Technologies and the development of the Automated Metadata Indexing and Analysis (AMIA) system

  • Authors:

  • Pei-Ying Chiang;May-chen Kuo;Jessy Lee;C. -C. Jay Kuo;Todd Richmond;Milton Rosenberg;Jeff Lund;Kip Haynes;Lindsay Armstrong

  • Affiliations:

  • Ming Hsieh Department of Electrical Engineering and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2546, USA;Ming Hsieh Department of Electrical Engineering and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2546, USA;Ming Hsieh Department of Electrical Engineering and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2546, USA;Ming Hsieh Department of Electrical Engineering and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA 90089-2546, USA;USC Institute for Creative Technologies, Marina Del Rey, CA 90292, USA;USC Institute for Creative Technologies, Marina Del Rey, CA 90292, USA;USC Institute for Creative Technologies, Marina Del Rey, CA 90292, USA;USC Institute for Creative Technologies, Marina Del Rey, CA 90292, USA;USC Institute for Creative Technologies, Marina Del Rey, CA 90292, USA

  • Venue:
  • Journal of Visual Communication and Image Representation
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Automated Metadata Indexing and Analysis (AMIA) project aims to provide an effective digital asset management (DAM) tool for large digital asset databases. We began with text-based indexing since it is still the most reliable approach as compared with other content-based media features. AMIA not only searches for the text of the file name, but also utilizes embedded information such as the metadata in Maya files. The AMIA system builds a linked map between all dependency files. We present an approach of preserving previously established metadata created by the old DAM tools, such as AlienBrain, and integrating them into the new system. Findings indicate that AMIA has significantly improved search performance comparing to previous DAM tools. Finally, the ongoing and future work in the AMIA project is described.