We propose a new binocular stereo algorithm that estimates scene structure as a collection of smooth surface patches. The disparities within each patch are modeled by a continuous-valued spline, while the extent of each patch is... more
Figure : Tracking and annotating an object using graph cut segmentation. A building sign on the USC campus is first detected using simple recognition, after which no additional information is needed. As the camera moves, we segment and... more
Figure : Tracking and annotating an object using graph cut segmentation. A building sign on the USC campus is first detected using simple recognition, after which no additional information is needed. As the camera moves, we segment and... more
In a previous work, we proposed a new integer programming formulation for the graph coloring problem which, to a certain extent, avoids symmetry. We studied the facet structure of the 0/1-polytope associated with it. Based on these... more
We present an approach based on integer programming formulations of the graph coloring problem. Our goal is to develop models that remove some symmetrical solutions obtained by color permutations. We study the problem from a polyhedral... more
Colorectal cancer (CRC) is the third most common type of cancer with the liver being the most common site for cancer spread. A precise understanding of patient liver anatomy and pathology, as well as surgical planning based on that, plays... more
Phase unwrapping, i.e. the retrieval of absolute phases from wrapped, noisy measures, is a tough problem because of the presence of rotational inconsistencies (residues), randomly generated by noise and undersampling on the principal... more
Numerous methods or algorithms have been designed to solve the problem of nonlinear dimensionality reduction (NLDR). However, very few among them are able to embed efficiently 'circular' manifolds like cylinders or tori, which have one or... more
This paper investigates the use of graph cuts for the minimization of an energy functional for road detection in satellite images, defined on the Bayesian MRF framework. The road identification process is modeled as a search for the... more
This paper investigates the use of graph cuts for the minimization of an energy functional for road detection in satellite images, defined on the Bayesian MRF framework. The road identification process is modeled as a search for the... more
We present a semi-automatic segmentation technique of the anatomical structures of the brain: cerebrum, cerebellum, and brain stem. The method uses graph cuts segmentation with an anatomic template for initialization. First, a skull... more
This work studies the convex relaxation approach to the left ventricle (LV) segmentation which gives rise to a challenging multi-region seperation with the geometrical constraint. For each region, we consider the global Bhattacharyya... more
Interactive techniques for extracting the foreground object from an image have been the interest of research in computer vision for a long time. This paper addresses the problem of an efficient, semi-interactive extraction of a foreground... more
![To find the object boundary, Active Contour deforms so it can be represented as a time varying curve v(s,t) = [x(s,t), y(s,t)] where s € [0,1] is arc length and ¢ € R* is time. Dynamics of the contour in presence of external and internal forces can be governed by the following equation](https://figures.academia-assets.com/119032068/figure_001.jpg)
![where, a and b are constants and a < b. When a > b this becomes a step function with transition at (a + b) /2 from 0 to 1. Probability distribution function (Eq. 12) has been chosen in such way that the probability value P..is small near the contour Cp and large for points farther away. In this fuzzy function, a and b dictate the non-linear behavior of the function. The parameters a and b control the extents (distance from the boundary) to which the output response is considered from Snake and then onwards from that of GrabCut respectively. The extent of the points considered near the contour can be suitably controlled by choosing appropriate values of a and b. The value of P. is zero (0) when the distance of the pixel from the boundary is in the range [0..a], and one (1) in the range [b..1] (all values normalized). For the values between [a..b], we empirically found the smooth, non-linear S-shaped function to provide the best result. Figure 7 shows the effect of the interval [a, b] on the distribution function.](https://figures.academia-assets.com/119032068/figure_005.jpg)
We consider the general problem of learning an unknown functional dependency, f : X → Y, between a structured input space X and a structured output space Y, from labeled and unlabeled examples. We formulate this problem in terms of... more
Local graph-based probabilistic representation of object shape and appearance for model-based medical image segmentation Image segmentation is the process of partitioning a digital image into regions originating from different objects in... more
Accurate prostate segmentation in Trans Rectal Ultra Sound (TRUS) images is an important step in different clinical applications. However, the development of computer aided automatic prostate segmentation in TRUS images is a challenging... more
Polarimetric Synthetic Aperture Radar (POLSAR) data have been commercially available for the last few years, which has increased demand for its operational use in remote sensing applications. Segmentation and classification of image data... more
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by Edmonds, Karp, and Dinic [7, 6] in 1972, capacity scaling... more
Image processing techniques are now widely spread out over a large quan-tity of domains: like medical imaging, movies post-production, games... Au-tomatic detection and extraction of regions of interest inside an image, a volume or a... more
Capacity scaling is a hierarchical approach to graph representation that can improve theoretical complexity and practical efficiency of max-flow/min-cut algorithms. Introduced by Edmonds, Karp, and Dinic [7, 6] in 1972, capacity scaling... more
This paper proposes a novel approach for uncertainty quantification in dense Conditional Random Fields (CRFs). The presented approach, called Perturband-MPM, enables efficient, approximate sampling from dense multi-label CRFs via random... more
This paper proposes a novel approach for uncertainty quantification in dense Conditional Random Fields (CRFs). The presented approach, called Perturb-and-MPM, enables efficient, approximate sampling from dense multi-label CRFs via random... more
Let G = (V, E, L) be an edge-labeled graph such that V is the set of vertices, E is the set of edges, L is the set of labels (colors) and each edge e \in E has a label l(e) associated; The goal of the minimum labeling global cut problem... more
Graph cut minimization formulates the segmentation problem as the liner combination of data and smoothness terms. The smoothness term is included in the energy formulation through a regularization parameter. We propose that the trade-off... more
This paper presents an artifact-free texture mapping from multiview images. Mapping multiple images onto a 3D mesh model is not an easy task, because artifacts may appear when two more images are mapped into neighboring meshes. We define... more
On fusion of range and intensity information using Graph-Cut for planar patch segmentation
We deal with two intimately related subjects: quasi-randomness and regular partitions. The purpose of the concept of quasi-randomness is to measure how much a given graph "resembles" a random one. Moreover, a regular partition... more
Markov Random Fields (MRF's) are an effective way to impose spatial smoothness in computer vision. We describe an application of MRF's to a non-traditional but important problem in medical imaging: the reconstruction of MR images from raw... more
Existing parallel MRI methods are limited by a fundamental trade-off in that suppressing noise introduces aliasing artifacts. Bayesian methods with an appropriately chosen image prior offer a promising alternative; however, previous... more
-Ce papier présente une nouvelle méthode de segmentation automatique de personnes dans les images. Elle se base sur la méthode efficace de la coupe de graphe en l'adaptant pour mieux correspondre à la classe des personnes. En effet, ni la... more
This paper presents a new fully automatic method for segmenting upright people in the images. Is is based on the efficient graph cut segmentation. Since colour and texture prevent from discriminating this particular class, silhouette... more
A vertex-cut X is said to be a restricted cut of a graph G if it is a vertex-cut such that no vertex u in G has all its neighbors in X. Clearly, each connected component of G − X must have at least two vertices. The restricted... more
Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Unlike standard LP relaxation methods that linearize the... more
We consider the problem of obtaining an approximate maximum a posteriori estimate of a discrete random field characterized by pairwise potentials that form a truncated convex model. For this problem, we propose two st-MINCUT based move... more
We present a new image segmentation algorithm based on graph cuts. Our main tool is separation of each pixel from a special point outside the image by a cut of a minimum cost. Such a cut creates a group of pixels ¡ £ ¢ around each pixel.... more
![To avoid the problem of small clusters, J. Shi and J. Ma- lik [8] propose to normalize the cost of an (A, B)-cut as follows:](https://figures.academia-assets.com/115289512/figure_001.jpg)
Combinatorial min-cut algorithms on graphs have emerged as an increasingly useful tool for problems in vision. Typically, the use of graph cuts is motivated by one of the following two reasons. Firstly, graph cuts allow geometric... more
Generating artificial classic mosaics from digital images is an area of NPR rendering that has recently seen several successful approaches. A sequence of mosaic images creates a unique and compelling animation style, however, there has... more
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our algorithm detects and matches dense features... more
Optimization with graph cuts became very popular in recent years. Progress in problems such as stereo correspondence, image segmentation, etc., can be attributed, in part, to the development of efficient graph cut based optimization.... more
In recent years, stereo correspondence algorithms based on graph cuts have gained popularity due to the significant improvement in accuracy over the local methods. Even though there has been a noticeable progress in efficient max-flow... more
Many computer vision applications can be formulated as labeling problems. However, multilabeling problems are usually very challenging to solve, especially when some ordering constraints are enforced. We solve in this paper a five-parts... more
Optimization with graph cuts became very popular in recent years. As more applications rely on graph cuts, different energy functions are being employed. Recent evaluation of optimization algorithms showed that the widely used swap and... more
In recent years, interactive methods for segmentation are increasing in popularity due to their success in different domains such as medical image processing, photo editing, etc. We present an interactive segmentation algorithm that can... more
Among the most exciting advances in early vision has been the development of efficient energy minimization algorithms for pixel-labeling tasks such as depth or texture computation. It has been known for decades that such problems can be... more
Optical coherence tomography (OCT) is a noninvasive imaging modality which can be used to obtain depth images of the retina. The changing layer thicknesses can thus be quantified by analyzing these OCT images, moreover these changes have... more
In this article, we introduce the Sharma-Mittal entropy of a graph, which is a generalization of the existing idea of the von-Neumann entropy. The well-known Rényi, Thallis, and von-Neumann entropies can be expressed as limiting cases of... more