Results 1  10
of
27
Submodularity beyond submodular energies: coupling edges in graph cuts
 IN CVPR
, 2011
"... We propose a new family of nonsubmodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We ..."
Abstract

Cited by 32 (17 self)
 Add to MetaCart
We propose a new family of nonsubmodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We demonstrate the advantages of edge coupling in a natural setting, namely image segmentation. In particular, for finestructured objects and objects with shading variation, our structured edge coupling leads to significant improvements over standard approaches.
Curvature Prior for MRFbased Segmentation and Shape
, 2011
"... Most image labeling problems such as segmentation and image reconstruction are fundamentally illposed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
(Show Context)
Most image labeling problems such as segmentation and image reconstruction are fundamentally illposed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general lead to computationally intractable models. This paper addresses the problem of discovering compact representations of higher order priors which allow efficient inference. We propose a framework for solving this problem which uses a recently proposed representation of higher order functions where they are encoded as lower envelopes of linear functions. Maximum a Posterior inference on our learned models reduces to minimizing a pairwise function of discrete variables, which can be done approximately using standard methods. Although this is a primarily theoretical paper, we also demonstrate the practical effectiveness of our framework on the problem of learning a shape prior for image segmentation and reconstruction. We show that our framework can learn a compact representation that approximates a prior that encourages low curvature shapes. We evaluate the approximation accuracy, discuss properties of the trained model, and show various results for shape inpainting and image segmentation. 1
The Elastic Ratio: Introducing Curvature into Ratiobased Image Segmentation
"... We present the first ratiobased image segmentation method which allows to impose curvature regularity of the region boundary. Our approach is a generalization of the ratio framework pioneered by Jermyn and Ishikawa so as to allow penalty functions that take into account the local curvature of the ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
We present the first ratiobased image segmentation method which allows to impose curvature regularity of the region boundary. Our approach is a generalization of the ratio framework pioneered by Jermyn and Ishikawa so as to allow penalty functions that take into account the local curvature of the curve. The key idea is to cast the segmentation problem as one of finding cyclic paths of minimal ratio in a graph where each graph node represents a line segment. Among ratios whose discrete counterparts can be globally minimized with our approach, we focus in particular on the elastic ratio L(C)
Generalized sequential treereweighted message passing
 arXiv:1205.6352
"... This paper addresses the problem of approximate MAPMRF inference in general graphical models. Following [36], we consider a family of linear programming relaxations of the problem where each relaxation is specified by a set of nested pairs of factors for which the marginalization constraint needs t ..."
Abstract

Cited by 8 (3 self)
 Add to MetaCart
(Show Context)
This paper addresses the problem of approximate MAPMRF inference in general graphical models. Following [36], we consider a family of linear programming relaxations of the problem where each relaxation is specified by a set of nested pairs of factors for which the marginalization constraint needs to be enforced. We develop a generalization of the TRWS algorithm [9] for this problem, where we use a decomposition into junction chains, monotonic w.r.t. some ordering on the nodes. This generalizes the monotonic chains in [9] in a natural way. We also show how to deal with nested factors in an efficient way. Experiments show an improvement over minsum diffusion, MPLP and subgradient ascent algorithms on a number of computer vision and natural language processing problems. 1
PseudoBound Optimization for Binary Energies
"... Abstract. Highorder and nonsubmodular pairwise energies are important for image segmentation, surface matching, deconvolution, tracking and other computer vision problems. Minimization of such energies is generally NPhard. One standard approximation approach is to optimize an auxiliary function ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
(Show Context)
Abstract. Highorder and nonsubmodular pairwise energies are important for image segmentation, surface matching, deconvolution, tracking and other computer vision problems. Minimization of such energies is generally NPhard. One standard approximation approach is to optimize an auxiliary function an upper bound of the original energy across the entire solution space. This bound must be amenable to fast global solvers. Ideally, it should also closely approximate the original functional, but it is very dicult to nd such upper bounds in practice. Our main idea is to relax the upperbound condition for an auxiliary function and to replace it with a family of pseudobounds, which can better approximate the original energy. We use fast polynomial parametric max ow approach to explore all global minima for our family of submodular pseudobounds. The best solution is guaranteed to decrease the original energy because the family includes at least one auxiliary function. Our PseudoBound Cuts algorithm improves the stateoftheart in many applications: appearance entropy minimization, target distribution matching, curvature regularization, image deconvolution and interactive segmentation.
Automatic segmentation of unknown objects, with application to baggage security
 In European Conference on Computer Vision (ECCV
, 2012
"... Abstract. Computed tomography (CT) is used widely to image patients for medical diagnosis and to scan baggage for threatening materials. Automated reading of these images can be used to reduce the costs of a human operator, extract quantitative information from the images or support the judgements o ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
Abstract. Computed tomography (CT) is used widely to image patients for medical diagnosis and to scan baggage for threatening materials. Automated reading of these images can be used to reduce the costs of a human operator, extract quantitative information from the images or support the judgements of a human operator. Object quantification requires an image segmentation to make measurements about object size, material composition and morphology. Medical applications mostly require the segmentation of prespecified objects, such as specific organs or lesions, which allows the use of customized algorithms that take advantage of training data to provide orientation and anatomical context of the segmentation targets. In contrast, baggage screening requires the segmentation algorithm to provide segmentation of an unspecified number of objects with enormous variability in size, shape, appearance and spatial context. Furthermore, security systems demand 3D segmentation algorithms that can quickly and reliably detect threats. To address this problem, we present a segmentation algorithm for 3D CT images that makes no assumptions on the number of objects in the image or on the composition of these objects. The algorithm features a new Automatic QUality Measure (AQUA) model that measures the segmentation confidence for any single object (from any segmentation method) and uses this confidence measure to both control splitting and to optimize the segmentation parameters at runtime for each dataset. The algorithm is tested on 27 bags that were packed with a large variety of different objects. 1
Evaluating Segmentation Error Without Ground Truth
"... Abstract. The automatic delineation of the boundaries of organs and other anatomical structures is a key component of many medical image processing systems. In this paper we present a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overl ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Abstract. The automatic delineation of the boundaries of organs and other anatomical structures is a key component of many medical image processing systems. In this paper we present a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overlap error and Dice coefficient of an arbitrary organ segmentation without knowing the ground truth delineation. We show the regressor to be much stronger a predictor of these error metrics than the responses of Probabilistic Boosting Classifiers trained on the segmentation boundary. The presented approach not only allows us to build reliable confidence measures and fidelity checks, but also to rank several segmentation hypotheses against each other during online usage of the segmentation algorithm in clinical practice. 1
Curvature Regularity for MultiLabel Problems Standard and Customized Linear Programming
"... Abstract. We follow recent work by Schoenemann et al. [25] for expressing curvature regularity as a linear program. While the original formulation focused on binary segmentation, we address several multilabel problems, including segmentation, denoising and inpainting, all cast as a single linear pr ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Abstract. We follow recent work by Schoenemann et al. [25] for expressing curvature regularity as a linear program. While the original formulation focused on binary segmentation, we address several multilabel problems, including segmentation, denoising and inpainting, all cast as a single linear program. Our multilabel segmentation introduces a “curvature Potts model ” and combines a wellknown Potts model relaxation [14] with the above work. For inpainting, we improve on [25] by grouping intensities into bins. Finally, we address the problem of denoising with absolute differences in the data term. Furthermore, we explore alternative solving strategies, including higher order Markov Random Fields, minsum diffusion and a combination of augmented Lagrangians and an accelerated first order scheme to solve the linear programs. 1
VESSEL SEGMENTATION USING 3D ELASTICA REGULARIZATION
"... Vascular diseases are among the most important health problems. Vessel segmentation is a very critical task for stenosis measurement and simulation, diagnosis and treatment planning. However, vessel segmentation is much more challenging than bloblike object segmentation due to the thin elongated an ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Vascular diseases are among the most important health problems. Vessel segmentation is a very critical task for stenosis measurement and simulation, diagnosis and treatment planning. However, vessel segmentation is much more challenging than bloblike object segmentation due to the thin elongated anatomy of the blood vessels, which can easily appear disconnected in the acquired images due to noise and occlusion. In this paper, we present a generic vessel segmentation approach that extracts the vessels by globally minimizing the surface curvature. The low curvature model enforces surface continuity and prevents the formation of false positives (leakages) and false negatives (holes). We present two contributions: First, we introduce a generic 3D vessel segmentation model by penalizing the boundary surface curvature. Second, we introduce an attraction force as a generalization of the boundary length in the elastica model, which guarantees a complete global solution and avoids shrinkage bias of length regularization. Our results will illustrate that the approach works efficiently across different acquisition modalities and for different applications.