A service that extracts text, tables, and form data directly from scanned documents or PDFs, going beyond traditional OCR by understanding document structure (key-value pairs, tables).
In AIF-C01 (Domain 3) it is distinguished from generic OCR because it preserves form and table structure. Question: automating data extraction from scanned invoices while preserving table format → Amazon Textract.
Amazon Textract is a concept that can show up on the exam. Check the full guide to see it in context.