Title :
Nonlinear vector prediction using feed-forward neural networks
Author :
Rizvi, Syed A. ; Nasrabadi, Nasser M.
Author_Institution :
Coll. of Staten Island, City Univ. of New York, NY
fDate :
10/1/1997 12:00:00 AM
Abstract :
The performance of a classical linear vector predictor is limited by its ability to exploit only the linear correlation between the blocks. However, a nonlinear predictor exploits the higher order correlations among the neighboring blocks, and can predict edge blocks with increased accuracy. We have investigated several neural network architectures that can be used to implement a nonlinear vector predictor, including the multilayer perceptron (MLP), the functional link (FL) network, and the radial basis function (RBF) network. Our experimental results show that a neural network predictor can predict the blocks containing edges with a higher accuracy than a linear predictor
Keywords :
correlation methods; edge detection; feedforward neural nets; image coding; multilayer perceptrons; neural net architecture; prediction theory; vector quantisation; MLP; edge blocks prediction; experimental results; feedforward neural networks; functional link network; higher order correlations; image coding; image compression; linear vector predictor; multilayer perceptron; neural network architectures; neural network predictor; nonlinear vector prediction; performance; predictive vector quantization; radial basis function network; Feedforward neural networks; Feedforward systems; Image coding; Image reconstruction; Laboratories; Multi-layer neural network; Multilayer perceptrons; Neural networks; Radial basis function networks; Vector quantization;
Journal_Title :
Image Processing, IEEE Transactions on