CmdID / aws / aws rekognition

aws rekognition compare-faces

Compares a face in the source input image with each of the 100 largest faces detected in the target input image. AWS CLI reference

1 example 4 options Its page in the AWS CLI reference

Examples

from aws-cli, each command read by CmdID

To compare faces in two images

The following compare-faces example compares faces in two images stored in an Amazon S3 bucket.

aws rekognition compare-faces --source-image '{"S3Object":{"Bucket":"MyImageS3Bucket","Name":"source.jpg"}}' --target-image '{"S3Object":{"Bucket":"MyImageS3Bucket","Name":"target.jpg"}}'

Identify

--source-imageThe input image as base64-encoded bytes or an S3 object.

--target-imageThe target image as base64-encoded bytes or an S3 object.

Its output, shortened

{
    "UnmatchedFaces": [],
    "FaceMatches": [
        {
            "Face": {
                "BoundingBox": {
                    "Width": 0.12368916720151901,
                    "Top": 0.16007372736930847,
                    "Left": 0.5901257991790771,
                    "Height": 0.25140416622161865
                },
                "Confidence": 100.0,
                "Pose": {
                    "Yaw": -3.7351467609405518,
                    "Roll": -0.10309021919965744,
                    "Pitch": 0.8637830018997192
                },
                "Quality": {
                    "Sharpness": 95.51618957519531,
                    "Brightness": 65.29893493652344
                },
                "Landmarks": [
                    {
                        "Y": 0.26721030473709106,
                        "X": 0.6204193830490112,
                        "Type": "eyeLeft"
                    },
                    {
                        "Y": 0.26831310987472534,
                        "X": 0.6776827573776245,
… 32 more lines

For more information, see Comparing Faces in Images in the Amazon Rekognition Developer Guide.

Options

4 in the AWS CLI reference

--quality-filterA filter that specifies a quality bar for how much filtering is done to identify faces.

--similarity-thresholdThe minimum level of confidence in the face matches that a match must meet to be included in the FaceMatches array.

--source-imageThe input image as base64-encoded bytes or an S3 object.

--target-imageThe target image as base64-encoded bytes or an S3 object.