We develop a pairwise classification framework for face recognition, in which a class face recognition problem is divided into a set of ? ?? ? two class problems. Such a problem...
Linear perspective projection has served as the dominant imaging model in computer vision. Recent developments in image sensing make the perspective model highly restrictive. This...
An effective object recognition scheme is to represent and match images on the basis of histograms derived from photometric color invariants. A drawback, however, is that certain c...
We describe a shape from texture method that constructs a maximum a posteriori estimate of surface coefficients using both the deformation of individual texture elements -as in lo...
This paper presents a technique for blindly removing image non-linearities in the absence of any calibration information or explicit knowledge of the imagingdevice. The basic appr...
In [10] we presented a new velocity estimation algorithm, using orientation tensors and parametric motion models to provide both fast and accurate results. One of the tradeoffs be...
This paper presents a novel modeling algorithm that is capable of simultaneously recovering correct shape geometry as well as its unknown topology from arbitrarily complicated dat...