Optoelectronic fractal scanning technique for wavelet transform and neural net pattern classifiers
Open Access
- 2 January 2003
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 40-46 vol.1
- https://doi.org/10.1109/ijcnn.1992.287240
Abstract
A 1D scan which follows Peano's curve to a desired resolution is demonstrated to preserve the 2D proximity relationship and is furthermore shown to be efficient for wavelet transform (WT) processing and artificial neural network pattern recognition. This deterministic fractal sampling method can be implemented in real time using optoelectronic scanning. For example, 2D texture patterns are analyzed by using a 1D WT. Those WT coefficients can be fed into a standard backpropagating neural network for pattern recognition. To speed up training time, a top-down design which generalizes Hopfield's energy landscape approach is given in terms of mini-max pattern classifiers.<>Keywords
This publication has 7 references indexed in Scilit:
- Wavelet transform as a bank of the matched filtersApplied Optics, 1992
- Neural networks based on peano curves and hairy neuronsTelematics and Informatics, 1990
- Texture description and segmentation through fractal geometryComputer Vision, Graphics, and Image Processing, 1989
- Reconfigurable neural nets by energy convergence learning principle based on extended McCulloch-Pitts neurons and synapsesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Adaptive optical networks using photorefractive crystalsApplied Optics, 1988
- Optical Neural ComputersScientific American, 1987
- Sur une courbe, qui remplit toute une aire planeMathematische Annalen, 1890