Network Matching: A Versatile Computer Vision Tool
Selander, John Michael
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/66244
Description
Title
Network Matching: A Versatile Computer Vision Tool
Author(s)
Selander, John Michael
Issue Date
1980
Department of Study
Electrical Engineering
Discipline
Electrical Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Engineering, Electronics and Electrical
Computer Science
Language
eng
Abstract
This work consists of a development and an investigation of the computational process of network matching as it is applied to the computer vision domain. In particular a cost based definition of network matching is developed which is oriented toward the kinds of computational problems that occur in computer vision. Emphasis is placed on the concurrent use of distance and topologic information. Several optimal and near optimal algorithms are developed, and their properties are examined. One of these algorithms was found to be a versatile tool for solving several hereto unrelated problems in the computer vision domain.
The latter part of this work describes the application of this algorithm to four problems. The first problem deals with the determination of depth information from a camera motion sequence. The second problem deals with the construction of three dimensional object models from many images. This problem is made more difficult by denying the computer information concerning the angles and distance between the camera and the object. The third problem deals with the recognition of occluding three dimensional objects in a single view. The final problem deals with network matching as applied to scene labeling in a noisy and ambiguous environment.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
