Refereed full papers (journals, book chapters, international conferences)

1995

@inproceedings{SqC1995,
	vgclass =	{refpap},
	vgproject =	{nn,invariance},
	author =	{David McG. Squire and Terry M. Caelli},
	title =	{Shift, Rotation and Scale Invariant Signatures for
	Two-Dimensional Contours, in a Neural Network Architecture},
	editor =	{Stephen W. Ellacott and John C. Mason and Iain J. Anderson},
	booktitle =	{Mathematics of Neural Networks: Models Algorithms and
	Applications},
	address =	{Boston},
	series =	{Statistics and OR},
	pages =	{344--348},
	publisher =	{Kluwer Academic Publishers},
	month =	{July},
	year =	{1995},
	doi =	{https://doi.org/10.1007/978-1-4615-6099-9_60},
	url =	{/publications/postscript/manna.ps.gz},
	abstract =	{A technique for obtaining shift, rotation and scale
	invariant signatures for two dimensional contours is proposed and
	demonstrated. An \emph{invariance factor} is calculated at each point
	by comparing the orientation of the tangent vector with vector fields
	corresponding to the generators of Lie transformation groups for shift,
	rotation and scaling.  The statistics of these invariance factors over
	the contour are used to produce an \emph{invariance signature}.

	This operation is implemented in a Model-Based Neural Network (MBNN),
	in which the architecture and weights are parameterised by the
	constraints of the problem domain. The end result after constructing
	and training this system is the same as a traditional neural network: a
	collection of layers of nodes with weighted connections. The design and
	modeling process can be thought of as \emph{compiling} an invariant
	classifier into a neural network.  We contend that these invariance
	signatures, whilst not unique, are sufficient to characterise contours
	for many pattern recognition tasks.},
}