Amazon Textract Extracts Text and Data
Use machine learning to instantly “read” virtually any type of document to accurately extract text and data
Launch our demos
PDF Textract
*Supported Formats: PDF
Image Textract
*Supported Formats: PNG & JPEG
Maximum Textract
*Up to 3000 Pages of PDF Document
Amazon Textract Features
optical character recognition (OCR)
with Deep Learning Technology
Extract data quickly & accurately
No code or templates to maintain
PNG & JPEG Formats
with synchronous operations
PDF Format
with asynchronous operations
PNG & JPEG Document Size
up to 10MB
PDF Document Size
Up to 500MB
PDF maximum page numbers
Up to 3000 Pages
can detect Latin-script characters
from English alphabet and ASCII symbols
quality requirement of an image
ideally at least 150 DPI
Cost of detecting text
$1.5 per 1000 pages
Cost of detecting tables
$15 for 1000 pages
Cost of detecting forms
$50 for 1000 pages
Copyright © 2020 Berkine Design
Amazon Textract is a service that belongs to Amazon Web Services ™