An optimal graph theoretic approach to data clustering: theory and its application to image segmentation

Abstract

A novel graph theoretic approach for data clustering is presented and its application to the image segmentation problem is demonstrated. The data to be clustered are represented by an undirected adjacency graph G with arc capacities assigned to reflect the similarity between the linked vertices. Clustering is achieved by removing arcs of G to form mutually exclusive subgraphs such that the largest inter-subgraph maximum flow is minimized. For graphs of moderate size (-2000 vertices), the optimal solution is obtained through partitioning a flow and cut equivalent tree of 6, which can be efficiently constructed using the Gomory-Hu algorithm. However for larger graphs this approach is impractical. New theorems for subgraph condensation are derived and are then used to develop a fast algorithm which hierarchically constructs and partitions a partially equivalent tree of much reduced size. This algorithm results in an optimal solution equivalent to that obtained by partitioning the complete equivalent tree and is able to handle very large graphs with several hundred thousand vertices. The new clustering algorithm is applied to the image segmentation problem. The segmentation is achieved by effectively searching for closed contours of edge elements (equivalent to minimum cuts in G), which consist mostly of strong edges, while rejecting contours containing isolated strong edges. This method is able to accurately locate region boundaries and at the same time guarantees the formation of closed edge contours.

TurboPixels: Fast Superpixels Using Geometric Flows

“…They seek a set of recursive bipartitions that globally minimize a cost function based on the nodes in a segment and/or the edges between segments. Wu and Leahy [26] were the first to segment images using graph cuts, minimizing the sum of the edge weights across cut boundaries. However, their algorithm is biased toward short boundaries, leading to the creation of small regions.…”

Graph-based representations and techniques for image processing and image analysis

“…The worst disadvantage of these approaches, as can be seen in Refs. [13][14][15], is that these algorithms are very time consuming, which prohibits their implementation for real-time applications.…”

Graph Cut Based Point-Cloud Segmentation for Polygonal Reconstruction

“…The graph cut algorithm is designed to minimize energy function in weighted graph where the energy function defines segmentation. This technique is widely used in standard image segmentation [3,4,5] or in segmentation of range images or stereo matching [6,7]. Several works benefits from graph cuts for 3D mesh segmentation [8,9] or surface extraction [10,11,12].…”