Results 1  10
of
12
Highlight and shading invariant color image segmentation using simulated annealing
 In Proceedings of the 3rd International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
, 2001
"... Abstract. Color constancy in color image segmentation is an important research issue. In this paper we develop a framework, based on the Dichromatic Re
ection Model for asserting the color highlight and shading invariance, and based on a Markov Random Field approach for segmentation. A given RGB im ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
(Show Context)
Abstract. Color constancy in color image segmentation is an important research issue. In this paper we develop a framework, based on the Dichromatic Re
ection Model for asserting the color highlight and shading invariance, and based on a Markov Random Field approach for segmentation. A given RGB image is transformed into a R'G'B ' space to remove any highlight components, and only the vectorangle component, representing color hue but not intensity, is preserved to remove shading eects. Due to the arbitrariness of vector angles for low R'G'B ' values, we perform a MonteCarlo sensitivity analysis to determine pixeldependent weights for the MRF segmentation. Results are presented and analyzed. 1
Feng D. “Segmentation of dual modality brain PET/CT images using the MAPMRF model
 Multimedia Signal Processing, 2008 IEEE 10 th Workshop on, IEEE
"... Abstract—Dual modality PET/CT has now essentially replaced PET in clinical practice and provided an opportunity to improve image segmentation through the high resolution, lower noise CT data. Thus far most research efforts have concentrated on segmentation of PETonly data. In this work we propose a ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract—Dual modality PET/CT has now essentially replaced PET in clinical practice and provided an opportunity to improve image segmentation through the high resolution, lower noise CT data. Thus far most research efforts have concentrated on segmentation of PETonly data. In this work we propose a systematic solution for the automated segmentation of brain PET/CT images into gray, white matter and CSF regions with the MAPMRF model. Our approach takes advantage of the full information available from the combined scan. A PET/CT image pair and its segmentation result are modelled as a random field triplet, and segmentation is eventually achieved by solving a maximum a posteriori (MAP) problem using the expectationmaximization (EM) algorithm with simulated annealing. We compared the novel algorithm to two widely used PETonly based segmentation methods in the SPM5 toolbox and the VBM toolbox for simulation and patient data. Our results suggest that using the proposed approach substantially improves the accuracy of the delineation of brain structures. I.
Markov Random Field Modeling for Threedimensional Reconstruction of the Left Ventricle in Cardiac Angiography
, 2005
"... This paper reports on a method for left ventricle threedimensional reconstruction from two orthogonal ventriculograms. The proposed algorithm is voxelbased and takes into account the conical projection geometry associated with the biplane image acquisition equipment. The reconstruction process sta ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
This paper reports on a method for left ventricle threedimensional reconstruction from two orthogonal ventriculograms. The proposed algorithm is voxelbased and takes into account the conical projection geometry associated with the biplane image acquisition equipment. The reconstruction process starts with an initial ellipsoidal approximation derived from the input ventriculograms. This model is subsequently deformed in such a way as to match the input projections. To this end, the object is modeled as a threedimensional MarkovGibbs random field, and an energy function is defined so that it includes one term that models the projections compatibility and another one that includes the space–time regularity constraints. The performance of this reconstruction method is evaluated by considering the reconstruction of mathematically synthesized phantoms and two 3D binary databases from two orthogonal synthesized projections. The method is also tested using real biplane ventriculograms. In this case, the performance of the reconstruction is expressed in terms of the projection error, which attains values between 9.50 % and 11.78 % for two biplane sequences including a total of 55 images.
Solving Stereo Correspondence through Minimizing Energy Function with HigherOrder Cliques
, 2008
"... Stereo correspondence is one of the most active research areas in computer vision. Energy minimization is widely used for early vision problems, such as image restoration, segmentation and stereo correspondence. Pairwise clique is the most commonly used smoothness term of energy function, but it is ..."
Abstract
 Add to MetaCart
(Show Context)
Stereo correspondence is one of the most active research areas in computer vision. Energy minimization is widely used for early vision problems, such as image restoration, segmentation and stereo correspondence. Pairwise clique is the most commonly used smoothness term of energy function, but it is unable to capture rich statistics of natural scene. Energy function considering higherorder clique potentials can characterizes richer statistics of natural scene than pairwise clique, but it is difficult to model higherorder clique potentials and the computation for minimization is much heavier. We introduce an reduced Pn Potts model which can characterize higherorder clique potentials and was first used for image segmentation. Specifically, we present two new models which map the Pn Potts model to αexpansion move and αβ swap move. Furthermore, we propose a new graph construction method for them which has fewer extra nodes than before. Those models can be easily applied to other vision problems. The experiment shows that the results considering Pn Potts model are more accurate than those without.
Abu Sayem
"... Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayesian labeling in which the segment of a image is defined as the maximum a posteriori (MAP) probability estimate of the true labeling. The Simulated Annealing (SA) algorithm is used to minimize the energy ..."
Abstract
 Add to MetaCart
(Show Context)
Segmentation on Computed Tomography (CT) image of heart and brain can be optimally posed as Bayesian labeling in which the segment of a image is defined as the maximum a posteriori (MAP) probability estimate of the true labeling. The Simulated Annealing (SA) algorithm is used to minimize the energy function associated with MRF posterior distribution function. The goal of this thesis paper is to minimize the energy function using Gaussian distribution and get accurate segmentation by slowly minimize the energy and simultaneously reduce the pixels which have no impact on the image at rapid rate to get the segmentation quickly without degrade the image. The propose algorithm able to get more precise segmentation.
A New Technique for Texture Classification Using Markov Random Fields
"... Abstract: This paper proposes, applies and evaluates a new technique for texture classification in digital images. The work describes, as far as possible in a quantitative way, the concept of texture in digital images. Furthermore, we developed an innovative model that allows classifying and charact ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract: This paper proposes, applies and evaluates a new technique for texture classification in digital images. The work describes, as far as possible in a quantitative way, the concept of texture in digital images. Furthermore, we developed an innovative model that allows classifying and characterizing texture in digital images, to be used as a useful tool in noninvasive inspection of visual surfaces. The proposed methodology extracts the statistical order from an image of texture. The extraction of the high statistical order has been made using as a tool Markov Random Fields. The Backpropagation neural net is used for designing a classification module that will serve to test the performance of the configuration histograms, which are based on the statistical order. Furthermore, the research suggests the evaluation of the proposed technique from a qualitative perspective.
Abstract The Curve Indicator Random Field
, 2001
"... Can the organization of local image measurements into curves be directly related to natural image structure? By viewing curve enhancement as a statistical estimation problem, we suggest that it can. In particular, the classical Gestalt perceptual organization cues of proximity and good continuation— ..."
Abstract
 Add to MetaCart
(Show Context)
Can the organization of local image measurements into curves be directly related to natural image structure? By viewing curve enhancement as a statistical estimation problem, we suggest that it can. In particular, the classical Gestalt perceptual organization cues of proximity and good continuation—the basis of many current curve enhancement systems—can be statistically measured in images. As a prior for our estimation approach we introduce the curve indicator random field (cirf). Technically, this random field is a superposition of local times of Markov processes that model the individual curves; intuitively, it is an idealized artist’s sketch, where the value of the field is the amount of ink deposited by the artist’s pen. The explicit formulation of the cirf allows the calculation of tractable formulas for its cumulants and moment generating functional. A novel aspect of the cirf is that contour intersections can be explicitly incorporated. More fundamentally, the cirf is a model of an ideal edge/line map, and therefore provides a basis for rigorously understanding real (noisy, blurry) edge/line measurements as an observation of the cirf. This model therefore allows us to derive
USING PROBABILISTIC GRAPHICAL MODELS TO DRAW INFERENCES IN SENSOR NETWORKS WITH TRACKING APPLICATIONS By
, 2014
"... ..."
(Show Context)
Image classification based on Markov random
"... This paper considers image classification based on a Markov random field (MRF), where the random field proposed here adopts Jeffreys divergence between categoryspecific probability densities. The classification method based on the proposed MRF is shown to be an extension of Switzer’s smoothing meth ..."
Abstract
 Add to MetaCart
(Show Context)
This paper considers image classification based on a Markov random field (MRF), where the random field proposed here adopts Jeffreys divergence between categoryspecific probability densities. The classification method based on the proposed MRF is shown to be an extension of Switzer’s smoothing method, which is applied in remote sensing and geospatial communities. Furthermore, the exact error rates due to the proposed and Switzer’s methods are obtained under the simple setup, and several properties are derived. Our method is applied to a benchmark data set of image classification, and exhibits a good performance in comparison with conventional methods. Key words: Bayes estimate; discriminant analysis; image analysis; KullbackLeibler information 1