Scene Grammars, Factor Graphs, and Belief Propagation
This work addresses scene understanding in image analysis, providing a general method that is incremental in combining existing techniques like grammars and belief propagation.
The paper tackles the problem of probabilistic modeling and inference for complex scenes from ambiguous observations, resulting in a framework that enables robust inference algorithms for applications like contour map reconstruction and face detection.
We describe a general framework for probabilistic modeling of complex scenes and inference from ambiguous observations. The approach is motivated by applications in image analysis and is based on the use of priors defined by stochastic grammars. We define a class of grammars that capture relationships between the objects in a scene and provide important contextual cues for statistical inference. The distribution over scenes defined by a probabilistic scene grammar can be represented by a graphical model and this construction can be used for efficient inference with loopy belief propagation. We show experimental results with two different applications. One application involves the reconstruction of binary contour maps. Another application involves detecting and localizing faces in images. In both applications the same framework leads to robust inference algorithms that can effectively combine local information to reason about a scene.