Scene Grammars, Factor Graphs, and Belief Propagation
- 30 May 2020
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in Journal of the ACM
- Vol. 67 (4), 1-41
- https://doi.org/10.1145/3396886
Abstract
We describe a general framework for probabilistic modeling of complex scenes and for 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 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.Keywords
Funding Information
- National Science Foundation (1447413)
This publication has 25 references indexed in Scilit:
- Context, Computation, and Optimal ROC Performance in Hierarchical ModelsInternational Journal of Computer Vision, 2010
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- 2D Object Detection and RecognitionPublished by MIT Press ,2002
- Biological Sequence AnalysisPublished by Cambridge University Press (CUP) ,1998
- A probabilistic approach to object recognition using local photometry and global geometryPublished by Springer Science and Business Media LLC ,1998
- On the Statistical Analysis of Dirty PicturesJournal of the Royal Statistical Society: Series B (Methodological), 1986
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society: Series B (Methodological), 1977
- Three models for the description of languageIEEE Transactions on Information Theory, 1956