Amazonka.Rekognition.CompareFaces

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

If the source image contains multiple faces, the service detects the largest face and compares it with each face detected in the target image.

CompareFaces uses machine learning algorithms, which are probabilistic. A false negative is an incorrect prediction that a face in the target image has a low similarity confidence score when compared to the face in the source image. To reduce the probability of false negatives, we recommend that you compare the target image against multiple source images. If you plan to use CompareFaces to make a decision that impacts an individual's rights, privacy, or access to services, we recommend that you pass the result to a human for review and further validation before taking action.

You pass the input and target images either as base64-encoded image bytes or as references to images in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, passing image bytes isn't supported. The image must be formatted as a PNG or JPEG file.

In response, the operation returns an array of face matches ordered by similarity score in descending order. For each face match, the response provides a bounding box of the face, facial landmarks, pose details (pitch, roll, and yaw), quality (brightness and sharpness), and confidence value (indicating the level of confidence that the bounding box contains a face). The response also provides a similarity score, which indicates how closely the faces match.

By default, only faces with a similarity score of greater than or equal to 80% are returned in the response. You can change this value by specifying the SimilarityThreshold parameter.

CompareFaces also returns an array of faces that don't match the source image. For each face, it returns a bounding box, confidence value, landmarks, pose details, and quality. The response also returns information about the face in the source image, including the bounding box of the face and confidence value.

The QualityFilter input parameter allows you to filter out detected faces that don’t meet a required quality bar. The quality bar is based on a variety of common use cases. Use QualityFilter to set the quality bar by specifying LOW, MEDIUM, or HIGH. If you do not want to filter detected faces, specify NONE. The default value is NONE.

If the image doesn't contain Exif metadata, CompareFaces returns orientation information for the source and target images. Use these values to display the images with the correct image orientation.

If no faces are detected in the source or target images, CompareFaces returns an InvalidParameterException error.

This is a stateless API operation. That is, data returned by this operation doesn't persist.

For an example, see Comparing Faces in Images in the Amazon Rekognition Developer Guide.

This operation requires permissions to perform the rekognition:CompareFaces action.

Creating a Request

data CompareFaces

See: newCompareFaces smart constructor.

Constructors

CompareFaces'

Fields

• qualityFilter :: Maybe QualityFilter

  A filter that specifies a quality bar for how much filtering is done to identify faces. Filtered faces aren't compared. If you specify AUTO, Amazon Rekognition chooses the quality bar. If you specify LOW, MEDIUM, or HIGH, filtering removes all faces that don’t meet the chosen quality bar. The quality bar is based on a variety of common use cases. Low-quality detections can occur for a number of reasons. Some examples are an object that's misidentified as a face, a face that's too blurry, or a face with a pose that's too extreme to use. If you specify NONE, no filtering is performed. The default value is NONE.

  To use quality filtering, the collection you are using must be associated with version 3 of the face model or higher.

• similarityThreshold :: Maybe Double

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

• sourceImage :: Image

  The input image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

  If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

• targetImage :: Image

  The target image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

  If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

Instances

ToJSON CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

toJSON :: CompareFaces -> Value

toEncoding :: CompareFaces -> Encoding

toJSONList :: [CompareFaces] -> Value

toEncodingList :: [CompareFaces] -> Encoding

ToHeaders CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

toHeaders :: CompareFaces -> [Header]

ToPath CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

toPath :: CompareFaces -> ByteString

ToQuery CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

toQuery :: CompareFaces -> QueryString

AWSRequest CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Associated Types

type AWSResponse CompareFaces

Methods

request :: (Service -> Service) -> CompareFaces -> Request CompareFaces

response :: MonadResource m => (ByteStringLazy -> IO ByteStringLazy) -> Service -> Proxy CompareFaces -> ClientResponse ClientBody -> m (Either Error (ClientResponse (AWSResponse CompareFaces)))

Generic CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Associated Types

type Rep CompareFaces :: Type -> Type

Methods

from :: CompareFaces -> Rep CompareFaces x

to :: Rep CompareFaces x -> CompareFaces

Read CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

readsPrec :: Int -> ReadS CompareFaces

readList :: ReadS [CompareFaces]

readPrec :: ReadPrec CompareFaces

readListPrec :: ReadPrec [CompareFaces]

Show CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

showsPrec :: Int -> CompareFaces -> ShowS

show :: CompareFaces -> String

showList :: [CompareFaces] -> ShowS

NFData CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

rnf :: CompareFaces -> ()

Eq CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

(==) :: CompareFaces -> CompareFaces -> Bool

(/=) :: CompareFaces -> CompareFaces -> Bool

Hashable CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

Methods

hashWithSalt :: Int -> CompareFaces -> Int

hash :: CompareFaces -> Int

type AWSResponse CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

type AWSResponse CompareFaces = CompareFacesResponse

type Rep CompareFaces

Defined in Amazonka.Rekognition.CompareFaces

type Rep CompareFaces = D1 ('MetaData "CompareFaces" "Amazonka.Rekognition.CompareFaces" "amazonka-rekognition-2.0-EaCrS9R3rWADqefEZvOx5B" 'False) (C1 ('MetaCons "CompareFaces'" 'PrefixI 'True) ((S1 ('MetaSel ('Just "qualityFilter") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe QualityFilter)) :*: S1 ('MetaSel ('Just "similarityThreshold") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Double))) :*: (S1 ('MetaSel ('Just "sourceImage") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Image) :*: S1 ('MetaSel ('Just "targetImage") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Image))))

newCompareFaces

Arguments

:: Image

$sel:sourceImage:CompareFaces'

-> Image

$sel:targetImage:CompareFaces'

-> CompareFaces

Create a value of CompareFaces with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:qualityFilter:CompareFaces', compareFaces_qualityFilter - A filter that specifies a quality bar for how much filtering is done to identify faces. Filtered faces aren't compared. If you specify AUTO, Amazon Rekognition chooses the quality bar. If you specify LOW, MEDIUM, or HIGH, filtering removes all faces that don’t meet the chosen quality bar. The quality bar is based on a variety of common use cases. Low-quality detections can occur for a number of reasons. Some examples are an object that's misidentified as a face, a face that's too blurry, or a face with a pose that's too extreme to use. If you specify NONE, no filtering is performed. The default value is NONE.

To use quality filtering, the collection you are using must be associated with version 3 of the face model or higher.

$sel:similarityThreshold:CompareFaces', compareFaces_similarityThreshold - The minimum level of confidence in the face matches that a match must meet to be included in the FaceMatches array.

$sel:sourceImage:CompareFaces', compareFaces_sourceImage - The input image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

$sel:targetImage:CompareFaces', compareFaces_targetImage - The target image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

Request Lenses

compareFaces_qualityFilter :: Lens' CompareFaces (Maybe QualityFilter)

A filter that specifies a quality bar for how much filtering is done to identify faces. Filtered faces aren't compared. If you specify AUTO, Amazon Rekognition chooses the quality bar. If you specify LOW, MEDIUM, or HIGH, filtering removes all faces that don’t meet the chosen quality bar. The quality bar is based on a variety of common use cases. Low-quality detections can occur for a number of reasons. Some examples are an object that's misidentified as a face, a face that's too blurry, or a face with a pose that's too extreme to use. If you specify NONE, no filtering is performed. The default value is NONE.

To use quality filtering, the collection you are using must be associated with version 3 of the face model or higher.

compareFaces_similarityThreshold :: Lens' CompareFaces (Maybe Double)

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

compareFaces_sourceImage :: Lens' CompareFaces Image

The input image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

compareFaces_targetImage :: Lens' CompareFaces Image

The target image as base64-encoded bytes or an S3 object. If you use the AWS CLI to call Amazon Rekognition operations, passing base64-encoded image bytes is not supported.

If you are using an AWS SDK to call Amazon Rekognition, you might not need to base64-encode image bytes passed using the Bytes field. For more information, see Images in the Amazon Rekognition developer guide.

Destructuring the Response

data CompareFacesResponse

See: newCompareFacesResponse smart constructor.

Constructors

CompareFacesResponse'

Fields

• faceMatches :: Maybe [CompareFacesMatch]

  An array of faces in the target image that match the source image face. Each CompareFacesMatch object provides the bounding box, the confidence level that the bounding box contains a face, and the similarity score for the face in the bounding box and the face in the source image.

• sourceImageFace :: Maybe ComparedSourceImageFace

  The face in the source image that was used for comparison.

• sourceImageOrientationCorrection :: Maybe OrientationCorrection

  The value of SourceImageOrientationCorrection is always null.

  If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

  Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

• targetImageOrientationCorrection :: Maybe OrientationCorrection

  The value of TargetImageOrientationCorrection is always null.

  If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

  Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

• unmatchedFaces :: Maybe [ComparedFace]

  An array of faces in the target image that did not match the source image face.

• httpStatus :: Int

  The response's http status code.

Instances

Generic CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

Associated Types

type Rep CompareFacesResponse :: Type -> Type

Methods

from :: CompareFacesResponse -> Rep CompareFacesResponse x

to :: Rep CompareFacesResponse x -> CompareFacesResponse

Read CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

Methods

readsPrec :: Int -> ReadS CompareFacesResponse

readList :: ReadS [CompareFacesResponse]

readPrec :: ReadPrec CompareFacesResponse

readListPrec :: ReadPrec [CompareFacesResponse]

Show CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

Methods

showsPrec :: Int -> CompareFacesResponse -> ShowS

show :: CompareFacesResponse -> String

showList :: [CompareFacesResponse] -> ShowS

NFData CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

Methods

rnf :: CompareFacesResponse -> ()

Eq CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

Methods

(==) :: CompareFacesResponse -> CompareFacesResponse -> Bool

(/=) :: CompareFacesResponse -> CompareFacesResponse -> Bool

type Rep CompareFacesResponse

Defined in Amazonka.Rekognition.CompareFaces

type Rep CompareFacesResponse = D1 ('MetaData "CompareFacesResponse" "Amazonka.Rekognition.CompareFaces" "amazonka-rekognition-2.0-EaCrS9R3rWADqefEZvOx5B" 'False) (C1 ('MetaCons "CompareFacesResponse'" 'PrefixI 'True) ((S1 ('MetaSel ('Just "faceMatches") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [CompareFacesMatch])) :*: (S1 ('MetaSel ('Just "sourceImageFace") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ComparedSourceImageFace)) :*: S1 ('MetaSel ('Just "sourceImageOrientationCorrection") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe OrientationCorrection)))) :*: (S1 ('MetaSel ('Just "targetImageOrientationCorrection") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe OrientationCorrection)) :*: (S1 ('MetaSel ('Just "unmatchedFaces") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [ComparedFace])) :*: S1 ('MetaSel ('Just "httpStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int)))))

newCompareFacesResponse

Arguments

:: Int

$sel:httpStatus:CompareFacesResponse'

-> CompareFacesResponse

Create a value of CompareFacesResponse with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

CompareFacesResponse, compareFacesResponse_faceMatches - An array of faces in the target image that match the source image face. Each CompareFacesMatch object provides the bounding box, the confidence level that the bounding box contains a face, and the similarity score for the face in the bounding box and the face in the source image.

$sel:sourceImageFace:CompareFacesResponse', compareFacesResponse_sourceImageFace - The face in the source image that was used for comparison.

$sel:sourceImageOrientationCorrection:CompareFacesResponse', compareFacesResponse_sourceImageOrientationCorrection - The value of SourceImageOrientationCorrection is always null.

If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

$sel:targetImageOrientationCorrection:CompareFacesResponse', compareFacesResponse_targetImageOrientationCorrection - The value of TargetImageOrientationCorrection is always null.

If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

$sel:unmatchedFaces:CompareFacesResponse', compareFacesResponse_unmatchedFaces - An array of faces in the target image that did not match the source image face.

$sel:httpStatus:CompareFacesResponse', compareFacesResponse_httpStatus - The response's http status code.

Response Lenses

compareFacesResponse_faceMatches :: Lens' CompareFacesResponse (Maybe [CompareFacesMatch])

An array of faces in the target image that match the source image face. Each CompareFacesMatch object provides the bounding box, the confidence level that the bounding box contains a face, and the similarity score for the face in the bounding box and the face in the source image.

compareFacesResponse_sourceImageFace :: Lens' CompareFacesResponse (Maybe ComparedSourceImageFace)

The face in the source image that was used for comparison.

compareFacesResponse_sourceImageOrientationCorrection :: Lens' CompareFacesResponse (Maybe OrientationCorrection)

The value of SourceImageOrientationCorrection is always null.

If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

compareFacesResponse_targetImageOrientationCorrection :: Lens' CompareFacesResponse (Maybe OrientationCorrection)

The value of TargetImageOrientationCorrection is always null.

If the input image is in .jpeg format, it might contain exchangeable image file format (Exif) metadata that includes the image's orientation. Amazon Rekognition uses this orientation information to perform image correction. The bounding box coordinates are translated to represent object locations after the orientation information in the Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

Amazon Rekognition doesn’t perform image correction for images in .png format and .jpeg images without orientation information in the image Exif metadata. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

compareFacesResponse_unmatchedFaces :: Lens' CompareFacesResponse (Maybe [ComparedFace])

An array of faces in the target image that did not match the source image face.

compareFacesResponse_httpStatus :: Lens' CompareFacesResponse Int

The response's http status code.