AWS Rekognition (Imaging AI)
Introductory example to AWS Rekognition. Amazon Rekognition makes it easy to add image and video analysis to your applications. You just provide an image or video to the Rekognition API, and the service can identify objects, people, text, scenes, and activities. It can detect any inappropriate content as well. Requirements: S3 bucket needs to be in EU-WEST-1. Docs: https://docs.aws.amazon.com/general/latest/gr/aws_service_limits.html#limits_rekognition https://docs.aws.amazon.com/rekognition/latest/dg/what-is.html
AWS Rekognition AI
Limits (transactions p/s)
US East (N. Virginia) Region – 50 US West (Oregon) Region – 50 EU (Ireland) Region – 50 US East (Ohio) Region – 5
Available Operations
CompareFaces DetectFaces DetectLabels DetectModerationLabels DetectText GetCelebrityInfo IndexFaces ListFaces RecognizeCelebrities SearchFaces SearchFacesByImage
Detect Faces (via aws-cli)
aws rekognition detect-faces --image '{"S3Object": {"Bucket":"mybucket.ai","Name":"people.jpg"}}' --attributes "ALL"
aws rekognition detect-faces --image '{"S3Object": {"Bucket":"coderecipes-pixels","Name":"sample-girl.jpg"}}' --attributes "ALL"
aws rekognition detect-labels --image '{"S3Object": {"Bucket":"coderecipes-pixels","Name":"mp3-player"}}'
Common Use Cases
your door camera can upload a photo of the visitor to Amazon S3, triggering a Lambda function that uses Rekognition API operations to identify your guest. You can run analysis directly on images stored in Amazon S3 without having to load or move the data.
Created on 12/6/2018