Unified miulti-scale corner detection

We define a universal gradient-based representation for V-, T- and X-type corners. This expression is used to define a corner detector, based on Moments of the Gradient in Scale-space (MoGS). The performance of this operator is compared with that of the Plessey and the Kitchen and Rosenfeld operators. The MoGS operator is shown to have better invariance to scale, to be more reliable and to provide better corner localisation than the other operators. The computation of corner attributes for edge orientation, aperture, contrast, corner type and size is illustrated.