Changes Amazon Rekognition introduces StartMediaAnalysisJob, GetMediaAnalysisJob, and ListMediaAnalysisJobs operations to run a bulk analysis of images with a Detect Moderation model.
Changes Amazon Rekognition introduces support for Custom Moderation. This allows the enhancement of accuracy for detect moderation labels operations by creating custom adapters tuned on customer data.
Changes This release adds support for improved accuracy with user vector in Amazon Rekognition Face Search. Adds new APIs: AssociateFaces, CreateUser, DeleteUser, DisassociateFaces, ListUsers, SearchUsers, SearchUsersByImage. Also adds new face metadata that can be stored: user vector.
Changes This release adds a new EyeDirection attribute in Amazon Rekognition DetectFaces and IndexFaces APIs which predicts the yaw and pitch angles of a person's eye gaze direction for each face detected in the image.
Changes This release adds a new attribute FaceOccluded. Additionally, you can now select attributes individually (e.g. ["DEFAULT", "FACE_OCCLUDED", "AGE_RANGE"] instead of ["ALL"]), which can reduce response time.
Changes Added support for aggregating moderation labels by video segment timestamps for Stored Video Content Moderation APIs and added additional information about the job to all Stored Video Get API responses.
Changes Added new status result to Liveness session status.
Changes This release adds support for Face Liveness APIs in Amazon Rekognition. Updates UpdateStreamProcessor to return ResourceInUseException Exception. Minor updates to API documentation.
Changes Adds support for "aliases" and "categories", inclusion and exclusion filters for labels and label categories, and aggregating labels by video segment timestamps for Stored Video Label Detection APIs.
Changes Adding support for ImageProperties feature to detect dominant colors and image brightness, sharpness, and contrast, inclusion and exclusion filters for labels and label categories, new fields to the API response, "aliases" and "categories"
Changes This release adds APIs which support copying an Amazon Rekognition Custom Labels model and managing project policies across AWS account.
Changes This release introduces support for the automatic scaling of inference units used by Amazon Rekognition Custom Labels models.
Changes This release adds support to configure stream-processor resources for label detections on streaming-videos. UpateStreamProcessor API is also launched with this release, which could be used to update an existing stream-processor.
Changes This release introduces a new field IndexFacesModelVersion, which is the version of the face detect and storage model that was used when indexing the face vector.
Changes This release added new KnownGender types for Celebrity Recognition.
Changes This Amazon Rekognition Custom Labels release introduces the management of datasets with projects
Changes This release added new attributes to Rekognition Video GetCelebrityRecognition API operations.
Changes This release added new attributes to Rekognition RecognizeCelebities and GetCelebrityInfo API operations.
Changes This release adds support for four new types of segments (opening credits, content segments, slates, and studio logos), improved accuracy for credits and shot detection and new filters to control black frame detection.
Changes Amazon Rekognition Custom Labels adds support for customer managed encryption, using AWS Key Management Service, of image files copied into the service and files written back to the customer.
Changes "This release introduces AWS tagging support for Amazon Rekognition collections, stream processors, and Custom Label models."
Changes This SDK Release introduces new API (DetectProtectiveEquipment) for Amazon Rekognition. This release also adds ServiceQuotaExceeded exception to Amazon Rekognition IndexFaces API.
Changes This release provides location information for the manifest validation files.
Changes This update adds the ability to detect black frames, end credits, shots, and color bars in stored videos
Changes This release adds DeleteProject and DeleteProjectVersion APIs to Amazon Rekognition Custom Labels.
Changes This update adds the ability to detect text in videos and adds filters to image and video text detection.
Changes This SDK Release introduces APIs for Amazon Rekognition Custom Labels feature (CreateProjects, CreateProjectVersion,DescribeProjects, DescribeProjectVersions, StartProjectVersion, StopProjectVersion and DetectCustomLabels). Also new is AugmentedAI (Human In The Loop) Support for DetectModerationLabels in Amazon Rekognition.
Changes This release adds enhanced face filtering support to the IndexFaces API operation, and introduces face filtering for CompareFaces and SearchFacesByImage API operations.
Changes Adding new Emotion, Fear
Changes GetContentModeration now returns the version of the moderation detection model used to detect unsafe content.
Changes GetLabelDetection now returns bounding box information for common objects and a hierarchical taxonomy of detected labels. The version of the model used for video label detection is also returned. DetectModerationLabels now returns the version of the model used for detecting unsafe content.
Changes This release updates the DetectFaces and IndexFaces operation. When the Attributes input parameter is set to ALL, the face location landmarks includes 5 new landmarks: upperJawlineLeft, midJawlineLeft, chinBottom, midJawlineRight, upperJawlineRight.
Changes This release updates the DetectLabels operation. Bounding boxes are now returned for certain objects, a hierarchical taxonomy is now available for labels, and you can now get the version of the detection model used for detection.
Changes This release updates the Amazon Rekognition IndexFaces API operation. It introduces a QualityFilter parameter that allows you to automatically filter out detected faces that are deemed to be of low quality by Amazon Rekognition. The quality bar is based on a variety of common use cases. You can filter low-quality detected faces by setting QualityFilter to AUTO, which is also the default setting. To index all detected faces regardless of quality, you can specify NONE. This release also provides a MaxFaces parameter that is useful when you want to only index the most prominent and largest faces in an image and don't want to index other faces detected in the image, such as smaller faces belonging to people standing in the background.
Changes This release introduces a new API called DescribeCollection to Amazon Rekognition. You can use DescribeCollection to get information about an existing face collection. Given the ID for a face collection, DescribeCollection returns the following information: the number of faces indexed into the collection, the version of the face detection model used by the collection, the Amazon Resource Name (ARN) of the collection and the creation date/time of the collection.
Changes This release introduces Amazon Rekognition support for video analysis.
Changes This release includes updates to Amazon Rekognition for the following APIs. The new DetectText API allows you to recognize and extract textual content from images. Face Model Versioning has been added to operations that deal with face detection.
Changes Update the enum value of LandmarkType and GenderType to be consistent with service response
Changes API Update for AmazonRekognition: Adding RecognizeCelebrities API
Changes Updated the CompareFaces API response to include orientation information, unmatched faces, landmarks, pose, and quality of the compared faces.
Changes Given an image, the API detects explicit or suggestive adult content in the image and returns a list of corresponding labels with confidence scores, as well as a taxonomy (parent-child relation) for each label.
Changes DetectFaces and IndexFaces operations now return an estimate of the age of the face as an age range.
Changes Amazon Rekognition is a service that makes it easy to add image analysis to your applications. With Rekognition, you can detect objects, scenes, and faces in images. You can also search and compare faces. Rekognition’s API enables you to quickly add sophisticated deep learning-based visual search and image classification to your applications.