Image annotation within the context of personal photo collections using hierarchical event and scene models

  • Authors:

  • Liangliang Cao;Jiebo Luo;Henry Kautz;Thomas S. Huang

  • Affiliations:

  • Beckman Institute and Coordinated Science Lab, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign. Urbana, IL;Kodak Research Laboratories Eastman, Kodak Company, Rochester, NY;Kodak Research Laboratories Eastman, Kodak Company, Rochester, NY;Beckman Institute and Coordinated Science Lab, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign. Urbana, IL

  • Venue:
  • IEEE Transactions on Multimedia - Special issue on integration of context and content
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Most image annotation systems consider a single photo at a time and label photos individually. In this work, we focus on collections of personal photos and exploit the contextual information naturally implied by the associated GPS and time metadata. First, we employ a constrained clustering method to partition a photo collection into event-based subcollections, considering that the GPS records may be partly missing (a practical issue). We then use conditional random field (CRF) models to exploit the correlation between photos based on 1) time-location constraints and 2) the relationship between collection-level annotation (i.e., events) and image-level annotation (i.e., scenes). With the introduction of such a multilevel annotation hierarchy, our system addresses the problem of annotating consumer photo collections that requires a more hierarchical description of the customers' activities than do the simpler image annotation tasks. The efficacy of the proposed system is validated by extensive evaluation using a sizable geotagged personal photo collection database, which consists of over 100 photo collections and is manually labeled for 12 events and 12 scenes to create ground truth.