# Knowledge base: Warsaw University of Technology

Back

## Stereo pair matching using fuzzy logic

#### Abstract

Methods making possible an acquisition and presentation of spatial images have become of very high importance in the field of image processing. There are many scientific workers doing an extensive research for finding new solutions, as well as improving known methods. One method enabling acquisition of three--dimensional images is so called stereoscopic vision. This doctoral thesis pertains to one of stereoscopic vision's major problems, which is matching the pair of stereoscopic images. The matching problem is one of the most important questions because its effective solution enables the use of stereoscopic vision techniques in practice. Despite the fact that it is a well known problem, and there are many different propositions on how it could be solved, the issue still remains unsolved to a satisfactory level for use in the real applications. In this thesis, novel methods using some elements from the fuzzy set theory for the matching the pair of stereoscopic images have been developed. Using the fuzzy set theory is a part of a research trend which consists in finding new ways of solution. The presented methods and experimental results should conclude that in some cases the application of fuzzy set theory allows to accomplish better results than obtained with the use of methods and algorithms known from the specialist literature.
Record ID
Diploma type
Doctor of Philosophy
Author
Title in Polish
Dopasowanie obrazów pary stereoskopowej z wykorzystaniem logiki rozmytej
Title in English
Stereo pair matching using fuzzy logic
Language
(pl) Polish
Certifying Unit
Faculty of Electronics and Information Technology (FEIT)
Discipline
information science / (technology domain) / (technological sciences)
Status
Finished
Start date
31-10-2006
Defense Date
13-05-2014
Title date
27-05-2014
Supervisor
Bohdan Butkiewicz Bohdan Butkiewicz,, The Institute of Computer Science (FEIT/ICS)Faculty of Electronics and Information Technology (FEIT)
Internal reviewers
External reviewers
Robert Nowicki Robert Nowicki,, Undefined Affiliation
Pages
258
Keywords in English
stereo pair, disparity, disparity map, stereo pair matching, fuzzy sets, intuitionistic fuzzy sets
Abstract in English
Methods making possible an acquisition and presentation of spatial images have become of very high importance in the field of image processing. There are many scientific workers doing an extensive research for finding new solutions, as well as improving known methods. One method enabling acquisition of three--dimensional images is so called stereoscopic vision. This doctoral thesis pertains to one of stereoscopic vision's major problems, which is matching the pair of stereoscopic images. The matching problem is one of the most important questions because its effective solution enables the use of stereoscopic vision techniques in practice. Despite the fact that it is a well known problem, and there are many different propositions on how it could be solved, the issue still remains unsolved to a satisfactory level for use in the real applications. In this thesis, novel methods using some elements from the fuzzy set theory for the matching the pair of stereoscopic images have been developed. Using the fuzzy set theory is a part of a research trend which consists in finding new ways of solution. The presented methods and experimental results should conclude that in some cases the application of fuzzy set theory allows to accomplish better results than obtained with the use of methods and algorithms known from the specialist literature.
PKT classification
410000
KBN classification
28
Thesis file
Request a WCAG compliant version

Uniform Resource Identifier
urn:pw-repo:WUT4756fa4505e84ed2933f07aff10add02