—Detection of spurious features is instrumental in many computer vision applications. The standard approach is feature based, where extracted features are matched between the ima...
Image matting is of great importance in both computer vision and graphics applications. Most existing state-of-the-art techniques rely on large sparse matrices such as the matting ...
Modeling data by multiple low-dimensional planes is an important problem in many applications such as computer vision and pattern recognition. In the most general setting where on...
The biological visual system possesses the ability to compute layered surface representations, in which one surface is represented as being viewed through another. This ability is...
This paper proposes the use of genetic algorithm to select an optimal feature set for distinguishing computer graphics from digital photographic images. Our previously developed a...