A new Bayesian framework for object recognition
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 517-523 Vol. 2
- https://doi.org/10.1109/cvpr.1999.784730
Abstract
We introduce an approach to feature-based object recognition, using maximum a posteriori (MAP) estimation under a Markov random field (MRF) model. This approach provides an efficienct solution for a wide class of priors that explicitly model dependencies between individual features of an object. These priors capture phenomena such as the fact that unmatched features due to partial occlusion are generally spatially correlated rather than independent. The main focus of this paper is a special case of the framework that yields a particularly efficient approximation method. We call this special case spatially coherent matching (SCM), as it reflects the spatial correlation among neighboring features of an object. The SCM method operates directly on the image feature map, rather than relying on the graph-based methods used in the general framework. We present some Monte Carlo experiments showing that SCM yields substantial improvements over Hausdorff matching for cluttered scenes and partially occluded objects.Keywords
This publication has 6 references indexed in Scilit:
- Higher-order statistics in object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Markov random fields with efficient approximationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A probabilistic formulation for Hausdorff matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Practical reliable Bayesian recognition of 2D and 3D objects using implicit polynomials and algebraic invariantsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Markov Random Field Modeling in Computer VisionPublished by Springer Nature ,1995
- Comparing images using the Hausdorff distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993