David McG. Squire and Terry M. Caelli,
Invariance Signatures: Characterizing contours by their
departures from invariance.
Tech. Rep. 97.04, Computer Vision Group, Computing Centre, University
of Geneva, rue Général Dufour, 24, CH-1211 Genève,
Switzerland, April 1997.
In this paper, a new invariant feature of two-dimensional contours is reported: the Invariance Signature. The Invariance Signature is a measure of the degree to which a contour is invariant under a variety of transformations, derived from the theory of Lie transformation groups. Since it is derived from local properties of the contour, it is well-suited to a neural network implementation. It is shown that a Model-Based Neural Network (MBNN) can be constructed which computes the Invariance Signature of a contour, and classifies patterns on this basis. Experiments demonstrate that Invariance Signature networks can be employed successfully for shift-, rotation- and scale-invariant optical character recognition.