An array of PPE types that you want to summarize.

The image in which you want to detect PPE on detected persons. The image can be passed as image bytes or you can reference an image stored in an Amazon S3 bucket.

Summary information for the types of PPE specified in the SummarizationAttributes input parameter.

The version number of the PPE detection model used to detect PPE in the image.

An array of persons detected in the image (including persons not wearing PPE).

The response's http status code.

The Amazon Resource Name (ARN) of the project that you want to delete.

The current status of the delete project operation.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The Amazon SNS topic ARN that you want Amazon Rekognition Video to publish the completion status of the celebrity recognition analysis to. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy.

Idempotent token used to identify the start request. If you use the same token with multiple StartCelebrityRecognition requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

The video in which you want to recognize celebrities. The video must be stored in an Amazon S3 bucket.

The identifier for the celebrity recognition analysis job. Use JobId to identify the job in a subsequent call to GetCelebrityRecognition.

The response's http status code.

If the previous response was incomplete (because there are more persons to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of persons.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Sort to use for elements in the Persons array. Use TIMESTAMP to sort array elements by the time persons are detected. Use INDEX to sort by the tracked persons. If you sort by INDEX, the array elements for each person are sorted by detection confidence. The default sort is by TIMESTAMP.

The identifier for a job that tracks persons in a video. You get the JobId from a call to StartPersonTracking.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of persons.

Information about a video that Amazon Rekognition Video analyzed. Videometadata is returned in every page of paginated responses from a Amazon Rekognition Video operation.

If the job fails, StatusMessage provides a descriptive error message.

The current status of the person tracking job.

An array of the persons detected in the video and the time(s) their path was tracked throughout the video. An array element will exist for each time a person's path is tracked.

The response's http status code.

If the previous response was incomplete (because there are more labels to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of text.

Maximum number of results to return per paginated call. The largest value you can specify is 1000.

Job identifier for the text detection operation for which you want results returned. You get the job identifer from an initial call to StartTextDetection.

An array of text detected in the video. Each element contains the detected text, the time in milliseconds from the start of the video that the text was detected, and where it was detected on the screen.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of text.

Undocumented member.

If the job fails, StatusMessage provides a descriptive error message.

Version number of the text detection model that was used to detect text.

Current status of the text detection job.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

Filters for technical cue or shot detection.

The ARN of the Amazon SNS topic to which you want Amazon Rekognition Video to publish the completion status of the segment detection operation. Note that the Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy to access the topic.

Idempotent token used to identify the start request. If you use the same token with multiple StartSegmentDetection requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

Undocumented member.

An array of segment types to detect in the video. Valid values are TECHNICAL_CUE and SHOT.

Unique identifier for the segment detection job. The JobId is returned from StartSegmentDetection.

The response's http status code.

Pagination token from the previous response.

Maximum number of collection IDs to return.

An array of collection IDs.

If the result is truncated, the response provides a NextToken that you can use in the subsequent request to fetch the next set of collection IDs.

Version numbers of the face detection models associated with the collections in the array CollectionIds. For example, the value of FaceModelVersions[2] is the version number for the face detection model used by the collection in CollectionId[2].

The response's http status code.

The Amazon Resource Name(ARN) of the model version that you want to start.

The minimum number of inference units to use. A single inference unit represents 1 hour of processing and can support up to 5 Transaction Pers Second (TPS). Use a higher number to increase the TPS throughput of your model. You are charged for the number of inference units that you use.

The current running status of the model.

The response's http status code.

ID of the collection to delete.

HTTP status code that indicates the result of the operation.

The response's http status code.

A set of tags (key-value pairs) that you want to attach to the collection.

ID for the collection that you are creating.

Version number of the face detection model associated with the collection you are creating.

Amazon Resource Name (ARN) of the collection. You can use this to manage permissions on your resources.

HTTP status code indicating the result of the operation.

The response's http status code.

The name of a stream processor created by CreateStreamProcessor.

The response's http status code.

Specifies the minimum confidence level for the labels to return. Amazon Rekognition doesn't return any labels with confidence lower than this specified value.

If MinConfidence is not specified, the operation returns labels with a confidence values greater than or equal to 55 percent.

Maximum number of labels you want the service to return in the response. The service returns the specified number of highest confidence labels.

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

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.

An array of labels for the real-world objects detected.

The value of OrientationCorrection 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.

Version number of the label detection model that was used to detect labels.

The response's http status code.

Amazon Resource Name (ARN) of the model, collection, or stream processor that contains the tags that you want a list of.

A list of key-value tags assigned to the resource.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The Amazon SNS topic ARN that you want Amazon Rekognition Video to publish the completion status of the content analysis to. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy to access the topic.

Idempotent token used to identify the start request. If you use the same token with multiple StartContentModeration requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

Specifies the minimum confidence that Amazon Rekognition must have in order to return a moderated content label. Confidence represents how certain Amazon Rekognition is that the moderated content is correctly identified. 0 is the lowest confidence. 100 is the highest confidence. Amazon Rekognition doesn't return any moderated content labels with a confidence level lower than this specified value. If you don't specify MinConfidence, GetContentModeration returns labels with confidence values greater than or equal to 50 percent.

The video in which you want to detect inappropriate, unwanted, or offensive content. The video must be stored in an Amazon S3 bucket.

The identifier for the content analysis job. Use JobId to identify the job in a subsequent call to GetContentModeration.

The response's http status code.

A filter that specifies a quality bar for how much filtering is done to identify faces. Filtered faces aren't searched for in the collection. 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.

(Optional) Specifies the minimum confidence in the face match to return. For example, don't return any matches where confidence in matches is less than 70%. The default value is 80%.

Maximum number of faces to return. The operation returns the maximum number of faces with the highest confidence in the match.

ID of the collection to search.

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.

An array of faces that match the input face, along with the confidence in the match.

Version number of the face detection model associated with the input collection (CollectionId).

The bounding box around the face in the input image that Amazon Rekognition used for the search.

The level of confidence that the searchedFaceBoundingBox, contains a face.

The response's http status code.

If the previous response was incomplete (because there are more stream processors to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of stream processors.

Maximum number of stream processors you want Amazon Rekognition Video to return in the response. The default is 1000.

List of stream processors that you have created.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of stream processors.

The response's http status code.

The ID of the collection to describe.

The version of the face model that's used by the collection for face detection.

For more information, see Model Versioning in the Amazon Rekognition Developer Guide.

The number of faces that are indexed into the collection. To index faces into a collection, use IndexFaces.

The number of milliseconds since the Unix epoch time until the creation of the collection. The Unix epoch time is 00:00:00 Coordinated Universal Time (UTC), Thursday, 1 January 1970.

The Amazon Resource Name (ARN) of the collection.

The response's http status code.

The Amazon Resource Name (ARN) of the model version that you want to delete.

The status of the deletion operation.

The response's http status code.

If the previous response was incomplete (because there is more results to retrieve), Amazon Rekognition Custom Labels returns a pagination token in the response. You can use this pagination token to retrieve the next set of results.

A list of model version names that you want to describe. You can add up to 10 model version names to the list. If you don't specify a value, all model descriptions are returned. A version name is part of a model (ProjectVersion) ARN. For example, my-model.2020-01-21T09.10.15 is the version name in the following ARN. arn:aws:rekognition:us-east-1:123456789012:project/getting-started/version/my-model.2020-01-21T09.10.15/1234567890123.

The maximum number of results to return per paginated call. The largest value you can specify is 100. If you specify a value greater than 100, a ValidationException error occurs. The default value is 100.

The Amazon Resource Name (ARN) of the project that contains the models you want to describe.

If the previous response was incomplete (because there is more results to retrieve), Amazon Rekognition Custom Labels returns a pagination token in the response. You can use this pagination token to retrieve the next set of results.

A list of model descriptions. The list is sorted by the creation date and time of the model versions, latest to earliest.

The response's http status code.

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.

Details about each celebrity found in the image. Amazon Rekognition can detect a maximum of 64 celebrities in an image. Each celebrity object includes the following attributes: Face, Confidence, Emotions, Landmarks, Pose, Quality, Smile, Id, KnownGender, MatchConfidence, Name, Urls.

Support for estimating image orientation using the the OrientationCorrection field has ceased as of August 2021. Any returned values for this field included in an API response will always be NULL.

The orientation of the input image (counterclockwise direction). If your application displays the image, you can use this value to correct the orientation. The bounding box coordinates returned in CelebrityFaces and UnrecognizedFaces represent face locations before the image orientation is corrected.

If the input image is in .jpeg format, it might contain exchangeable image (Exif) metadata that includes the image's orientation. If so, and the Exif metadata for the input image populates the orientation field, the value of OrientationCorrection is null. The CelebrityFaces and UnrecognizedFaces bounding box coordinates represent face locations after Exif metadata is used to correct the image orientation. Images in .png format don't contain Exif metadata.

Details about each unrecognized face in the image.

The response's http status code.

Specifies the minimum confidence level for the labels to return. DetectCustomLabels doesn't return any labels with a confidence value that's lower than this specified value. If you specify a value of 0, DetectCustomLabels returns all labels, regardless of the assumed threshold applied to each label. If you don't specify a value for MinConfidence, DetectCustomLabels returns labels based on the assumed threshold of each label.

Maximum number of results you want the service to return in the response. The service returns the specified number of highest confidence labels ranked from highest confidence to lowest.

The ARN of the model version that you want to use.

Undocumented member.

An array of custom labels detected in the input image.

The response's http status code.

If the previous response was incomplete (because there is more search results to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of search results.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Sort to use for grouping faces in the response. Use TIMESTAMP to group faces by the time that they are recognized. Use INDEX to sort by recognized faces.

The job identifer for the search request. You get the job identifier from an initial call to StartFaceSearch.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of search results.

Information about a video that Amazon Rekognition analyzed. Videometadata is returned in every page of paginated responses from a Amazon Rekognition Video operation.

If the job fails, StatusMessage provides a descriptive error message.

The current status of the face search job.

An array of persons, PersonMatch, in the video whose face(s) match the face(s) in an Amazon Rekognition collection. It also includes time information for when persons are matched in the video. You specify the input collection in an initial call to StartFaceSearch. Each Persons element includes a time the person was matched, face match details (FaceMatches) for matching faces in the collection, and person information (Person) for the matched person.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The Amazon SNS topic ARN you want Amazon Rekognition Video to publish the completion status of the label detection operation to. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy.

Idempotent token used to identify the start request. If you use the same token with multiple StartLabelDetection requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

Specifies the minimum confidence that Amazon Rekognition Video must have in order to return a detected label. Confidence represents how certain Amazon Rekognition is that a label is correctly identified.0 is the lowest confidence. 100 is the highest confidence. Amazon Rekognition Video doesn't return any labels with a confidence level lower than this specified value.

If you don't specify MinConfidence, the operation returns labels with confidence values greater than or equal to 50 percent.

The video in which you want to detect labels. The video must be stored in an Amazon S3 bucket.

The identifier for the label detection job. Use JobId to identify the job in a subsequent call to GetLabelDetection.

The response's http status code.

Optional value specifying the minimum confidence in the face match to return. For example, don't return any matches where confidence in matches is less than 70%. The default value is 80%.

Maximum number of faces to return. The operation returns the maximum number of faces with the highest confidence in the match.

ID of the collection the face belongs to.

ID of a face to find matches for in the collection.

An array of faces that matched the input face, along with the confidence in the match.

Version number of the face detection model associated with the input collection (CollectionId).

ID of the face that was searched for matches in a collection.

The response's http status code.

The ID you want to assign to all the faces detected in the image.

A filter that specifies a quality bar for how much filtering is done to identify faces. Filtered faces aren't indexed. 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 default value is AUTO. 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.

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

The maximum number of faces to index. The value of MaxFaces must be greater than or equal to 1. IndexFaces returns no more than 100 detected faces in an image, even if you specify a larger value for MaxFaces.

If IndexFaces detects more faces than the value of MaxFaces, the faces with the lowest quality are filtered out first. If there are still more faces than the value of MaxFaces, the faces with the smallest bounding boxes are filtered out (up to the number that's needed to satisfy the value of MaxFaces). Information about the unindexed faces is available in the UnindexedFaces array.

The faces that are returned by IndexFaces are sorted by the largest face bounding box size to the smallest size, in descending order.

MaxFaces can be used with a collection associated with any version of the face model.

An array of facial attributes that you want to be returned. This can be the default list of attributes or all attributes. If you don't specify a value for Attributes or if you specify ["DEFAULT"], the API returns the following subset of facial attributes: BoundingBox, Confidence, Pose, Quality, and Landmarks. If you provide ["ALL"], all facial attributes are returned, but the operation takes longer to complete.

If you provide both, ["ALL", "DEFAULT"], the service uses a logical AND operator to determine which attributes to return (in this case, all attributes).

The ID of an existing collection to which you want to add the faces that are detected in the input images.

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 isn't 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.

The version number of the face detection model that's associated with the input collection (CollectionId).

An array of faces detected and added to the collection. For more information, see Searching Faces in a Collection in the Amazon Rekognition Developer Guide.

If your collection is associated with a face detection model that's later than version 3.0, the value of OrientationCorrection is always null and no orientation information is returned.

If your collection is associated with a face detection model that's version 3.0 or earlier, the following applies:

• 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. The value of OrientationCorrection is null.
• If the image doesn't contain orientation information in its Exif metadata, Amazon Rekognition returns an estimated orientation (ROTATE_0, ROTATE_90, ROTATE_180, ROTATE_270). Amazon Rekognition doesn’t perform image correction for images. The bounding box coordinates aren't translated and represent the object locations before the image is rotated.

Bounding box information is returned in the FaceRecords array. You can get the version of the face detection model by calling DescribeCollection.

An array of faces that were detected in the image but weren't indexed. They weren't indexed because the quality filter identified them as low quality, or the MaxFaces request parameter filtered them out. To use the quality filter, you specify the QualityFilter request parameter.

The response's http status code.

If the previous response was incomplete (because there are more labels to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of labels.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Sort to use for elements in the Labels array. Use TIMESTAMP to sort array elements by the time labels are detected. Use NAME to alphabetically group elements for a label together. Within each label group, the array element are sorted by detection confidence. The default sort is by TIMESTAMP.

Job identifier for the label detection operation for which you want results returned. You get the job identifer from an initial call to StartlabelDetection.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of labels.

Information about a video that Amazon Rekognition Video analyzed. Videometadata is returned in every page of paginated responses from a Amazon Rekognition video operation.

If the job fails, StatusMessage provides a descriptive error message.

An array of labels detected in the video. Each element contains the detected label and the time, in milliseconds from the start of the video, that the label was detected.

The current status of the label detection job.

Version number of the label detection model that was used to detect labels.

The response's http status code.

The Amazon Resource Name (ARN) of the model version that you want to delete.

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

The current status of the stop operation.

The response's http status code.

Name of the stream processor for which you want information.

Current status of the stream processor.

Face recognition input parameters that are being used by the stream processor. Includes the collection to use for face recognition and the face attributes to detect.

Kinesis video stream that provides the source streaming video.

Kinesis data stream to which Amazon Rekognition Video puts the analysis results.

ARN of the stream processor.

Detailed status message about the stream processor.

Name of the stream processor.

Date and time the stream processor was created

The time, in Unix format, the stream processor was last updated. For example, when the stream processor moves from a running state to a failed state, or when the user starts or stops the stream processor.

ARN of the IAM role that allows access to the stream processor.

The response's http status code.

The minimum confidence in the person match to return. For example, don't return any matches where confidence in matches is less than 70%. The default value is 80%.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The ARN of the Amazon SNS topic to which you want Amazon Rekognition Video to publish the completion status of the search. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy to access the topic.

Idempotent token used to identify the start request. If you use the same token with multiple StartFaceSearch requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

The video you want to search. The video must be stored in an Amazon S3 bucket.

ID of the collection that contains the faces you want to search for.

The identifier for the search job. Use JobId to identify the job in a subsequent call to GetFaceSearch.

The response's http status code.

An identifier returned in the completion status published by your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

Optional parameters that let you set criteria the text must meet to be included in your response.

Undocumented member.

Idempotent token used to identify the start request. If you use the same token with multiple StartTextDetection requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidentaly started more than once.

Undocumented member.

Identifier for the text detection job. Use JobId to identify the job in a subsequent call to GetTextDetection.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The Amazon SNS topic ARN you want Amazon Rekognition Video to publish the completion status of the people detection operation to. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy.

Idempotent token used to identify the start request. If you use the same token with multiple StartPersonTracking requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

The video in which you want to detect people. The video must be stored in an Amazon S3 bucket.

The identifier for the person detection job. Use JobId to identify the job in a subsequent call to GetPersonTracking.

The response's http status code.

If the previous response was incomplete (because there is more recognized celebrities to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of celebrities.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Sort to use for celebrities returned in Celebrities field. Specify ID to sort by the celebrity identifier, specify TIMESTAMP to sort by the time the celebrity was recognized.

Job identifier for the required celebrity recognition analysis. You can get the job identifer from a call to StartCelebrityRecognition.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of celebrities.

Information about a video that Amazon Rekognition Video analyzed. Videometadata is returned in every page of paginated responses from a Amazon Rekognition Video operation.

If the job fails, StatusMessage provides a descriptive error message.

Array of celebrities recognized in the video.

The current status of the celebrity recognition job.

The response's http status code.

The name of the stream processor to start processing.

The response's http status code.

Optional parameters that let you set the criteria that the text must meet to be included in your response.

The input image as base64-encoded bytes or an Amazon S3 object. If you use the AWS CLI to call Amazon Rekognition operations, you can't pass image bytes.

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.

An array of text that was detected in the input image.

The model version used to detect text.

The response's http status code.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of text.

Maximum number of results to return per paginated call. The largest value you can specify is 1000.

Job identifier for the text detection operation for which you want results returned. You get the job identifer from an initial call to StartSegmentDetection.

An array containing the segment types requested in the call to StartSegmentDetection.

If the previous response was incomplete (because there are more labels to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of text.

Currently, Amazon Rekognition Video returns a single object in the VideoMetadata array. The object contains information about the video stream in the input file that Amazon Rekognition Video chose to analyze. The VideoMetadata object includes the video codec, video format and other information. Video metadata is returned in each page of information returned by GetSegmentDetection.

If the job fails, StatusMessage provides a descriptive error message.

An array of segments detected in a video. The array is sorted by the segment types (TECHNICAL_CUE or SHOT) specified in the SegmentTypes input parameter of StartSegmentDetection. Within each segment type the array is sorted by timestamp values.

Current status of the segment detection job.

An array of objects. There can be multiple audio streams. Each AudioMetadata object contains metadata for a single audio stream. Audio information in an AudioMetadata objects includes the audio codec, the number of audio channels, the duration of the audio stream, and the sample rate. Audio metadata is returned in each page of information returned by GetSegmentDetection.

The response's http status code.

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.

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

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.

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.

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.

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

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.

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.

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

The response's http status code.

An array of facial attributes you want to be returned. This can be the default list of attributes or all attributes. If you don't specify a value for Attributes or if you specify ["DEFAULT"], the API returns the following subset of facial attributes: BoundingBox, Confidence, Pose, Quality, and Landmarks. If you provide ["ALL"], all facial attributes are returned, but the operation takes longer to complete.

If you provide both, ["ALL", "DEFAULT"], the service uses a logical AND operator to determine which attributes to return (in this case, all attributes).

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.

The value of OrientationCorrection 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.

Details of each face found in the image.

The response's http status code.

If the previous response was incomplete (because there are more faces to retrieve), Amazon Rekognition Video returns a pagination token in the response. You can use this pagination token to retrieve the next set of faces.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Unique identifier for the face detection job. The JobId is returned from StartFaceDetection.

If the response is truncated, Amazon Rekognition returns this token that you can use in the subsequent request to retrieve the next set of faces.

Information about a video that Amazon Rekognition Video analyzed. Videometadata is returned in every page of paginated responses from a Amazon Rekognition video operation.

If the job fails, StatusMessage provides a descriptive error message.

An array of faces detected in the video. Each element contains a detected face's details and the time, in milliseconds from the start of the video, the face was detected.

The current status of the face detection job.

The response's http status code.

Amazon Resource Name (ARN) of the model, collection, or stream processor that you want to assign the tags to.

The key-value tags to assign to the resource.

The response's http status code.

If the previous response was incomplete (because there is more data to retrieve), Amazon Rekognition returns a pagination token in the response. You can use this pagination token to retrieve the next set of faces.

Maximum number of faces to return.

ID of the collection from which to list the faces.

Version number of the face detection model associated with the input collection (CollectionId).

If the response is truncated, Amazon Rekognition returns this token that you can use in the subsequent request to retrieve the next set of faces.

An array of Face objects.

The response's http status code.

The identifier for your AWS Key Management Service (AWS KMS) customer master key (CMK). You can supply the Amazon Resource Name (ARN) of your CMK, the ID of your CMK, an alias for your CMK, or an alias ARN. The key is used to encrypt training and test images copied into the service for model training. Your source images are unaffected. The key is also used to encrypt training results and manifest files written to the output Amazon S3 bucket (OutputConfig).

If you choose to use your own CMK, you need the following permissions on the CMK.

• kms:CreateGrant
• kms:DescribeKey
• kms:GenerateDataKey
• kms:Decrypt

If you don't specify a value for KmsKeyId, images copied into the service are encrypted using a key that AWS owns and manages.

A set of tags (key-value pairs) that you want to attach to the model.

The ARN of the Amazon Rekognition Custom Labels project that manages the model that you want to train.

A name for the version of the model. This value must be unique.

The Amazon S3 bucket location to store the results of training. The S3 bucket can be in any AWS account as long as the caller has s3:PutObject permissions on the S3 bucket.

The dataset to use for training.

The dataset to use for testing.

The ARN of the model version that was created. Use DescribeProjectVersion to get the current status of the training operation.

The response's http status code.

If the previous response was incomplete (because there is more results to retrieve), Amazon Rekognition Custom Labels returns a pagination token in the response. You can use this pagination token to retrieve the next set of results.

The maximum number of results to return per paginated call. The largest value you can specify is 100. If you specify a value greater than 100, a ValidationException error occurs. The default value is 100.

If the previous response was incomplete (because there is more results to retrieve), Amazon Rekognition Custom Labels returns a pagination token in the response. You can use this pagination token to retrieve the next set of results.

A list of project descriptions. The list is sorted by the date and time the projects are created.

The response's http status code.

If the previous response was incomplete (because there is more data to retrieve), Amazon Rekognition returns a pagination token in the response. You can use this pagination token to retrieve the next set of content moderation labels.

Maximum number of results to return per paginated call. The largest value you can specify is 1000. If you specify a value greater than 1000, a maximum of 1000 results is returned. The default value is 1000.

Sort to use for elements in the ModerationLabelDetections array. Use TIMESTAMP to sort array elements by the time labels are detected. Use NAME to alphabetically group elements for a label together. Within each label group, the array element are sorted by detection confidence. The default sort is by TIMESTAMP.

The identifier for the inappropriate, unwanted, or offensive content moderation job. Use JobId to identify the job in a subsequent call to GetContentModeration.

If the response is truncated, Amazon Rekognition Video returns this token that you can use in the subsequent request to retrieve the next set of content moderation labels.

Information about a video that Amazon Rekognition analyzed. Videometadata is returned in every page of paginated responses from GetContentModeration.

If the job fails, StatusMessage provides a descriptive error message.

The current status of the content moderation analysis job.

Version number of the moderation detection model that was used to detect inappropriate, unwanted, or offensive content.

The detected inappropriate, unwanted, or offensive content moderation labels and the time(s) they were detected.

The response's http status code.

Collection from which to remove the specific faces.

An array of face IDs to delete.

An array of strings (face IDs) of the faces that were deleted.

The response's http status code.

The ID for the celebrity. You get the celebrity ID from a call to the RecognizeCelebrities operation, which recognizes celebrities in an image.

An array of URLs pointing to additional celebrity information.

Retrieves the known gender for the celebrity.

The name of the celebrity.

The response's http status code.

The name of the stream processor you want to delete.

The response's http status code.

Amazon Resource Name (ARN) of the model, collection, or stream processor that you want to remove the tags from.

A list of the tags that you want to remove.

The response's http status code.

Sets up the configuration for human evaluation, including the FlowDefinition the image will be sent to.

Specifies the minimum confidence level for the labels to return. Amazon Rekognition doesn't return any labels with a confidence level lower than this specified value.

If you don't specify MinConfidence, the operation returns labels with confidence values greater than or equal to 50 percent.

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.

Shows the results of the human in the loop evaluation.

Version number of the moderation detection model that was used to detect unsafe content.

Array of detected Moderation labels and the time, in milliseconds from the start of the video, they were detected.

The response's http status code.

A set of tags (key-value pairs) that you want to attach to the stream processor.

Kinesis video stream stream that provides the source streaming video. If you are using the AWS CLI, the parameter name is StreamProcessorInput.

Kinesis data stream stream to which Amazon Rekognition Video puts the analysis results. If you are using the AWS CLI, the parameter name is StreamProcessorOutput.

An identifier you assign to the stream processor. You can use Name to manage the stream processor. For example, you can get the current status of the stream processor by calling DescribeStreamProcessor. Name is idempotent.

Face recognition input parameters to be used by the stream processor. Includes the collection to use for face recognition and the face attributes to detect.

ARN of the IAM role that allows access to the stream processor.

ARN for the newly create stream processor.

The response's http status code.

An identifier you specify that's returned in the completion notification that's published to your Amazon Simple Notification Service topic. For example, you can use JobTag to group related jobs and identify them in the completion notification.

The ARN of the Amazon SNS topic to which you want Amazon Rekognition Video to publish the completion status of the face detection operation. The Amazon SNS topic must have a topic name that begins with AmazonRekognition if you are using the AmazonRekognitionServiceRole permissions policy.

Idempotent token used to identify the start request. If you use the same token with multiple StartFaceDetection requests, the same JobId is returned. Use ClientRequestToken to prevent the same job from being accidently started more than once.

The face attributes you want returned.

DEFAULT - The following subset of facial attributes are returned: BoundingBox, Confidence, Pose, Quality and Landmarks.

ALL - All facial attributes are returned.

The video in which you want to detect faces. The video must be stored in an Amazon S3 bucket.

The identifier for the face detection job. Use JobId to identify the job in a subsequent call to GetFaceDetection.

The response's http status code.

The name of the project to create.

The Amazon Resource Name (ARN) of the new project. You can use the ARN to configure IAM access to the project.

The response's http status code.

The lowest estimated age.

The highest estimated age.

Undocumented member.

The audio codec used to encode or decode the audio stream.

The sample rate for the audio stream.

The number of audio channels in the segment.

The duration of the audio stream in milliseconds.

Boolean value that indicates whether the face has beard or not.

Level of confidence in the determination.

A threshold used to determine the maximum luminance value for a pixel to be considered black. In a full color range video, luminance values range from 0-255. A pixel value of 0 is pure black, and the most strict filter. The maximum black pixel value is computed as follows: max_black_pixel_value = minimum_luminance + MaxPixelThreshold *luminance_range.

For example, for a full range video with BlackPixelThreshold = 0.1, max_black_pixel_value is 0 + 0.1 * (255-0) = 25.5.

The default value of MaxPixelThreshold is 0.2, which maps to a max_black_pixel_value of 51 for a full range video. You can lower this threshold to be more strict on black levels.

The minimum percentage of pixels in a frame that need to have a luminance below the max_black_pixel_value for a frame to be considered a black frame. Luminance is calculated using the BT.709 matrix.

The default value is 99, which means at least 99% of all pixels in the frame are black pixels as per the MaxPixelThreshold set. You can reduce this value to allow more noise on the black frame.

Height of the bounding box as a ratio of the overall image height.

Left coordinate of the bounding box as a ratio of overall image width.

Width of the bounding box as a ratio of the overall image width.

Top coordinate of the bounding box as a ratio of overall image height.

The confidence, in percentage, that Amazon Rekognition has that the recognized face is the celebrity.

An array of URLs pointing to additional information about the celebrity. If there is no additional information about the celebrity, this list is empty.

Undocumented member.

The name of the celebrity.

A unique identifier for the celebrity.

Provides information about the celebrity's face, such as its location on the image.

Bounding box around the body of a celebrity.

An array of URLs pointing to additional celebrity information.

The confidence, in percentage, that Amazon Rekognition has that the recognized face is the celebrity.

The name of the celebrity.

The unique identifier for the celebrity.

Face details for the recognized celebrity.

Information about a recognized celebrity.

The time, in milliseconds from the start of the video, that the celebrity was recognized.

Level of confidence that the faces match.

Provides face metadata (bounding box and confidence that the bounding box actually contains a face).

Bounding box of the face.

The emotions that appear to be expressed on the face, and the confidence level in the determination. Valid values include "Happy", "Sad", "Angry", "Confused", "Disgusted", "Surprised", "Calm", "Unknown", and "Fear".

Indicates the pose of the face as determined by its pitch, roll, and yaw.