Image Segmentation With Maximum Cuts
نویسنده
چکیده
This paper presents an alternative approach to the image segmentation problem. Similar to other recent proposals a graph theoretic framework is used: Given an image a weighted undirected graph is constructed, where each pixel becomes a vertex of the graph and edges measure a relationship between pixels. Our approach differs from previous work in the way we define the edge weights. Typically the edge weights represent pixel similiarities and a good segmentation corresponds to a (normalized) minimum cut of the graph. The shortcoming of the minimum cut approach is that it favors cutting small regions of isolated nodes and therefore a normalization is needed in order to enforce a more balanced partitioning. We propose to fix this shortcoming by using a maximum cut approach, because a maximum cut is usually achieved when the clusters are of similar size. Our edge weights measure the pixel dissimilarity and hence we seek a maximum cut of the graph. Since computing the maximum cut is NP-complete we use an approximation algorithm based on semidefinite programming to obtain a good cut. We define different graph structures that can be used and show that the computational complexity of the problem significantly depends on the structure of the graph. Synthetic and real images are segmented and the results are compared to results obtained by alternative segmentation algorithms.
منابع مشابه
A comparative performance of gray level image thresholding using normalized graph cut based standard S membership function
In this research paper, we use a normalized graph cut measure as a thresholding principle to separate an object from the background based on the standard S membership function. The implementation of the proposed algorithm known as fuzzy normalized graph cut method. This proposed algorithm compared with the fuzzy entropy method [25], Kittler [11], Rosin [21], Sauvola [23] and Wolf [33] method. M...
متن کاملGraph Cuts for Image Segmentation
In computer vision, segmentation is the process of partitioning digital image into multiple regions (sets of pixels), according to some homogeneity criterion. The problem of segmentation is a well-studied one in literature and there are a wide variety of approaches that are used. Graph cuts has emerged as a preferred method to solve a class of energy minimization problems such as Image Segmenta...
متن کاملA Parallel Framework for Parametric Maximum Flow Problems in Image Segmentation
This paper presents a framework that supports the implementation of parallel solutions for the widespread parametric maximum flow computational routines used in image segmentation algorithms. The framework is based on supergraphs, a special construction combining several image graphs into a larger one, and works on various architectures (multi-core or GPU), either locally or remotely in a clust...
متن کاملBinary Image Segmentation Using Graph Cuts 6.854 Advanced Algorithm Term Project
We implemented several maximum-flow algorithms, and applied them for segmentation of a degraded binary image. The purpose of the segmentation is to track the position of the hand in camera images for gestural interaction. The segmentation is based on the maximum a posteriori estimation which can be reformulated as a network flow problem. We compare the running time of the different algorithms w...
متن کاملA Simple Topology Preserving Max-Flow Algorithm for Graph Cut Based Image Segmentation
In this paper, we propose a modification to the Boykov-Kolmogorov maximum flow algorithm [2] in order to make the algorithm preserve the topology of an initial interface. This algorithm is being widely used in computer vision and image processing fields for its efficiency and speed when dealing with problems such as graph cut based image segmentation. Using our modification we are able to incor...
متن کامل