Brown University

Statistical Inference and Probabilistic Modeling in Compositional Vision

Description

Abstract:
This thesis is a mathematical and computational study of compositional vision. Three topics are covered: (1) ROC performance in a compositional world; (2) the construction of a probabilistic model for compositional structure; and (3) the construction of probabilistic model of image gray levels for a given vocabulary of elementary parts. Chapter 1 introduces compositional vision and a probabilistic framework for modeling hierarchy, reusability, and conditional data models. Chapter 2 focuses on theoretical questions about the ROC performance of various approaches to recognition in hypothetical compositional worlds. The results suggest that even sub-optimal decisions within a hierarchical framework will substantially outperform a decision process that does not explicitly allow for part-based decomposition. Chapter 3 focuses on the first component of the Bayesian approach to compositional vision: a prior probability model on hierarchical image interpretations. Non-Markovian (context-sensitive) distributions are investigated, and two theoretical questions are addressed. The existence of a class of non-Markovian distributions is established, and the convergence of an iterative perturbation scheme for achieving these distributions is proven. Chapter 4 focuses on the second component of the Bayesian approach to compositional vision: a probability model on pixel intensities conditioned on a given hierarchical structure. In particular, a generative approach to modeling object parts is developed through a probabilistic extension of the idea of fragment-based templates. Chapter 5 makes some conclusions and suggests future directions.
Notes:
Thesis (Ph.D.) -- Brown University (2009)

Access Conditions

Rights
In Copyright
Restrictions on Use
Collection is open for research.

Citation

Zhang, Wei, "Statistical Inference and Probabilistic Modeling in Compositional Vision" (2009). Applied Mathematics Theses and Dissertations. Brown Digital Repository. Brown University Library. https://doi.org/10.7301/Z04F1P1W

Relations

Collection: