored in tables during extraction. When finished with this course, you will have the skills and knowledge of how to use Amazon Textract to create smart search indexes, build automated approval workflows, and better maintain compliance with document archival rules by flagging data that may require manual input, as well as being able to export data contained within those documents to other systems.
Table of contents
- Overview and Sync Operations 3m
- Text Detection Mechanism 4m
- Item Location 5m
- Text Analysis Mechanism 4m
- Text Content and Forms 5m
- Tables, Selection Elements, and Responses 4m
- Demo: Text Detection and Analysis on Single-page Docs 5m
- Demo: Implementing Key-value Extraction 3m
- Demo: Implementing Table Extraction 3m
- Summary 1m