Two-Dimensional Fast Orthogonal Neural Network for Image Recognition

Authors:
Bartłomiej Stasiak
Affiliations:
Institute of Computer Science, Technical University of Łódź, Łódź, Poland 93-005
Venue:
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Year:
2009

Citing 3
Cited 0

Discrete cosine transform: algorithms, advantages, applications

Discrete cosine transform: algorithms, advantages, applications
Tensor Rank One Discriminant Analysis-A convergent method for discriminative multilinear subspace selection

Neurocomputing
Fast orthogonal neural networks

ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a method of constructing a fast orthogonal neural network suitable for raw image recognition and classification. The neural architecture of the proposed network is based on fast cosine transform algorithm modified to enable Fourier amplitude spectrum computation. The presented network has reduced computational complexity and it reaches low generalization error values as compared to a standard multilayer perceptron.