Explanation

Amazon Textract is the correct AWS service for extracting key-value pairs from scanned documents like invoices and forms.

Why Amazon Textract?

• Purpose: Amazon Textract is specifically designed for document text extraction, including structured data like key-value pairs from forms, tables, and documents
• Capabilities: It can automatically detect and extract text, forms (key-value pairs), tables, and other structured data from scanned documents
• Use Case: Perfect for processing invoices, forms, and other business documents where you need to extract specific fields like names, amounts, dates, etc.

Why not the others?

• Amazon Rekognition: Primarily for image and video analysis (facial recognition, object detection, etc.), not document text extraction
• Amazon Comprehend: For natural language processing and text analysis (sentiment analysis, entity recognition, etc.), but not specifically designed for document form extraction
• Amazon OpenSearch: A search and analytics engine, not a document processing service

Amazon Textract uses machine learning to understand the layout and structure of documents, making it ideal for financial institutions processing large volumes of scanned invoices and forms.