Robust Appearance-Based Object Recognition Using a Fully Connected Markov Random Field

  • Authors:

  • B. Caputo;S. Bouattour;H. Niemann

  • Affiliations:

  • -;-;-

  • Venue:
  • ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a new kernel method for appearance-based object recognition, highly robust to noise and occlusion. It consists of a fully connected Markov Random Field that integrates results of Spin Glass theory with Gibbs probability distributions via nonlinear kernel mapping. We call this model Spin Glass-Markov Random Field. We present theoretical analysis and several experiments that show its effectiveness and robustness to noise and occlusion. We obtain in both cases excellent results. Particularly, we achieve a recognition rate above 93% with just 40% of visible portion of the object.