Skip to main content
Skip table of contents

Face and Label Extractor Powered by DeepVA Motivation

Analyze your video content to automatically extract faces together with name tags

Automatically run an analysis of your video content which returns image assets of extracted faces together with name labels

Using a video assets residing within your VidiCore environment, the Face and Label Extractor is able to analyze and extract faces detected in the content and group them together with name tags identified from lower third. The extracted keyframes containing the identified faces will then be imported as new image assets in VidiCore. With extracted faces together with metadata describing the person in the picture you are then able to train face recognition models, and analyze your video content library to detect which time spans in the content the person is appearing.

For all customers that are looking beyond the pre-trained face detection models offered and instead wants to build their own model people such as regional politicans or local celebrities. This is a valuable tool for generating source material to be used together with face recognition services that can be trained, such as the Face Training and Analysis Powered by DeepVA

Seamless integration into any VidiCore system, anywhere.


  • VidiCore version 21.3 or later

  • Callback-bucket or directory on cloud storage with  access configured. Instructions provided in the Vidispine Customer Knowledgebase.

  • Proxy copy of video residing on supported cloud storage (AWS S3)

Service Activation

Activate the service by posting the ResourceDocument to your VidiCore Server on /API/resource/vidinet.

Connection Status

Connection status can be seen in VidiCore Server from /API/resource/vidinet and in the Vidinet dashboard -> Service details. You can connect multiple VidiCore Server instances to one VidiNet Service, using the same or different access key pairs. (Using unique key pairs for each VidiCore Server is recommended).

Service Usage

For detailed instructions on how to run face detection jobs from the VidiCore Server API see the Face Training Theme and the VidiCore API documentation.

Job Status and Billing

VidiCore Server will provide Vidinet job status and progress in /API/job and in the Vidinet dashboard -> Service details. 

Successful jobs will be charged to your account and listed in the Vidinet dashboard -> Billing. Failed jobs will not be listed nor billed.

Supported formats

For list of supported formats, see DeepVA documentation.


Visit and we will assist you.

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.