Amazon Textract

Amazon Textract is a fully managed machine learning service that automatically extracts text, handwriting, and data from scanned documents. It goes beyond simple optical character recognition (OCR) to identify, understand, and extract data from forms and tables, enabling automation of document…

Key facts

First appeared: 2018
Category: technology
Problem solved: Amazon Textract was created to solve the laborious, error-prone, and time-consuming problem of extracting data from vast quantities of documents. Traditional methods involved either manual data entry, which was slow and expensive, or basic OCR software that could extract text but struggled with understanding document structure, handwriting, forms, and tables, often requiring extensive post-processing and human intervention.
Platforms: AWS Cloud

Related technologies

Amazon S3
Amazon SageMaker
Document Management Systems (DMS)
Amazon Comprehend
Amazon DynamoDB
Robotic Process Automation (RPA) tools
AWS Lambda
AWS Step Functions

Notable users

Nationwide
Workday
United Airlines
Fidelity National Information Services (FIS)
Deloitte
Guardian Life Insurance