AMP (Audiovisual Metadata Platform)
Page tree

This site has moved to: https://uisapp2.iu.edu/confluence-prd/display/AMP/AMP%3A+Audiovisual+Metadata+Platform

Skip to end of metadata
Go to start of metadata
  • About 
    • Azure Video OCR utilizes the results produced by Azure Video Indexer, including the main indexer file and the video OCR artifacts, and generates the standard AMP Video OCR JSON.
    • 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/amp_vocr/azure_video_ocr.xml : This is the configuration file that details the tools usage, its inputs, outputs, version, and other things.
    • galaxy/tools/amp_vocr/azure_video_ocr.py : This is a python wrapper to generate AMP Video OCR JSON based on Azure Video indexer JSON and Video OCR Artifacts JSON output from Azure Video Indexer.
    • galaxy/tools/amp_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, it needs be used as the next MGM taking outputs from Azure Video Indexer with the include_ocr flag set to true. 
  • Parameters
    • input_video: The same input video file used by Azure Video Indexer
    • azure_video_index: Azure Video Index JSON output from Azure Video Indexer
    • azure_artifact_ocr: Azure Artifact OCR JSON output from Azure Video Indexer
  • Outputs
    • amp_vocr: The standardized AMP Video OCR JSON
  • No labels