Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
  • About 
    • Video indexer builds upon media AI technologies to make it easier to extract insights from videos. Forms of content discovery such as searching for spoken words, faces, characters, and emotions.
    • Azure Video Indexer produces a number of data points relating to a video, but this tool is focused on video OCR .
    • It has been added as a tool on AMP's Galaxy and performs video OCR on the input videos.
    • The output produced by this tool is a JSON consisting of the text and the corresponding bounding box information on each frame in the input.
  • Source Code
    • galaxy/tools/video_tools/azure_video_indexer.xml : This is the configuration file that details the tools usage, its inputs, outputs, version, and other things.
    • galaxy/tools/video_tools/azure_video_indexer_wrapper.py : This is a python wrapper to submit the video to Azure Video Indexer, check the status, retrieve the output, and convert it to AMP's schema. 
    • galaxy/tools/amp_json_schema/video_ocr.py :  Classes used to construct AMP Video OCR json output.
  • Running 
    • The tool can be invoked from Galaxy UI as other tools. User needs to supply Azure account information and as well as input data in the form of a video file.
  • Parameters
    • Input File: the video file to be passed through the OCR.
    • Account ID: Azure Video Indexer account ID
    • API Key: Azure Video Indexer API key
    • Location: The region video is stored in Azure (Trial, US EAST 2, US WEST 2)
  • Output
    • output_from_azure: The output JSON directly from Azure.
    • output_amp_ocr_schema: The standardized Video OCR Schema JSON