Analyze Media

Images, audio, and video are examples of unstructured information that represent a vast quantity of data. CFS extracts metadata from these files but cannot process their content, so by default documents that represent these files are indexed without any content.

To enrich documents that represent rich media files, you can send the files to an IDOL Media Server for analysis. Media Server can:

  • extract text from scanned documents, and subtitles and scrolling text from video.
  • identify people that appear by matching faces to a database of known faces.
  • identify known logos and objects.
  • detect and read barcodes, including QR codes.
  • determine the language of speech in a video file, convert the speech into text, and identify any known speakers.

For more information about the types of analysis that you can run, refer to the Media Server Administration Guide.

NOTE: Some types of analysis require you to train Media Server before you start processing.