Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
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
Mumford-Shah Regularizer with Contextual Feedback
Date
2008-7-24
Author
Erdem, Erkut
Tarı, Zehra Sibel
Metadata
Show full item record
Item Usage Stats
60
views
0
downloads
Cite This
We present a simple and robust feature preserving image regularization by letting local region measures modulate the diffusivity. The purpose of this modulation is to disambiguate low level cues in early vision. We interpret the Ambrosio-Tortorelli approximation of the Mumford-Shah model as a system with modulatory feedback and utilize this interpretation to integrate high level information into the regularization process. The method does not require any prior model or learning; the high level information is extracted from local regions and fed back to the regularization step. An important characteristic of the method is that both negative and positive feedback can be simultaneously used without creating oscillations. Experiments performed with both gray and color natural images demonstrate the potential of the method under difficult noise types, non-uniform contrast, existence of multi-scale patterns and textures.
Subject Keywords
Variational and PDE methods, feature preserving diffusion
,
Structure preserving diffusion
,
Disambiguation in low level vision
URI
https://hdl.handle.net/11511/28576
Journal
Journal of Mathematical Imaging and Vision
DOI
https://doi.org/10.1007/s10851-008-0109-y
Collections
Department of Computer Engineering, Article
Suggestions
OpenMETU
Core
Mumford-shah regularizer with spatial coherence
Erdem, Erkut; Sancar-Yilmaz, Aysun; Tarı, Zehra Sibel (2007-01-01)
As recently discussed by Bar, Kiryati, and Sochen in [3], the Ambrosio-Tortorelli approximation of the Mumford-Shah functional de-Lines an extended line process regularization where the regularizer has an additional constraint introduced by the term rho vertical bar del v vertical bar(2). This term mildly forces some spatial organization by demanding that the edges are smooth. However, it does not force spatial coherence such as edge direction compatibility or edge connectivity, as in the traditional edge d...
Human action recognition with line and flow histograms
İKİZLER CİNBİŞ, NAZLI; Cinbiş, Ramazan Gökberk; DUYGULU ŞAHİN, PINAR (2008-12-11)
We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of lines which are fitted to boundaries of human figures. By using an entropy-based approach, we apply feature selection to densify our feature representation, thus, minimizing classification time without degrading accuracy. We also use a compact representation of optical flow for motion information. Using line and flow histograms to...
An improved method of photometric stereo using local shape from shading
Sakarya, U; Erkmen, İsmet (Elsevier BV, 2003-10-01)
This paper presents an improved photometric stereo (PS) method by integrating it with a local shape from shading (SFS) algorithm. PS produces the initial estimate of image for the global accuracy and also provides the recovery of albedo, SFS supplies the more detailed information within each homogeneous area. The quality of depth obtained by integrating PS and SFS is compared with the real depth using absolute dept error function, and the improvement ranging from 2.3 to 14% over PS is obtained.
Towards finding optimal mixture of subspaces for data classification
Musa, Mohamed Elhafiz Mustafa; Atalay, Mehmet Volkan; Department of Computer Engineering (2003)
In pattern recognition, when data has different structures in different parts of the input space, fitting one global model can be slow and inaccurate. Learning methods can quickly learn the structure of the data in local regions, consequently, offering faster and more accurate model fitting. Breaking training data set into smaller subsets may lead to curse of dimensionality problem, as a training sample subset may not be enough for estimating the required set of parameters for the submodels. Increasing the ...
Decoupled Modular Regularized VMS-POD for Darcy-Brinkman Equations
Güler Eroğlu, Fatma; Kaya Merdan, Songül; Rebholz, Leo G (2019-05-01)
We extend the post-processing implementation of a projection based variational multiscale (VMS) method with proper orthogonal decomposition (POD) to flows governed by double diffusive convection. In the method, the stabilization terms are added to momentum equation, heat and mass transfer equations as a completely decoupled separate steps. The theoretical analyses are presented. The results are verified with numerical tests on a benchmark problem.
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
E. Erdem and Z. S. Tarı, “Mumford-Shah Regularizer with Contextual Feedback,”
Journal of Mathematical Imaging and Vision
, pp. 67–84, 2008, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/28576.