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

1990

@article{KhL1990,
	vgclass =	{refpap},
	vgproject =	{nn,invariance},
	author =	{Alireza Khotanzad and Jiin-Her Lu},
	title =	{Classification of Invariant Image Representations Using a
	Neural Network},
	journal =	{IEEE Transactions on Acoustics, Speech, and Signal Processing},
	volume =	{38},
	number =	{6},
	pages =	{1028--1038},
	month =	{June},
	year =	{1990},
	abstract =	{In this paper, a neural network (NN) based approach for
	classification of images represented by translation-, scale- and
	rotation-invariant features is presented. The utilized network is a
	multilayer perceptron (MLP) classifier with one hidden layer. The
	backpropagation learning is used for its training. Two types of
	features are used: moment invariants derived from geometrical moments
	of the image, and the newly developed Zernike moment based features.
	Zernike moments are the mapping of the image onto a set of complex
	orthogonal polynomials. The performance of the MLP is compared to those
	of three other statistical classifiers, namely Bayes,
	nearest-neighbour, and minimum-mean-distance. Through extensive
	experimentation with noiseless as well as noisy binary images of all
	English characters (26 classes), the following conclusions are reached:
	1) the MLP outperforms the other three classifiers, especially when
	noise is present, 2) the nearest-neighbour classifier performs about
	the same as the NN for the noiseless case, 3) the NN can do well even
	with a very small number of training samples, 4) the NN has a good
	degree of fault tolerance, and 5) the Zernike moment based features
	possess strong class separability power and are more powerful than
	moment invariants.},
}