Feature-level notice: Streaming Events and Batch Image Content Moderation have been closed to new customers since April 30, 2026. The rest of Amazon Rekognition is not affected.
What is Amazon Rekognition?
Amazon Rekognition is a fully managed computer vision service from AWS that enables image and video analysis without machine learning expertise. The service provides pre built models for common analysis scenarios like face detection, object recognition, text extraction, and content moderation. With Custom Labels, you can also train Rekognition on your own categories.
Rekognition processes images and videos through simple API calls. You upload media to S3 or send it directly to the API and receive structured analysis results with confidence scores. The service scales automatically and requires no infrastructure management.
Core Features
- Face Detection: Detection, comparison, and analysis of faces in images and videos
- Object Recognition: Identification of thousands of objects, scenes, and activities
- Text Extraction: OCR for text in images like signs, documents, or license plates
- Content Moderation: Detection of inappropriate, offensive, or unwanted content
- Custom Labels: Train your own models for specific objects or categories
Typical Use Cases
Content Moderation for Platforms
Automate moderation of user generated content. Rekognition detects inappropriate images and videos before they are published. You define thresholds for different categories and escalate borderline cases for manual review.
Identity Verification
Compare faces on ID documents with selfies for secure onboarding processes. Rekognition also detects liveness to prevent fraud with photos of photos. Ideal for financial services, e-commerce, and digital services.
Visual Quality Control
With Custom Labels, train Rekognition on your products and automatically detect defects in manufacturing. The service identifies scratches, dents, or assembly errors in real time directly on the production line.
Advantages
- No ML expertise required for standard analyses
- Pay per use without upfront costs or minimum quantities
- Fast integration via REST APIs and SDKs
- Custom Labels for company specific applications
Integration with innFactory
As an AWS Reseller, innFactory supports you with Amazon Rekognition: architecture design for computer vision applications, Custom Labels training, integration into existing workflows, and compliance compliant implementation.
Typical Use Cases
Frequently Asked Questions
What is Amazon Rekognition?
Amazon Rekognition is a fully managed AI service for image and video analysis. It provides pre built machine learning models for face detection, object recognition, text extraction, and content moderation without requiring ML expertise.
What analysis features does Rekognition offer?
Rekognition offers face detection and comparison, object recognition with thousands of labels, text extraction from images, content moderation for inappropriate content, celebrity recognition, and custom labels for your own categories.
Can I train Rekognition with my own categories?
Yes, with Custom Labels you can train Rekognition on your specific objects. You upload labeled example images, and Rekognition automatically trains a customized model for your application.
How does video analysis work?
Rekognition Video analyzes stored videos in S3 or real time streams. It detects people, objects, and activities over time, tracks faces through videos, and can identify segments with specific content.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of AWS (official documentation). This page does not represent an offer by AWS.