Isoperimetric graph partitioning for image segmentation

By Leo J. Grady, Eric L. Schwartz. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

295 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New Algorithm (2007, background): “For many graph based segmentation algorithms [14, 3, 6, 7], the edge weights encode image intensity changes.”
Star Shape Prior for Graph-Cut Image Segmentation (2008, background): “Global optimization ([8–10, 5, 11–13,7, 14, 15]), often formulated as a graph problem, became popular because it is more robust compared to the local methods such as thresholding or region-growing [16].”
Recent Advances in Graph Partitioning (2013, methodology): “Another relevant formulation of the partitioning objective which is useful for image segmentation is given by optimizing the isoperimetric ratio for sets [89].”
Lazy Random Walks for Superpixel Segmentation (2014, methodology): “In addition, another important related work with our paper is the RW algorithm and its applications in image processing [12], [13], [22], [23].”
Generative Image Segmentation Using Random Walks with Restart (2008, result): “In contrast to most existing models which focus on the inter-label discrimination, we address the problem of finding the generative model for each label like [10].”