Texture segmentation by minimizing vector-valued energy functionals: The Coupled-Membrane model
Lecture notes in computer sciencePublished 1 January 1992Open access
Tai Sing Lee, David Mumford, Alan Yuille
Citations54
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The proposed Coupled-Membrane model applies the weak membrane approach to an image WI(σ,θ, x, y), derived from the power responses of a family of selfsimilar quadrature Gabor wavelets, and is adequate in segmenting a class of synthetic and natural texture images.
Abstract
This paper presents a computational model that segments images based on the textural properties of object surfaces. The proposed Coupled-Membrane model applies the weak membrane approach to an image WI(σ,θ, x, y), derived from the power responses of a family of selfsimilar quadrature Gabor wavelets. While segmentation breaks are allowed in x and y only, coupling is introduced to in all 4 dimensions. The resulting spatial and spectral diffusion prevents minor variations in local textures from producing segmentation boundaries. Experiments showed that the model is adequate in segmenting a class of synthetic and natural texture images.
Keywords
ChemistryComputer Science
ScienceOptimization by Simulated Annealing
44,600 Citations1983Scott Kirkpatrick, C. D. Gelatt +1 more
A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems.
Journal of Aesthetics and Art CriticismThe Ecological Approach to Visual Perception
23,142 Citations1980Marc H. Bornstein, James J. Gibson
Journal of the Optical Society of America AUncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters
3,165 Citations1985John Daugman
Evidence is presented that the 2D receptive-field profiles of simple cells in mammalian visual cortex are well described by members of this optimal 2D filter family, and thus such visual neurons could be said to optimize the general uncertainty relations for joint 2D-spatial-2D-spectral information resolution.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMultichannel texture analysis using localized spatial filters
1,375 Citations1990Alan C. Bovik, Marianna Clark +1 more
An interpretation of image texture as a region code, or carrier of region information, is emphasized and examples are given of both types of texture processing using a variety of real and synthetic textures.
Biological CyberneticsGabor filters as texture discriminator
737 Citations1989I. Fogel, Dov Sagi
The model was found to be in good correlation with known psychophysical characteristics as texton based texture segregation and micropattern density sensitivity, however, this simple model fails to predict human performance in discrimination tasks based on differences in the density of “terminators”.
IEEE Transactions on Pattern Analysis and Machine IntelligenceBoundary detection by constrained optimization
481 Citations1990Donald Geman, Stuart Geman +2 more
A statistical framework is used for finding boundaries and for partitioning scenes into homogeneous regions and incorporates a measure of disparity between certain spatial features of block pairs of pixel gray levels, using the Kolmogorov-Smirnov nonparametric measures of difference between the distributions of these features.
Journal of the Optical Society of America ARelationship between spatial-frequency and orientation tuning of striate-cortex cells
227 Citations1985Michael A. Webster, Russell L. De Valois
The two-dimensional RF shape of striate cells more closely approximates that predicted by a two- dimensional Gabor model or by a Gaussian-derivative model than it does the classic shape based on the output of geniculate cells with aligned RF's.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSegmentation of textured images and Gestalt organization using spatial/spatial-frequency representations
184 Citations1990T.R. Reed, Harry Wechsler
Experimental results in the area of texture segmentation and Gestalt grouping using the Wigner distribution are presented, proving the feasibility of using s/sf representations for low-level (early, preattentive) vision.
International Journal of Computer VisionA common framework for image segmentation
180 Citations1991Davi Geiger, Alan Yuille
The Markov random field formalism is considered, a special case of the Bayesian approach, in which the probability distributions are specified by an energy function, and simple modifications to the energy can give a direct relation to robust statistics or can encourage hysteresis and nonmaximum suppression.
NatureComputing texture boundaries from images
168 Citations1988Harry Voorhees, Tomaso Poggio
This work proposes that blobs computed by a centre-surround operator are useful as texture elements, and that a simple non-parametric statistic can be used to compare local distributions of blob attributes to locate texture boundaries.
Proceedings of the National Academy of SciencesSpatial-frequency organization in primate striate cortex.
123 Citations1989M. S. Silverman, David H. Grosof +2 more
There is a systematic correlation between the topographical variation in spatial-frequency tuning and the modular CytOx pattern, which varied continuously in density, and low-frequency cells are at the center of the blobs, and cells tuned to increasingly higher spatial frequencies are at increasing radial distances.
IEEE Transactions on Systems Man and CyberneticsAn adaptive computational model for texture segmentation
42 Citations1988Terry Caelli
Extensions to current models for texture segmentation are presented, in which the underlying detector (filter) mechanisms are allowed to adapt to the incoming signal in terms of their dynamical response range and associativities.
DSpace@MIT (Massachusetts Institute of Technology)Finding Texture Boundaries in Images
30 Citations1987Harry Voorhees
An algorithm for computing blobs from natural images and a statistic for measuring the difference between two sample distributions of blob attributes are presented, which are applicable to edge detection as well.