Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Fusion of image segmentation with domain specific information under an unsupervised markov random fields model
Download
index.pdf
Date
2014
Author
Karadağ, Özge Öztimur
Metadata
Show full item record
Item Usage Stats
142
views
222
downloads
Cite This
The formulation of image segmentation problem is evolved considerably, from the early years of computer vision in 1970s to these years, in 2010s. While the initial studies offer mostly unsupervised approaches, a great deal of recent studies shift towards the supervised solutions. This is due to the advancements in the cognitive science and its influence on the computer vision research. Also, accelerated availability of computational power enables the researchers to develop complex algorithms. Despite the great effort on the image segmentation research, the state of the art techniques still fall short to satisfy the need of the further processing steps of computer vision. This study is another attempt to generate a “substantially complete” segmentation output for the consumption of object classification, recognition and detection steps. Our approach is to fuse the multiple segmentation outputs in order to achieve the “best” result with respect to a cost function. The proposed approach, called Boosted-MRF, elegantly formulates the segmentation fusion problem as a Markov Random Fields (MRF) model in an unsupervised framework. For this purpose, a set of initial segmentation outputs is obtained and the consensus among the segmentation partitions are formulated in the energy function of the Markov Random Fields model. Finally, minimization of the energy function yields the “best” consensus among the segmentation ensemble. We proceed one step further to improve the performance of the Boosted-MRF by introducing some auxiliary domain information into the segmentation fusion process. This enhanced segmentation fusion method, called the Domain Specific MRF, updates the energy function of the MRF model by the available information which is received from a domain expert. For this purpose, a top-down segmentation method is employed to obtain a set of Domain Specific Segmentation Maps which are incomplete segmentations of a given image. Therefore, in this second segmentation fusion method, in addition to the set of bottom-up segmentation ensemble, we generate ensemble of top-down Domain Specific Segmentation Maps. Based on the bottom–up and top down segmentation ensembles a new MRF energy function is defined. Minimization of this energy function yields the “best” consensus which is consistent with the domain specific information. The experiments performed on various datasets show that the proposed segmentation fusion methods improve the performances of the segmentation outputs in the ensemble measured with various indexes, such as Probabilistic Rand Index, Mutual Information. The Boosted-MRF method is also compared to a popular segmentation fusion method, namely, Best of K. The Boosted-MRF is slightly better than the Best of K method. The suggested Domain Specific-MRF method is applied on a set of outdoor images with vegetation where vegetation information is utilized as domain specific information. A slight improvement in the performance is recorded in this experiment. The method is also applied on remotely sensed dataset of building images, where more advanced domain specific information is available. The segmentation performance is evaluated with a performance measure which is specifically defined to estimate the segmentation performance for building images. In these two experiments with the Domain Specific-MRF method, it is observed that, as long as reliable domain specific information is available, the segmentation performance improves significantly.
Subject Keywords
Image segmentation.
,
Image analysis.
,
Image processing
,
Markov random fields.
URI
http://etd.lib.metu.edu.tr/upload/12617113/index.pdf
https://hdl.handle.net/11511/23506
Collections
Graduate School of Natural and Applied Sciences, Thesis
Suggestions
OpenMETU
Core
Improving edge detection using ıntersection consistency
Çiftçi, Serdar; Yarman Vural, Fatoş Tunay; Kalkan, Sinan; Department of Computer Engineering (2011)
Edge detection is an important step in computer vision since edges are utilized by the successor visual processing stages including many tasks such as motion estimation, stereopsis, shape representation and matching, etc. In this study, we test whether a local consistency measure based on image orientation (which we call Intersection Consistency - IC), which was previously shown to improve detection of junctions, can be used for improving the quality of edge detection of seven different detectors; namely, C...
Design and implementation of a novel visual analysis system for image clasiffication
Altintakan, Ümit Lütfü; Yazıcı, Adnan; Körpeoğlu, İbrahim; Department of Computer Engineering (2013)
Possibilities offered by the technology to create, share and disseminate image and video data have resulted in a rapid increase in the available visual data. However, the data is useless unless it is effectively accessed, which necessitates the semantic analysis of visual data. In this dissertation, we present a novel visual analysis system along with its application to image classification problem. We aim to address the challenges in the area originated from the semantic gap, and to facilitate the research...
Alignment of uncalibrated images for multi-view classification
Arık, Sercan Ömer; Vural, Elif; Frossard, Pascal (2011-12-29)
Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pairwise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of im...
Fast 3D reconstruction from medical image series based on thresholding method Eşikleme metodunu kullanarak medikal görüntü serisinden hizli 3 boyutlu model oluşturma
Öz, Sinan; Serinağaoğlu Doğrusöz, Yeşim (2010-07-15)
Many practical applications in the field of medical image processing need valid, reliable and fast image segmentation. In this study, we propose a semi-automatic segmentation approach. In this approach, an extended version of the Otsu's method for three level thresholding and a recursive connected component algorithm are combined. The segmentation process is accomplished using Extended Otsu's method and labeling in each consecutive slice. Extended Otsu's method is a thresholding method selecting two thresho...
A Robust quality metric for image super resolution /
Kipman, Yiğit; Akar, Gözde; Department of Electrical and Electronics Engineering (2015)
Superresolution have become an active topic in image processing in the last decade. Various superresolution algorithms have been developed; however these superresolution algorithms may introduce defects such as blurring, aliasing, added noise and ringing. Evaluating the performance of these superresolution algorithms is an important problem; because the original high resolution image is not available while quantifying the quality of superresolution image. Subjective tests can be made to quantify the perceiv...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
Ö. Ö. Karadağ, “Fusion of image segmentation with domain specific information under an unsupervised markov random fields model,” Ph.D. - Doctoral Program, Middle East Technical University, 2014.