Dynamic estimation of family relations from photos

  • Authors:
  • Tong Zhang;Hui Chao;Dan Tretter

  • Affiliations:
  • Hewlett-Packard Labs, Palo Alto, CA;Hewlett-Packard Labs, Palo Alto, CA;Hewlett-Packard Labs, Palo Alto, CA

  • Venue:
  • MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part II
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we present an approach to estimate dynamic relations among major characters in family photo collections. This is a fully automated procedure which first identifies major characters in photo collections through face clustering. Then, based on demographic estimation, facial similarity, coappearance information and people's positions in photos, social relations of people such as husband/wife, parents/kids, siblings, relatives and friends can be derived. A workflow is proposed to integrate the information from different aspects in order to give the optimal result. Especially, based on timestamps of photos, dynamic relation trees are displayed to show the evolution of people's relations over time.