Pseudo-invariant image transformations on a hexagonal lattice

A novel data structure for a machine vision system is presented in this pap er. The approach is inspired from anatomical considerations of the primate' s vision system. The geometrical arrangements of cones (photo receptors) on a primate's retina can be described in terms of a hexagonal lattice. The i mportance of this lattice is that it possesses special computational featur es pertinent to the vision process. Pseudo- (quasi-) invariant transformations are relevant to both biological and machine vision systems. They provide a means by which an image can be r epresented independent of a coordinate system. This facilitates the object recognition process. This paper describes a method of producing pseudo-inva riant image transformations on a hexagonal lattice. A method of implementin g the invariant transformations on a computer is provided. Application area s where the transformations can be employed are discussed. (C) 2000 Elsevie r Science B.V. All rights reserved.