This mode uses the annotations to apply blurring on the input video. This includes a list of IDs to blur, the original video, and the annotations JSON. The second pass of the workflow takes a larger number of inputs that must be combined into a single asset. See sample below.įoo_thumb%06d.jpg Ī cropped jpg of each detected face, where the number indicates the labelId of the face This can be edited by the user to modify the blurring bounding boxes. Face id's are not guaranteed to be identical on subsequent runs of the analysis pass. Mode: FaceRedactorMode.Analyze, resolution: AnalysisResolution.SourceResolutionĪnnotation data of face locations in JSON format. The Analyze pass of the two-pass workflow takes a video input and produces a JSON file with a list of the face locations, Face ID's and jpg images of each detected face.īe advised that the face id's are not guaranteed to be identical on subsequent runs of the analysis pass. Video with blurring effect applied to faces Mode: FaceRedactorMode.Combined, blurType: BlurType.Med, resolution: AnalysisResolution.SourceResolution Use the resolution property set to SourceResolution to achieve the best results for redaction.
REDACTED FACE MP4
mp4 file that contains blurred faces using the selected blur effect. The output in the asset folder for the job will be a single.
REDACTED FACE MANUAL
This produces a redacted MP4 video file in a single pass without any manual editing of the JSON file required.
REDACTED FACE HOW TO
In this article, the sample code will show how to use the simplified single pass Combined mode on a sample source file. You can also easily just combine the two modes in a single pass that runs both tasks in one job this mode is called Combined. This workflow is split into Analyze and Redact modes. To make arbitrary per frame adjustments the preset uses a metadata file in JSON format as input to the second pass. In addition to a fully automatic Combined mode, the two-pass workflow allows you the ability to choose the faces you wish to blur (or not blur) via a list of face IDs. For this reason, the preset can be used a two-pass mode to improve the quality and accuracy of the blurring through an editing stage prior to submitting the file for the final blur pass. The automated redaction process is complex and does not always blur every face 100% guaranteed. By using Azure Media Services, you agree to be bound by the Cognitive Services Terms, the OST, DPA, and the Privacy Statement Face redaction modesįacial redaction works by detecting faces in every frame of video and tracking the face object both forwards and backwards in time, so that the same individual can be blurred from other angles as well.
More privacy information, including on data retention, deletion/destruction, is available in the OST and here. For Microsoft’s privacy obligations and handling of your data, review Microsoft’s Privacy Statement, the Online Services Terms (OST) and Data Processing Addendum (“DPA”).
To learn about compliance, privacy and security in Azure Media Services, the Azure Cognitive Services Terms. Before uploading any videos, including any biometric data, to the Azure Media Services service for processing and storage, you must have all the proper rights, including all appropriate consents, from the individuals in the video. You must not use Azure Media Services or any other Azure service in a manner that violates the rights of others. Compliance, privacy, and securityĪs an important reminder, you must comply with all applicable laws in your use of analytics in Azure Media Services. This article gives details about Face Detector Preset and shows how to use it with Azure Media Services SDK for. A few minutes of footage that contains multiple faces can take hours to redact manually, but with this preset the face redaction process will require just a few simple steps.
You may want to use the face redaction service in public safety and news media scenarios. Face redaction enables you to modify your video in order to blur faces of selected individuals. AMS website | Media Services v2 documentation | Code Samples | Troubleshooting guideĪzure Media Services v3 API includes a Face Detector preset that offers scalable face detection and redaction (blurring) in the cloud.
0 kommentar(er)
