We propose a multi-modal object tracking algorithm that combines appearance, motion and audio information in a particle filter. The proposed tracker fuses at the likelihood level ...
To segment a whole object from an image is an essential and challenging task in image processing. In this paper, we propose a hybrid segmentation algorithm which combines prior sh...
This paper presents novel techniques for detecting watermarks in images in a known-cover attack framework using natural scene models. Specifically, we consider a class of watermar...
Kalpana Seshadrinathan, Hamid R. Sheikh, Alan C. B...
Despite the ability of current GPU processors to treat heavy parallel computation tasks, its use for solving medical image segmentation problems is still not fully exploited and re...
We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...