Building Personal Digital Photograph Libraries: An Approach with Ontology-Based MPEG-7 Dozen Dimensional Digital Content Architecture

  • Authors:
  • Pei-Jeng Kuo;Terumasa Aoki;Hiroshi Yasuda

  • Affiliations:
  • University of Tokyo;University of Tokyo;University of Tokyo

  • Venue:
  • CGI '04 Proceedings of the Computer Graphics International
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

The current trend of image retrieval is to incorporatethe image visual features used in Content Based ImageRetrieval (CBIR) and semantics annotations used inMetadata Based Image Retrieval to enhance retrievalperformance. Because of the pervasive of consumerimaging devices, building personal digital photographlibraries became an increasingly interested domain.Personal digital photograph collections have specificcharacteristics compare to general purpose imagedatabases. Hence, annotation architecture speciallydesigned for that plays an important role in building aninteroperatable data repository for future indexing,browsing and retrieving purposes. We propose aMPEG-7 based multimedia content descriptionarchitecture, Dozen Dimensional Digital Content(DDDC), which annotates multimedia data with twelvemain attributes regarding its semantic representation.In addition, we also proposed a machine-understandable"Spatial and Temporal BasedOntology" representation for the above DDDCsemantics description to enable semi-automaticannotation process.