Home photo retrieval: time matters

  • Authors:
  • Philippe Mulhem;Joo-Hwee Lim

  • Affiliations:
  • IPAL-CNRS, Heng Mui Keng Terrace, Singapore;Institute for Infocomm Research, Heng Mui Keng Terrace, Singapore

  • Venue:
  • CIVR'03 Proceedings of the 2nd international conference on Image and video retrieval
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Temporal information has been regarded as a key vehicle for sorting and grouping home photos into albums associated with events. While time-based browsing might be adequate for relatively small photo collection, query and retrieval would be very useful to find relevant photos of an event in large collection. In this paper, we propose the use of temporal events for organizing and representing home photos using structured document formalism and hence a new way to retrieve photos of an event using both image content and temporal context. We describe a hierarchical model of temporal events and the algorithm to construct it from a collection of home photos. In particular, we compute metadata of a node from the metadata of its children recursively to facilitate content-based and context-based matching between a query and an event. With semantic content representation extracted using Visual Keywords and Extended Conceptual Graphs, we demonstrate the effectiveness of photo retrieval on 2400 time-stamped heterogeneous home photos with very promising results.