Skip to content

Face Recognition

Jump to bottom
Giuliano Catrambone edited this page Jan 25, 2019 · 1 revision

The FaceRecognition Task receives a video as input and generates, depending on the Output parameter

  • another video (an avi video using h264 as codec without audio) that it is a copy of the input video where all the faces are highlighed with a circle or a rectangle

  • OR an image for each face met inside the input video. All these ingested images could be used to train the deep learned model to identify (so not just recognize) the face inside a video. In this scenario, it is possible to tag all the images ingested and use them in the FaceIdentification Task to identify the faces.

  • Here follows some examples (body of the POST)

  1. Home

    Tutorial
    1. User registration
    2. Add content - Pull
    3. Add content, on success send an email
    4. Two Tasks (Add content) to be executed in parallel
    5. Add a set of video encoding profiles
    6. Add two contents, send an email, concat, cut and encode
    7. Add a single image profile (Logo)
    8. Add a video, an image, encode the image, overlay the encoded image on the video

  2. REST API version 1 (latest)

    Registration
    1. User registration
    2. Login
    3. Create Workspace
    4. Share Workspace
    5. Update Workspace
    6. Update User
    Workflow Ingestion
    1. Workflow
    2. Status/metadata of an ingestion
    3. Group Of Tasks
    Workflow As Library
    1. Workflow as Library
    2. Create-Update a Workflow as Library
    3. Delete a Workflow as Library
    4. Use of a Workflow as Library
    Add-Remove Content
    1. Add a new Content
      1. Pull
      2. Push
    2. Remove a Content
    3. Information about the contents saved into MMS
    4. Retention of a Content
    Delivery
    1. Download HTTP of a Content
    2. FTP of a Content
    3. Local copy of a Content
    4. Live Proxy
    5. VOD Proxy
    6. Countdown
    7. Check Streaming
    Social Network Delivery
    1. POST a Content on Facebook
    2. POST a Content on YouTube
    3. YouTube Live Broadcast
    4. Facebook Live Broadcast
    Encoding (video-audio-image)
    1. Add encoding profiles
    2. Remove encoding profiles
    3. Encode
    4. Information about the encoding profiles saved into MMS
    5. Predefined MMS Encoding Profiles
    Media activities
    1. Concatenate videos having same codecs
    2. Cut
    3. Video speed
    4. Extract tracks
    5. Add silent audio
    Overlay
    1. Overlay an Image on a Video
    2. Overlay a Text on a Video
    3. Picture In Picture
    4. Intro Outro Overlay
    5. Live Grid
    Frame Processing
    1. Frame of a video
    2. Periodical Frames of a video
    3. I-Frames of a video
    4. Motion JPEG video generated by Periodical Frames of a video
    5. Motion JPEG video generated by I-Frames of a video
    6. Slideshow video by images
    Recorder
    1. Live Recorder
    2. Live Cut
    Communication
    1. HTTP Callback
    2. Notification through email
    Utilities
    1. Change File Format
    2. Media Cross Reference
    Computer Vision
    1. Face Recognition
    2. Face Identification
    Configuration
    1. YouTube
    2. Facebook
    3. Live URL
    4. FTP
    5. E-Mail
Clone this wiki locally