Toward a Unified Probabilistic Framework for Object Recognition and Segmentation

摘要

This paper presents a novel and effective Bayesian belief network that integrates object segmentation and recognition. The network consists of three latent variables that represent the local features, the recognition hypothesis, and the segmentation hypothesis. The probabilities are the result of approximate inference based on stochastic simulations with Gibbs sampling, and can be calculated for large databases of objects. Experimental results demonstrate that this framework outperforms a feed-forward recognition system that ignores the segmentation problem.