The correct answer is B, Amazon Textract. Amazon Textract is a machine learning service that automatically extracts text and data from scanned documents, including PDF files and images. It is capable of recognizing and extracting information from forms, tables, and handwriting, making it the ideal choice for automating the process of capturing enrollment data from scanned paper forms. The other options are not suitable for this task: Amazon Rekognition is used for image and video analysis, Amazon Transcribe is for converting speech to text, and Amazon Comprehend is for natural language processing.