This paper investigates segmentation of images and videos using graph cuts and shape priors. Graph cuts is used to find the global optimum of a cost function based on the region and boundary properties of the image or video. The region and boundary properties are estimated using certain pixels marked by the user. A shape prior term is added to this cost function to bias the solution towards a k...

The maximum a posteriori (MAP) configuration of binary variable models with submodular graph-structured energy functions can be found efficiently and exactly by graph cuts. Max-product belief propagation (MP) has been shown to be suboptimal on this class of energy functions by a canonical counterexample where MP converges to a suboptimal fixed point (Kulesza & Pereira, 2008). In this work, we s...

Voxel occupancy is one approach for reconstructing the 3-dimensional shape of an object from multiple views. In voxel occupancy, the task is to produce a binary labeling of a set of voxels, that determines which voxels are filled and which are empty. In this paper, we give an energy minimization formulation of the voxel occupancy problem. The global minimum of this energy can be rapidly compute...

We study the problem of sketching an input graph, so that, given the sketch, one can estimate the value (capacity) of any cut in the graph up to 1+ε approximation. Our results include both upper and lower bound on the sketch size, expressed in terms of the vertex-set size n and the accuracy ε. We design a randomized scheme which, given ε ∈ (0, 1) and an n-vertex graph G = (V,E) with edge capaci...

Graph cuts have become an increasingly important tool for solving a number of energy minimization problems in computer vision and other fields. In this paper, the graph cut problem is reformulated as an unconstrained l1 norm minimization that can be solved effectively using interior point methods. This reformulation exposes connections between the graph cuts and other related continuous optimiz...

Brain MRI segmentation remains a challenging problem in spite of numerous existing techniques. To overcome the inherent difficulties associated with this segmentation problem, we present a new method of information integration in a graph based framework. In addition to image intensity, tissue priors and local boundary information are integrated into the edge weight metrics in the graph. Further...

We demonstrate a new technique for general purpose interactive segmentation of N-dimensional images. The method creates two segments: “object” and “background”. The technical details can be found in our paper [1] in this proceedings. Below we concentrate on the actual interface. The user can enter seeds via mouse-operated brush of red (for object) or blue (for background) color. The size of the...

In this paper we address the problem of minimizing a large class of energy functions that occur in early vision. The major restriction is that the energy function’s smoothness term must only involve pairs of pixels. We propose two algorithms that use graph cuts to compute a local minimum even when very large moves are allowed. The first move we consider is an α-βswap: for a pair of labels α, β,...

In this paper, we propose a new method, which requires no interactive operation, to estimate background from an image sequence with occluding objects. The images are taken from the same viewpoint under similar illumination conditions. Our method combines the information from input images by selecting the appropriate pixels to construct the background. We have two simple assumptions for the inpu...

Standard quadratic programs are non-convex quadratic programs with the only constraint that variables must belong to a simplex. By a famous result of Motzkin and Straus, those problems are connected to the clique number of a graph. In this paper, we study cutting plane techniques to obtain strong bounds for standard quadratic programs. Our cuts are derived in the context of a Spatial Branch & B...