Natural image matting is an extremely challenging image processing problem due to its ill-posed nature. It often requires skilled user interaction to aid definition of foreground ...
Muhammad Sarim, Adrian Hilton, Jean-Yves Guillemau...
We develop a statistical framework for the simultaneous, unsupervised segmentation and discovery of visual object categories from image databases. Examining a large set of manuall...
Natural images are known to have scale invariant statistics. While some eariler studies have reported the kurtosis of marginal bandpass filter response distributions to be constant...
Divisive normalization has been recognized as a successful approach to model the perceptual sensitivity of biological vision. It also provides a useful image representation that i...
We develop a linear model of commonly observed joint color changes in images due to variation in lighting and certain non-geometric camera parameters. This is done by observing ho...