Representing images by means of interval-valued fuzzy sets. Application to stereo matching

Galar, Mikel, Barrenechea, Edurne, Fernandez, Javier, Bustince, Humberto and Beliakov, Gleb 2011, Representing images by means of interval-valued fuzzy sets. Application to stereo matching, in T2FUZZ 2011 : IEEE Symposium on Advances in Type-2 Fuzzy Logic Systems, IEEE, [Paris, France], pp. 134-141.

Attached Files
Name Description MIMEType Size Downloads

Title Representing images by means of interval-valued fuzzy sets. Application to stereo matching
Author(s) Galar, Mikel
Barrenechea, Edurne
Fernandez, Javier
Bustince, Humberto
Beliakov, Gleb
Conference name Symposium on Advances in Type-2 Fuzzy Logic Systems (1st : 2011 : Paris, France)
Conference location Paris, France
Conference dates 11-15 Apr. 2011
Title of proceedings T2FUZZ 2011 : IEEE Symposium on Advances in Type-2 Fuzzy Logic Systems
Editor(s) [Unknown]
Publication date 2011
Conference series SSCI 2011- Symposium Series on Computational Intelligence
Start page 134
End page 141
Publisher IEEE
Place of publication [Paris, France]
Keyword(s) interval-valued fuzzy set
interval-valued similarity
stereo matching problem
Summary Stereo matching tries to find correspondences between locations in a pair of displaced images of the same scene in order to extract the underlying depth information. Pixel correspondence estimation suffers from occlusions, noise or bias. In this work, we introduce a novel approach to represent images by means of interval-valued fuzzy sets to overcome the uncertainty due to the above mentioned problems. Our aim is to take advantage of this representation in the stereo matching algorithm. The image interval-valued fuzzification process that we propose is based on image segmentation in a different way to the common use of segmentation in stereo vision. We introduce interval-valued fuzzy similarities to compare windows whose pixels are represented by intervals. In the experimental analysis we show the goodness of this representation in the stereo matching problem. The new representation together with the new similarity measure that we introduce shows a better overall behavior with respect to other very well-known methods.
ISBN 9781612840789
9781612840772
Language eng
Field of Research 080108 Neural, Evolutionary and Fuzzy Computation
080104 Computer Vision
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2011, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30042207

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 56 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Tue, 14 Feb 2012, 15:16:54 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.