Answer: Amazon Textract

**Explanation:** Amazon Textract is specifically designed for extracting text, forms, and tables from scanned documents. It can identify and extract key-value pairs from documents like invoices, forms, and receipts. Here's why: 1. **Amazon Textract** is an AWS service that uses machine learning to automatically extract text, handwriting, and data from scanned documents. 2. It can identify form data (key-value pairs) and table data from documents, making it ideal for processing invoices, forms, and receipts. 3. **Amazon Rekognition** is for image and video analysis (object detection, facial recognition). 4. **Amazon Comprehend** is for natural language processing (sentiment analysis, entity recognition). 5. **Amazon OpenSearch** is a search and analytics engine. For extracting structured data like names and amounts from scanned invoices, Amazon Textract is the correct choice.

Author: Jin H