A computer vision service that analyzes images and video: object and scene detection, facial recognition, content moderation, and person tracking, via an API without needing to train your own models.
In AIF-C01 (Domain 3) it is compared to Textract (extracts text from documents) and Comprehend (analyzes text, not images). Question: detecting inappropriate content in images uploaded by users → Amazon Rekognition.
Amazon Rekognition is a concept that can show up on the exam. Check the full guide to see it in context.