We present a new method for blind document bleed through removal based on separate Markov Random Field (MRF) regularization for the recto and for the verso side, where separate pri...
We propose a method to identify and localize object
classes in images. Instead of operating at the pixel level,
we advocate the use of superpixels as the basic unit of a
class s...
We address the problem of parameter estimation in presence
of both uncertainty and outlier noise. This is a common
occurrence in computer vision: feature localization
is perform...
Image matting is the problem of determining for each pixel in an image whether it is foreground, background, or the mixing parameter, ”alpha”, for those pixels that are a mixt...
Abstract. We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques re...