Detect Face and Emotion with Azure Media Analytics. Overview. The Azure Media Face Detector media processor MP enables you to count, track movements, and even gauge audience participation and reaction via facial expressions. This service contains two features Face detection Face detection finds and tracks human faces within a video. Multiple faces can be detected and subsequently be tracked as they move around, with the time and location metadata returned in a JSON file. During tracking, it will attempt to give a consistent ID to the same face while the person is moving around on screen, even if they are obstructed or briefly leave the frame. Note. This service does not perform facial recognition. An individual who leaves the frame or becomes obstructed for too long will be given a new ID when they return. Emotion detection Emotion Detection is an optional component of the Face Detection Media Processor that returns analysis on multiple emotional attributes from the faces detected, including happiness, sadness, fear, anger, and more. The Azure Media Face Detector MP is currently in Preview. This topic gives details about Azure Media Face Detector and shows how to use it with Media Services SDK for. NET. Face Detector input files. Video files. Currently, the following formats are supported MP4, MOV, and WMV. Fingerprint, face, iris, voice and multibiometric product brochures, 30day SDK and component trials, biometric algorithm demo applications and databases. Face_Swap_04-1.png' alt='Face Sdk Microsoft' title='Face Sdk Microsoft' />Clarity Consulting Inc. Facebook Developer Toolkit for the Microsoft Visual Studio Express Team. We have. Ive been bгosing online more than 2 hours today, yet I never found any interesting article like yours. It is prett worth enogh for me. The essential tech news of the moment. Technologys news site of record. Not for dummies. Get information and code samples to help you quickly get started using the Face API with C in Cognitive Services. Face Detector output files. The face detection and tracking API provides high precision face location detection and tracking that can detect up to 6. Frontal faces provide the best results, while side faces and small faces less than or equal to 2. The detected and tracked faces are returned with coordinates left, top, width, and height indicating the location of faces in the image in pixels, as well as a face ID number indicating the tracking of that individual. Face ID numbers are prone to reset under circumstances when the frontal face is lost or overlapped in the frame, resulting in some individuals getting assigned multiple IDs. Elements of the output JSON file. The job produces a JSON output file that contains metadata about detected and tracked faces. The metadata includes coordinates indicating the location of faces, as well as a face ID number indicating the tracking of that individual. Face ID numbers are prone to reset under circumstances when the frontal face is lost or overlapped in the frame, resulting in some individuals getting assigned multiple IDs. The output JSON includes the following attributes Element. Descriptionversion. This refers to the version of the Video API. Applies to Azure Media Redactor only defines the frame index of the current event. Ticks per second of the video. This is the time offset for timestamps. In version 1. 0 of Video APIs, this will always be 0. In future scenarios we support, this value may change. Frames per second of the video. The metadata is chunked up into different segments called fragments. Each fragment contains a start, duration, interval number, and events. The start time of the first event in ticks. The length of the fragment, in ticks. The interval of each event entry within the fragment, in ticks. Each event contains the faces detected and tracked within that time duration. It is an array of array of events. The outer array represents one interval of time. The inner array consists of 0 or more events that happened at that point in time. An empty bracket means no faces were detected. The ID of the face that is being tracked. This number may inadvertently change if a face becomes undetected. A given individual should have the same ID throughout the overall video, but this cannot be guaranteed due to limitations in the detection algorithm occlusion, etc. The upper left X and Y coordinates of the face bounding box in a normalized scale of 0. X and Y coordinates are relative to landscape always, so if you have a portrait video or upside down, in the case of i. OS, youll have to transpose the coordinates accordingly. The width and height of the face bounding box in a normalized scale of 0. Detected. This is found at the end of the JSON results and summarizes the number of faces that the algorithm detected during the video. Because the IDs can be reset inadvertently if a face becomes undetected e. Face Detector uses techniques of fragmentation where the metadata can be broken up in time based chunks and you can download only what you need, and segmentation where the events are broken up in case they get too large. Some simple calculations can help you transform the data. For example, if an event started at 6. StartTimescale 2. Seconds x Framerate 6. Face detection input and output example. Input video. Input Video. Task configuration presetWhen creating a task with Azure Media Face Detector, you must specify a configuration preset. The following configuration preset is just for face detection. Tracking. Mode Fast. Attribute descriptions. Attribute name. Description. Mode. Fast fast processing speed, but less accurate default. JSON output. The following example of JSON output was truncated. Emotion detection input and output example. Input video. Input Video. Task configuration presetWhen creating a task with Azure Media Face Detector, you must specify a configuration preset. The following configuration preset specifies to create JSON based on the emotion detection. Emotion. Window. Ms 9. Emotion. aggregate. Emotion. Interval. Ms 3. 42. Attribute descriptions. Attribute name. Description. Mode. Faces Only face detection. Per. Face. Emotion Return emotion independently for each face detection. Aggregate. Emotion Return average emotion values for all faces in frame. Aggregate. Emotion. Window. Ms. Use if Aggregate. Emotion mode selected. Specifies the length of video used to produce each aggregate result, in milliseconds. Aggregate. Emotion. Interval. Ms. Use if Aggregate. Emotion mode selected. Specifies with what frequency to produce aggregate results. Aggregate defaults. Below are recommended values for the aggregate window and interval settings. Aggregate. Emotion. Window. Ms should be longer than Aggregate. Emotion. Interval. Ms. DefaultssMaxsMinsAggregate. Emotion. Window. Ms. Aggregate. Emotion. Interval. Ms. 0. 5. JSON output. JSON output for aggregate emotion truncated. Face. Distribution. Mean. Scores. Face. Distribution. Mean. Scores. Face. Distribution. Mean. Scores. Face. Distribution. Mean. Scores. Face. Distribution. Mean. Scores. Face. Distribution. Limitations. The supported input video formats include MP4, MOV, and WMV. The detectable face size range is 2. The faces out of this range will not be detected. For each video, the maximum number of faces returned is 6. Some faces may not be detected due to technical challenges e. Frontal and near frontal faces have the best results. NET sample code. The following program shows how to Create an asset and upload a media file into the asset. Create a job with a face detection task based on a configuration file that contains the following json preset. Download the output JSON files. Create and configure a Visual Studio project. Set up your development environment and populate the app. Media Services development with. NET. Exampleusing System. System. Configuration. System. IO. using System. Linq. using Microsoft. Windows. Azure. Media. Services. Client. System. Threading. System. Threading. Tasks. namespace Face. Plotter Hp 110 Plus Driver. Detection. class Program. AADTenant. Domain. Configuration. Manager. App. SettingsAADTenant. Domain. private static readonly string RESTAPIEndpoint. Configuration. Manager. App. SettingsMedia. Service. RESTAPIEndpoint. Field for service context. Cloud. Media. Context context null. Mainstring args. Credentials new Azure. Ad. Token. CredentialsAADTenant. Domain, Azure. Environments. Azure. Cloud. Environment. Provider new Azure. Ad. Token. Providertoken. Credentials. context new Cloud. Media. Contextnew UriRESTAPIEndpoint, token. Provider. Run the Face. Detection job. var asset Run.