Abstract

It is widely recognized that effective image processing and machine vision must involve the use of information at multiple scales, and that models of human vision must be multi-scale as well. The most commonly used image representations are linear transforms, in which an image is decomposed into a sum of elementary basis functions. Besides being well understood, linear transformations in the form of convolutions provide a useful model of some of the early processing in the human visual system.

© 1989 Optical Society of America