Which service would you use to analyze and process images and videos with deep learning?

• A. Amazon Textract
• B. Amazon Rekognition
• C. Amazon Polly
• D. Amazon Translate

Answer: (B)

Amazon Rekognition is the service designed for analyzing and processing images and videos using deep learning. It can detect objects, scenes, and activities in images; perform facial analysis (such as estimating age range and emotions) and facial recognition; detect and extract text within images; and analyze videos with labeling, motion/activity detection, and people tracking across frames. This broad, vision-focused capability set is built specifically for deep-learning-powered image and video analysis, making it the right choice for these tasks.

Other services serve different purposes: Textract specializes in extracting text and data from documents; Polly converts text to lifelike speech; Translate handles language translation.