Title :
Application of adaptive constructive neural networks to image compression
Author :
Ma, Liying ; Khorasani, K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Concordia Univ., Montreal, Que., Canada
fDate :
9/1/2002 12:00:00 AM
Abstract :
The objective of the paper is the application of an adaptive constructive one-hidden-layer feedforward neural networks (OHL-FNNs) to image compression. Comparisons with fixed structure neural networks are performed to demonstrate and illustrate the training and the generalization capabilities of the proposed adaptive constructive networks. The influence of quantization effects as well as comparison with the baseline JPEG scheme are also investigated. It has been demonstrated through several experiments that very promising results are obtained as compared to presently available techniques in the literature.
Keywords :
data compression; feedforward neural nets; generalisation (artificial intelligence); image coding; learning (artificial intelligence); OHL-FNNs; adaptive constructive neural networks; adaptive constructive one-hidden-layer feedforward neural networks; baseline JPEG scheme; constructive algorithms; feedforward neural networks; fixed structure neural networks; generalization capabilities; generalization capability; image compression; quantization effects; Adaptive systems; Cellular neural networks; Feedforward neural networks; Image coding; Image reconstruction; Image storage; Neural networks; Pixel; Quantization; Transform coding;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2002.1031943
