Data Extraction Service - Amazon Textract

Automatically extract printed text, handwriting, and data from any document with intelligent document processing

What is Amazon Textract?

 Extract text and structured data such as tables and forms from documents using artificial intelligence (AI)—no configuration or templates necessary.

 Go beyond simple optical character recognition (OCR) by extracting relationships, structure, and text from documents.

 Improve security and compliance through robust data privacy, encryption, security controls, and support compliance standards such as HIPAA, GDPR, and more.

 Easily implement human reviews with Amazon Augmented AI (A2I) to manage nuanced or sensitive workflows and audit predictions.

What is Amazon Textract? (1:49)

Use Cases

Lending

Extract critical information out of mortgage applications such as asset valuation, credit score or property value using OCR to speed up response times to your customers. 

Healthcare and Life Sciences

Better serve your patients and insurers by extracting important patient data from health intake forms, insurance claims, and pre-authorization forms. Keep data organized and in its original context, and eliminate manual review of output.

Insurance

Data extraction can be particularly challenging in the insurance sector, given the varying document layouts and formats for quotes, insurance forms, claims, and receipts. Using Amazon Textract, you can quickly extract relevant information such case ID, property address quickly and accurately

Public Sector

Easily extract relevant data from government-related forms such as small business loans, federal tax forms, and business applications with a high degree of accuracy.

Amazon Textract on the Free Tier
PRODUCT DESCRIPTION  FREE TIER OFFER DETAILS  PRODUCT PRICING

Amazon Textract

Intelligent document processing

Automatically extract printed text, handwriting, and data from any document.

3 MONTH FREE TRIAL

Detect Document Text API: 1,000 pages per month

Analyze Document API:

  • 100 Pages per month when using Forms or Tables feature
  • Additional 100 pages per month when using Queries feature 

Analyze Expense API: 100 pages per month

Analyze ID API: 100 pages per month

Amazon Textract Pricing

Free Tier Offer

AWS helps new customers get started for free. See how you can use the AWS Free Tier with Amazon Textract

Amazon Textract
Automatically extract printed text, handwriting, and data from any document.
3 MONTH FREE TRIAL

Detect Document Text API: 1,000 pages per month

Analyze Document API: 100 Pages per month when using Forms or Tables feature

Analyze ID API: 100 pages per month

Amazon Textract Pricing »
AWS Lambda
Sign up for an AWS Account
Creating an AWS account is free and gives you immediate access to the AWS Free Tier.

Learn More About Amazon Textract

Browse through our collection of videos to learn more about Amazon Textract

  • Videos
  • Automate document processing using AWS machine learning (5:38)
    Learn How to Process Paycheck Protection Program (PPP) Loans Using Amazon Textract (7:18)
    Learn how to add human reviews to your document processing pipelines (11:52)
    AWS re:Invent 2020: Using AI to automate clinical workflows (17:33)
  • Tutorials
  • Tutorials

    Start with these free and simple tutorials to explore Amazon Textract

    Getting Started with Amazon Textract

    In this tutorial, you will learn how to use Amazon Textract to extract text and structured data from a document. You will sign in to Amazon Textract, extract raw text, forms, and table cells from a sample document, download the results, and learn about human review.

    Learn more »

    Extracting Key-Value Pairs from a Form Document

    The tutorial will show you how to extract key-value pairs in form documents from Block objects that are stored in a map

    Learn more »

    Exporting Tables into a CSV File

    The tutorial will show you how to export tables from an image of a document into a comma-separated values (CSV) file

    Learn more »

    Creating an AWS Lambda Function

    You can call Amazon Textract API operations from within an AWS Lambda function. The instructions will show you how to create a Lambda function in Python that calls DetectDocumentText.

    Learn more »

    Extracting and Sending Text to AWS Comprehend for Analysis

    Amazon Textract lets you include document text detection and analysis in your applications. With Amazon Textract you can extract text from a variety of different document types using both synchronous and asynchronous document processing. The extracted text can then be saved to a file or database, or sent to another AWS service for further processing.

    Learn more »

    Automatically process mortgage and bank documents

    A mortgage packet can come with up to 20 different types of forms such as W-2’s, bank statements, and deed information which makes it difficult to use traditional technologies to automate the process. Using OCR and NLP, you can automate the extraction of these documents whether they are structured forms like W-2’s or semi-structured documents like mortgage forms. 

    Learn more »

AWS Free Tier

The AWS Free Tier offers users an opportunity to explore products for free, with offers including products that are always free, free for 12 months, and short-term free trials.

Get Started

Creating an AWS account is free and gives you immediate access to the AWS Free Tier.