Neural network architectures for vector prediction

Author

Rizvi, Syed A. ; Wang, Lin-Cheng ; Nasrabadi, Nasser M.

Author_Institution

Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA

Volume

84

Issue

10

fYear

1996

fDate

10/1/1996 12:00:00 AM

Firstpage

1513

Lastpage

1528

Abstract

A vector predictor is an integral part of a predictive vector quantization coding scheme. The conventional techniques for designing a nonlinear predictor are extremely complex and suboptimal due to the absence of a suitable model for the source data. We investigated several neural network architectures that can be used to implement a nonlinear vector predictor, including the multilayer perceptron, the functional link network and the radial basis function network. We also evaluated and compared the performance of these neural network predictors with that of a linear vector predictor. Our experimental results show that a neural network predictor can predict the blocks containing edges with a higher accuracy than a linear predictor. However, the performance of a neural network predictor is comparable to that of a linear predictor for predicting the stationary and shade blocks

Keywords

edge detection; feedforward neural nets; image coding; multilayer perceptrons; neural net architecture; prediction theory; vector quantisation; edge detection; functional link network; multilayer perceptron; neural network architectures; nonlinear vector predictor; predictive vector quantization; radial basis function network; shade block prediction; Dynamic range; Geometry; Image reconstruction; Laboratories; Multi-layer neural network; Multilayer perceptrons; Neural networks; Predictive models; Radial basis function networks; Vector quantization;

fLanguage

English

Journal_Title

Proceedings of the IEEE

Publisher

ieee

ISSN

0018-9219

Type

jour

DOI

10.1109/5.537115

Filename

537115