Vf. Nesteruk, GENERAL-PRINCIPLES FOR CONSTRUCTING THE KERNELS OF NONLINEAR STATISTICAL IMAGE TRANSFORMS, Telecommunications & radio engineering, 48(6), 1993, pp. 85-89
Classes of nonlinear inertialess statistical transforms of optical ima
ges are examined. The origin of the kernels is related to the features
of visual perception as well as the ability to maintain constancy or
stabilization of the characteristics of transformed images and also th
e principles of duality and the maximum information effect.