Back to Gap Map Infrastructure / Classic ML & computer vision

Amazon Rekognition

closed / Overall score: n/a

AWS's managed image and video analysis service, with pretrained APIs for labels, text, faces, face search and liveness, celebrities, content moderation and protective equipment. Custom Labels trains classifiers and detectors for a customer's own objects from as few as ten images with automated machine learning, inside the same service. It runs only as a hosted AWS API.

Openness

1 high confidence

1.0

license: Proprietary
source: closed(hosted AWS service

A managed AWS service with no published code or models and no self-hosted edition.

https://docs.aws.amazon.com/rekognition/latest/dg/what-is.html recorded 2026-09-26
Developer guide: "Amazon Rekognition is a cloud-based image and video analysis service" with "a simple, easy-to-use API that can quickly analyze any image or video file that's stored in Amazon S3".

Adoption

not assessed

AWS publishes no customer or request count for Rekognition, and it has no package or download count of its own, so no level is assigned.

https://aws.amazon.com/rekognition/ recorded 2026-09-26
The product page, read for a usage disclosure; it lists features and pricing but no customer or request count.

Capability

5 medium confidence

5.0

Rekognition covers both ends of computer vision in one service: pretrained analysis that needs no training, and Custom Labels, which searches for and trains a model for a customer's own objects from a handful of labeled images without any machine-learning work on their side. That automated path from labeled images to a deployed model is what AutoGluon does for tables.

https://aws.amazon.com/rekognition/ recorded 2026-09-26
Product page: "Custom labels: Detect custom objects, such as brand logos, using automated machine learning (AutoML) to train your models with as few as 10 images." Features also listed: face liveness, face detection and analysis, text detection, face compare and search, content moderation, labels, celebrity recognition, video segment detection.
https://docs.aws.amazon.com/rekognition/latest/dg/what-is.html recorded 2026-09-26
Developer guide capability list: object, scene and concept detection; text detection; unsafe content; celebrity recognition; facial analysis; Custom Labels ("Build custom classifiers to detect objects specific to your use case"); image properties; video analysis.

Verified 2026-09-26