Machine Learning
RecognitionAmazon Textract
Managed extraction of text, forms, tables, and document structure from scanned documents and images.
Key points
- It goes beyond basic OCR by returning supported structured document relationships.
Best-known use cases
- Extract fields and tables from forms or invoices.
What candidates often confuse it with
- Textract extracts document structure; Comprehend analyzes the meaning of extracted text.
Key takeaway
Choose Textract when document images must become structured text/data.
Related services
- Amazon Comprehend
- Amazon S3
Relevant exam tasks
- D2.2