BMVC 2004, Kingston, 7th-9th Sept, 2004

Spectral Embedding and Min Cut for Image Segmentation
F. Estrada, A. Jepson and C. Chennubhotla (University of Toronto, Canada)

Recently it has been shown that min-cut algorithms can provide perceptually
salient image segments when they are given appropriate proposals for source
and sink regions. Here we explore the use of random walks and associated
spectral embedding techniques for the automatic generation of suitable proposal
regions. To do this, we first derive a mathematical connection between
spectral embedding and anisotropic image smoothing kernels. We then use
properties of the spectral embedding and the associated smoothing kernels to
select multiple pairs of source and sink regions for min-cut. This typically
provides an over-segmentation, and therefore region merging is used to form
the final image segmentation. We demonstrate this process on several sample
(pdf article)