Amazon Rekognition

What is it

A cloud-based image and video analysis service that makes it easy to add advanced computer vision capabilities to your applications.

Detect objects, scenes, activities, faces, text in images and videos, as well as analyze emotions, facial attributes, and compare faces.

Detection of inappropriate content in images and videos
Online identity verification (e.g., facial recognition for authentication)
Media analysis for indexing and search (e.g., identifying people, objects in videos)
Generation of smart alerts for connected homes (e.g., detecting people or packages at the door)
Security and surveillance analysis

Managed computer vision: No prior machine learning knowledge required to use
Image analysis: Detection of objects, scenes, faces, text, and inappropriate content
Video analysis: Detection of activities, people, objects, and inappropriate content in videos
Facial recognition: Face detection, analysis, and comparison
Customization: Allows training of custom models for specific use cases
Integration: Integrates with other AWS services like S3, Lambda, and CloudWatch

Amazon Rekognition: Offers a managed and scalable solution for computer vision, eliminating the need to build and train ML models from scratch. Ideal for those who need quick results and don't want to manage ML infrastructure.
Manual computer vision/libraries (e.g., OpenCV, TensorFlow): Offers greater control and flexibility for customization but requires knowledge in ML and programming, plus infrastructure management. Suitable for very specific use cases or research.