Conditional Random Fields for High-Level Part Correlation Analysis in Images

  • Giuseppe Passino
  • Ebroul Izquierdo
Conference paper

DOI: 10.1007/978-3-540-77051-0_30

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4816)
Cite this paper as:
Passino G., Izquierdo E. (2007) Conditional Random Fields for High-Level Part Correlation Analysis in Images. In: Falcidieno B., Spagnuolo M., Avrithis Y., Kompatsiaris I., Buitelaar P. (eds) Semantic Multimedia. SAMT 2007. Lecture Notes in Computer Science, vol 4816. Springer, Berlin, Heidelberg

Abstract

A novel approach to model the semantic knowledge associated to objects detected in images is presented. The model is aimed at the classification of such objects according to contextual information combined to the extracted features. The system is based on Conditional Random Fields, a probabilistic graphical model used to model the conditional a-posteriori probability of the object classes, thus avoiding problems related to source modelling and features independence constraints. The novelty of the approach is in the addressing of the high-level, semantically rich objects interrelationships among image parts. This paper presents the application of the model to this new problem class and a first implementation of the system.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Giuseppe Passino
    • 1
  • Ebroul Izquierdo
    • 1
  1. 1.Queen Mary, University of London, Mile End Rd, London, E1 4NSUK

Personalised recommendations