Amazon Textract announces accuracy and feature updates to DetectDocumentText and AnalyzeDocument APIs
News
Amazon Textract has announced significant updates to its document text detection and analysis APIs, improving machine learning model accuracy and adding new features.
- New support for superscripts, subscripts, and rotated text in documents
- Enhanced accuracy for text detection in box forms
- Improved extraction of visually similar character sets (e.g., '0' vs. 'O')
- Better text recognition for lower-resolution documents like faxes
- Updates available across multiple global AWS regions
These improvements help users extract text more accurately from a wider variety of document types and qualities, enhancing the overall performance of the Amazon Textract service.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Jan 6
2025
2025
How to enhance Amazon Macie data discovery capabilities using Amazon Textract
Jan 8
2024
2024
Create a document lake using large-scale text extraction from documents with Amazon Textract
Feb 23
2024
2024
Ensuring fair play by detecting and preventing profile alterations with Amazon Textract
May 7
2026
2026
Amazon ElastiCache now supports real-time full-text, exact-match, and numeric range search
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.