This is the Amazon Rekognition API reference.
", "operations": { - "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, role, 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.
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.
Creates a collection in an AWS Region. You can add faces to the collection using the IndexFaces operation.
For example, you might create collections, one for each of your application users. A user can then index faces using the IndexFaces operation and persist results in a specific collection. Then, a user can search the collection for faces in the user-specific container.
When you create a collection, it is associated with the latest version of the face model version.
Collection names are case-sensitive.
This operation requires permissions to perform the rekognition:CreateCollection action. If you want to tag your collection, you also require permission to perform the rekognition:TagResource operation.
Creates a new Amazon Rekognition Custom Labels dataset. You can create a dataset by using an Amazon Sagemaker format manifest file or by copying an existing Amazon Rekognition Custom Labels dataset.
To create a training dataset for a project, specify train for the value of DatasetType. To create the test dataset for a project, specify test for the value of DatasetType.
The response from CreateDataset is the Amazon Resource Name (ARN) for the dataset. Creating a dataset takes a while to complete. Use DescribeDataset to check the current status. The dataset created successfully if the value of Status is CREATE_COMPLETE.
To check if any non-terminal errors occurred, call ListDatasetEntries and check for the presence of errors lists in the JSON Lines.
Dataset creation fails if a terminal error occurs (Status = CREATE_FAILED). Currently, you can't access the terminal error information.
For more information, see Creating dataset in the Amazon Rekognition Custom Labels Developer Guide.
This operation requires permissions to perform the rekognition:CreateDataset action. If you want to copy an existing dataset, you also require permission to perform the rekognition:ListDatasetEntries action.
Creates a new Amazon Rekognition Custom Labels project. A project is a group of resources (datasets, model versions) that you use to create and manage Amazon Rekognition Custom Labels models.
This operation requires permissions to perform the rekognition:CreateProject action.
Detects instances of real-world entities within an image (JPEG or PNG) provided as input. This includes objects like flower, tree, and table; events like wedding, graduation, and birthday party; and concepts like landscape, evening, and nature.
For an example, see Analyzing Images Stored in an Amazon S3 Bucket in the Amazon Rekognition Developer Guide.
DetectLabels does not support the detection of activities. However, activity detection is supported for label detection in videos. For more information, see StartLabelDetection in the Amazon Rekognition Developer Guide.
You pass the input image as base64-encoded image bytes or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, passing image bytes is not supported. The image must be either a PNG or JPEG formatted file.
For each object, scene, and concept the API returns one or more labels. Each label provides the object name, and the level of confidence that the image contains the object. For example, suppose the input image has a lighthouse, the sea, and a rock. The response includes all three labels, one for each object.
{Name: lighthouse, Confidence: 98.4629}
{Name: rock,Confidence: 79.2097}
{Name: sea,Confidence: 75.061}
In the preceding example, the operation returns one label for each of the three objects. The operation can also return multiple labels for the same object in the image. For example, if the input image shows a flower (for example, a tulip), the operation might return the following three labels.
{Name: flower,Confidence: 99.0562}
{Name: plant,Confidence: 99.0562}
{Name: tulip,Confidence: 99.0562}
In this example, the detection algorithm more precisely identifies the flower as a tulip.
In response, the API returns an array of labels. In addition, the response also includes the orientation correction. Optionally, you can specify MinConfidence to control the confidence threshold for the labels returned. The default is 55%. You can also add the MaxLabels parameter to limit the number of labels returned.
If the object detected is a person, the operation doesn't provide the same facial details that the DetectFaces operation provides.
DetectLabels returns bounding boxes for instances of common object labels in an array of Instance objects. An Instance object contains a BoundingBox object, for the location of the label on the image. It also includes the confidence by which the bounding box was detected.
DetectLabels also returns a hierarchical taxonomy of detected labels. For example, a detected car might be assigned the label car. The label car has two parent labels: Vehicle (its parent) and Transportation (its grandparent). The response returns the entire list of ancestors for a label. Each ancestor is a unique label in the response. In the previous example, Car, Vehicle, and Transportation are returned as unique labels in the response.
This is a stateless API operation. That is, the operation does not persist any data.
This operation requires permissions to perform the rekognition:DetectLabels action.
Detects unsafe content in a specified JPEG or PNG format image. Use DetectModerationLabels to moderate images depending on your requirements. For example, you might want to filter images that contain nudity, but not images containing suggestive content.
To filter images, use the labels returned by DetectModerationLabels to determine which types of content are appropriate.
For information about moderation labels, see Detecting Unsafe Content in the Amazon Rekognition Developer Guide.
You pass the input image either as base64-encoded image bytes or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, passing image bytes is not supported. The image must be either a PNG or JPEG formatted file.
", "DetectProtectiveEquipment": "Detects Personal Protective Equipment (PPE) worn by people detected in an image. Amazon Rekognition can detect the following types of PPE.
Face cover
Hand cover
Head cover
You pass the input image as base64-encoded image bytes or as a reference to an image in an Amazon S3 bucket. The image must be either a PNG or JPG formatted file.
DetectProtectiveEquipment detects PPE worn by up to 15 persons detected in an image.
For each person detected in the image the API returns an array of body parts (face, head, left-hand, right-hand). For each body part, an array of detected items of PPE is returned, including an indicator of whether or not the PPE covers the body part. The API returns the confidence it has in each detection (person, PPE, body part and body part coverage). It also returns a bounding box (BoundingBox) for each detected person and each detected item of PPE.
You can optionally request a summary of detected PPE items with the SummarizationAttributes input parameter. The summary provides the following information.
The persons detected as wearing all of the types of PPE that you specify.
The persons detected as not wearing all of the types PPE that you specify.
The persons detected where PPE adornment could not be determined.
This is a stateless API operation. That is, the operation does not persist any data.
This operation requires permissions to perform the rekognition:DetectProtectiveEquipment action.
Detects text in the input image and converts it into machine-readable text.
Pass the input image as base64-encoded image bytes or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, you must pass it as a reference to an image in an Amazon S3 bucket. For the AWS CLI, passing image bytes is not supported. The image must be either a .png or .jpeg formatted file.
The DetectText operation returns text in an array of TextDetection elements, TextDetections. Each TextDetection element provides information about a single word or line of text that was detected in the image.
A word is one or more ISO basic latin script characters that are not separated by spaces. DetectText can detect up to 100 words in an image.
A line is a string of equally spaced words. A line isn't necessarily a complete sentence. For example, a driver's license number is detected as a line. A line ends when there is no aligned text after it. Also, a line ends when there is a large gap between words, relative to the length of the words. This means, depending on the gap between words, Amazon Rekognition may detect multiple lines in text aligned in the same direction. Periods don't represent the end of a line. If a sentence spans multiple lines, the DetectText operation returns multiple lines.
To determine whether a TextDetection element is a line of text or a word, use the TextDetection object Type field.
To be detected, text must be within +/- 90 degrees orientation of the horizontal axis.
For more information, see DetectText in the Amazon Rekognition Developer Guide.
", + "DetectText": "Detects text in the input image and converts it into machine-readable text.
Pass the input image as base64-encoded image bytes or as a reference to an image in an Amazon S3 bucket. If you use the AWS CLI to call Amazon Rekognition operations, you must pass it as a reference to an image in an Amazon S3 bucket. For the AWS CLI, passing image bytes is not supported. The image must be either a .png or .jpeg formatted file.
The DetectText operation returns text in an array of TextDetection elements, TextDetections. Each TextDetection element provides information about a single word or line of text that was detected in the image.
A word is one or more script characters that are not separated by spaces. DetectText can detect up to 100 words in an image.
A line is a string of equally spaced words. A line isn't necessarily a complete sentence. For example, a driver's license number is detected as a line. A line ends when there is no aligned text after it. Also, a line ends when there is a large gap between words, relative to the length of the words. This means, depending on the gap between words, Amazon Rekognition may detect multiple lines in text aligned in the same direction. Periods don't represent the end of a line. If a sentence spans multiple lines, the DetectText operation returns multiple lines.
To determine whether a TextDetection element is a line of text or a word, use the TextDetection object Type field.
To be detected, text must be within +/- 90 degrees orientation of the horizontal axis.
For more information, see DetectText in the Amazon Rekognition Developer Guide.
", "DistributeDatasetEntries": "Distributes the entries (images) in a training dataset across the training dataset and the test dataset for a project. DistributeDatasetEntries moves 20% of the training dataset images to the test dataset. An entry is a JSON Line that describes an image.
You supply the Amazon Resource Names (ARN) of a project's training dataset and test dataset. The training dataset must contain the images that you want to split. The test dataset must be empty. The datasets must belong to the same project. To create training and test datasets for a project, call CreateDataset.
Distributing a dataset takes a while to complete. To check the status call DescribeDataset. The operation is complete when the Status field for the training dataset and the test dataset is UPDATE_COMPLETE. If the dataset split fails, the value of Status is UPDATE_FAILED.
This operation requires permissions to perform the rekognition:DistributeDatasetEntries action.
Gets the name and additional information about a celebrity based on their Amazon Rekognition ID. The additional information is returned as an array of URLs. If there is no additional information about the celebrity, this list is empty.
For more information, see Recognizing Celebrities in an Image in the Amazon Rekognition Developer Guide.
This operation requires permissions to perform the rekognition:GetCelebrityInfo action.
Gets the celebrity recognition results for a Amazon Rekognition Video analysis started by StartCelebrityRecognition.
Celebrity recognition in a video is an asynchronous operation. Analysis is started by a call to StartCelebrityRecognition which returns a job identifier (JobId).
When the celebrity recognition operation finishes, Amazon Rekognition Video publishes a completion status to the Amazon Simple Notification Service topic registered in the initial call to StartCelebrityRecognition. To get the results of the celebrity recognition analysis, first check that the status value published to the Amazon SNS topic is SUCCEEDED. If so, call GetCelebrityDetection and pass the job identifier (JobId) from the initial call to StartCelebrityDetection.
For more information, see Working With Stored Videos in the Amazon Rekognition Developer Guide.
GetCelebrityRecognition returns detected celebrities and the time(s) they are detected in an array (Celebrities) of CelebrityRecognition objects. Each CelebrityRecognition contains information about the celebrity in a CelebrityDetail object and the time, Timestamp, the celebrity was detected. This CelebrityDetail object stores information about the detected celebrity's face attributes, a face bounding box, known gender, the celebrity's name, and a confidence estimate.
GetCelebrityRecognition only returns the default facial attributes (BoundingBox, Confidence, Landmarks, Pose, and Quality). The BoundingBox field only applies to the detected face instance. The other facial attributes listed in the Face object of the following response syntax are not returned. For more information, see FaceDetail in the Amazon Rekognition Developer Guide.
By default, the Celebrities array is sorted by time (milliseconds from the start of the video). You can also sort the array by celebrity by specifying the value ID in the SortBy input parameter.
The CelebrityDetail object includes the celebrity identifer and additional information urls. If you don't store the additional information urls, you can get them later by calling GetCelebrityInfo with the celebrity identifer.
No information is returned for faces not recognized as celebrities.
Use MaxResults parameter to limit the number of labels returned. If there are more results than specified in MaxResults, the value of NextToken in the operation response contains a pagination token for getting the next set of results. To get the next page of results, call GetCelebrityDetection and populate the NextToken request parameter with the token value returned from the previous call to GetCelebrityRecognition.
The known gender identity for the celebrity that matches the provided ID.
", + "base": "The known gender identity for the celebrity that matches the provided ID. The known gender identity can be Male, Female, Nonbinary, or Unlisted.
", "refs": { "Celebrity$KnownGender": null, "CelebrityDetail$KnownGender": "Retrieves the known gender for the celebrity.
", diff --git a/service/rekognition/api.go b/service/rekognition/api.go index 1a6f0e55e0a..660963bcdf1 100644 --- a/service/rekognition/api.go +++ b/service/rekognition/api.go @@ -77,7 +77,7 @@ func (c *Rekognition) CompareFacesRequest(input *CompareFacesInput) (req *reques // // 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, role, and yaw), quality +// 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. @@ -2784,8 +2784,8 @@ func (c *Rekognition) DetectTextRequest(input *DetectTextInput) (req *request.Re // TextDetections. Each TextDetection element provides information about a single // word or line of text that was detected in the image. // -// A word is one or more ISO basic latin script characters that are not separated -// by spaces. DetectText can detect up to 100 words in an image. +// A word is one or more script characters that are not separated by spaces. +// DetectText can detect up to 100 words in an image. // // A line is a string of equally spaced words. A line isn't necessarily a complete // sentence. For example, a driver's license number is detected as a line. A @@ -8241,6 +8241,7 @@ type Celebrity struct { Id *string `type:"string"` // The known gender identity for the celebrity that matches the provided ID. + // The known gender identity can be Male, Female, Nonbinary, or Unlisted. KnownGender *KnownGender `type:"structure"` // The confidence, in percentage, that Amazon Rekognition has that the recognized @@ -15538,6 +15539,7 @@ func (s *KinesisVideoStream) SetArn(v string) *KinesisVideoStream { } // The known gender identity for the celebrity that matches the provided ID. +// The known gender identity can be Male, Female, Nonbinary, or Unlisted. type KnownGender struct { _ struct{} `type:"structure"` @@ -21964,6 +21966,12 @@ const ( // KnownGenderTypeFemale is a KnownGenderType enum value KnownGenderTypeFemale = "Female" + + // KnownGenderTypeNonbinary is a KnownGenderType enum value + KnownGenderTypeNonbinary = "Nonbinary" + + // KnownGenderTypeUnlisted is a KnownGenderType enum value + KnownGenderTypeUnlisted = "Unlisted" ) // KnownGenderType_Values returns all elements of the KnownGenderType enum @@ -21971,6 +21979,8 @@ func KnownGenderType_Values() []string { return []string{ KnownGenderTypeMale, KnownGenderTypeFemale, + KnownGenderTypeNonbinary, + KnownGenderTypeUnlisted, } }