2000
@article{SqC2000,
vgclass = {refpap},
vgproject = {nn,invariance},
author = {David McG. Squire and Terry M. Caelli},
title = {Invariance Signatures: Characterizing contours by their
departures from invariance},
journal = {Computer Vision and Image Understanding},
volume = {77},
number = {3},
pages = {284--316},
month = {March},
year = {2000},
doi = {https://doi.org/10.1006/cviu.2000.0809},
url = {/publications/postscript/1999/SquireCaelli_cviu99.pdf},
url1 = {/publications/postscript/1999/SquireCaelli_cviu99.ps.gz},
abstract = {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. It is shown that the Invariance Signature is
itself invariant under shift, rotation and scaling of the contour.
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.},
}