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

1993

@article{ScD1993,
	vgclass =	{refpap},
	vgproject =	{nn,invariance},
	author =	{William A.C. Schmidt and Jon P. Davis},
	title =	{Pattern Recognition Properties of Various Feature Spaces
	for Higher Order Neural Networks},
	journal =	{IEEE Transactions on Pattern Analysis and Machine Intelligence},
	volume =	{15},
	number =	{8},
	pages =	{795--801},
	month =	{August},
	year =	{1993},
	abstract =	{Higher order neural networks (HONN's) are a form of
	preprocessing for the standard backpropagation neural networks that use
	geometrically motivated nonlinear combinations of scene pixels to
	achieve invariant pattern recognition feature spaces. In standard
	backpropagation, scene pixel values are presented directly to the
	neural network input nodes. By proper choice of HONN pixel
	combinations, it is possible to directly incorporate geometric
	invariance properties into the HONN. The HONN can be considered to be a
	particular type of preprocessing that explicitly creates nonlinear
	decision surfaces. Originally, HONN's had fully interconnected input
	pixels that caused a severe storage requirement.  We explore
	alternatives that reduce the number of network weights while
	maintaining geometric invariant properties for recognizing patterns in
	real-time processing applications.

	This study is limited to translation and rotation invariance. We are
	primarily interested in examining the properties of various feature
	spaces for HONN's, in correlated and uncorrelated noise, such as the
	effect of various types of input features, feature size and number of
	feature pixels, and the effect of scene size. We also consider the HONN
	training robustness in terms of target detectability.

	The experimental setup consists of a $15 \times 20$ pixel scene
	possibly containing a $3 \times 10$ target. Each trial used 500
	training scenes plus 500 testing scenes. Results indicate that HONN's
	yield similar geometric target recognition properties to classical
	template matching.  However, the HONN's require an order of magnitude
	less computer processing time compared with template matching. For our
	simple target, HONN's with zero hidden layers yield results equivalent
	to HONN's with multiple layers.  This reduces network training time
	over the multiple layer networks.  Finally HONN's exhibit robust
	training characteristics. The HONN's that were trained at one input
	noise level and tested at a different level maintained similar
	probability of detection and probability of false alarm characteristics
	than did the HONN's that were trained and tested at the same input
	noise levels. Results indicate that HONN's could be considered for
	real-time target recognition applications.},
}