Posted On: Nov 16, 2020
HAQM Textract, a machine learning service, extracts text and other data from documents as well as tables and forms. Today, we are pleased to announce two new features:
- HAQM Textract now supports recognition of handwritten text from documents such as healthcare forms, prescriptions, dispute letters, tax documents, income documents, checks, claims, academic papers and many more. You can use the Detect Document Text or Analyze Document APIs to process images or PDF’s of scanned documents and extract both printed text and handwriting making it easy for you to automate almost any scanned document processing. You can also use HAQM Augmented AI (HAQM A2I), another AWS service, which makes it easy to build the workflows for human review of the machine learning predictions. You can log in to the HAQM Textract console to test out the handwriting feature, or check out the new demo by HAQM Machine Learning Hero Mike Chambers.
- HAQM Textract now supports processing of documents with printed text in Spanish, German, Italian, Portuguese, and French. You can start sending documents in these languages for text extraction, and HAQM Textract will automatically detect and extract the information for you.
We are also pleased to announce that HAQM Textract is now available in the AWS EU (Paris) region. To get started, log into the HAQM Textract console to test out your handwritten documents and the new language support. To learn more about Textract capabilities, please visit the HAQM Textract website, developer guide, or resource page.