We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of `mean cut' cost functions. Minimizing these cost functions corresponds ...
Abstract. We present a geometric and statistical approach to gaitbased human recognition. The novelty here is to consider observations of gait, considered as planar silhouettes, to...
We present a variational approachto dense stereo reconstructionwhich combines powerful tools such as regularization and multi-scale processing to estimate directly depth from a num...
Volumetric data commonly has high depth complexity which makes it difficult to judge spatial relationships accurately. There are many different ways to enhance depth perception, su...
Medial axis transform (MAT) is a basic tool for shape analysis. But, in spite of its usefulness, it has some drawbacks, one of which is its instability under the boundary perturba...