ExAws.Rekognition

Rekognition uses ex_aws under the hood so you should go through their README for more information on how to setup/configure the project, it's really easy.

You can check AWS Rekognition documentation for the list of functionalities and available actions.

Action	Supported
CompareFaces	✅
CreateCollection	✅
CreateStreamProcessor	✅
DeleteCollection	✅
DeleteFaces	✅
DeleteStreamProcessor	✅
DescribeCollection	✅
DescribeStreamProcessor	✅
DetectFaces	✅
DetectLabels	✅
DetectModerationLabels	✅
DetectText	✅
GetCelebrityInfo	✅
GetCelebrityRecognition	✅
GetContentModeration	✅
GetFaceDetection	✅
GetFaceSearch	✅
GetLabelDetection	✅
GetPersonTracking	✅
IndexFaces	✅
ListCollections	✅
ListFaces	✅
ListStreamProcessors	✅
RecognizeCelebrities	✅
SearchFaces	✅
SearchFacesByImage	✅
StartCelebrityRecognition	✅
StartContentModeration	✅
StartFaceDetection	✅
StartFaceSearch	✅
StartLabelDetection	✅
StartPersonTracking	✅
StartStreamProcessor	✅
StopStreamProcessor	✅

Installation

The package can be installed by adding ex_aws_rekognition to your list of dependencies in mix.exs:

def deps do
  [
    {:ex_aws_rekognition, "~> 0.6.0"}
  ]
end

Usage

  {:ok, source_image_binary} = File.read("path/to/face_source.jpeg")
  {:ok, target_image_binary} = File.read("path/to/face_target.jpeg")

  ExAws.Rekognition.compare_faces(
    source_image_binary,
    target_image_binary,
    similarity_threshold: 0.5
  )
  |> ExAws.request()

Complete documentation can be found at https://hexdocs.pm/ex_aws_rekognition/ExAws.Rekognition.html.