Title Information
Title
Statistical Inference and Probabilistic Modeling in Compositional Vision
Name: Personal
Name Part
Zhang, Wei
Role
Role Term: Text
creator
Origin Information
Copyright Date (keyDate="yes", encoding="w3cdtf")
2009
Physical Description
Extent
xiii, 138 p.
digitalOrigin
born digital
Note
Thesis (Ph.D.) -- Brown University (2009)
Name: Personal
Name Part
Geman, Stuart
Role
Role Term: Text
director
Name: Personal
Name Part
Bienenstock, Elli
Role
Role Term: Text
reader
Name: Personal
Name Part
Gidas, Basilis
Role
Role Term: Text
reader
Name: Corporate
Name Part
Brown University. Applied Mathematics
Role
Role Term: Text
sponsor
Genre (aat)
theses
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.
Subject (Local)
Topic
generative
Subject (Local)
Topic
probabilistic
Subject (Local)
Topic
hierarchical
Subject (Local)
Topic
pattern recognition
Subject (Local)
Topic
template-based
Subject (FAST) (authorityURI="http://id.worldcat.org/fast", valueURI="http://id.worldcat.org/fast/1055254")
Topic
Pattern perception
Subject (FAST) (authorityURI="http://id.worldcat.org/fast", valueURI="http://id.worldcat.org/fast/872687")
Topic
Computer vision
Record Information
Record Content Source (marcorg)
RPB
Record Creation Date (encoding="iso8601")
20091218
Language
Language Term: Code (ISO639-2B)
eng
Language Term: Text
English
Identifier: DOI
10.7301/Z04F1P1W
Access Condition: rights statement (href="http://rightsstatements.org/vocab/InC/1.0/")
In Copyright
Access Condition: restriction on access
Collection is open for research.
Type of Resource (primo)
dissertations