Application of adaptive constructive neural networks to image compression

L Ma, K Khorasani - IEEE Transactions on Neural Networks, 2002 - ieeexplore.ieee.org
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 …

Adaptive constructive neural networks using hermite polynomials for image compression

L Ma, K Khorasani - International Symposium on Neural Networks, 2005 - Springer
Compression of digital images has been a very important subject of research for several
decades, and a vast number of techniques have been proposed. In particular, the possibility …

[PDF][PDF] Edge Preserving Image Compression Technique using Adaptive Feed Forward Neural Network.

SB Roy, K Kayal, J Sil - EuroIMSA, 2005 - Citeseer
The aim of the paper is to develop an edge preserving image compression technique using
one hidden layer feed forward neural network of which the neurons are determined …

New pruning techniques for constructive neural networks with application to image compression

L Ma, K Khorasani - … Sensor Fusion, and Target Recognition IX, 2000 - spiedigitallibrary.org
Image compression is an important research domain in image processing. Recently, several
neural netowkr (NN) based schemes developed in this are. In particular, constructive feed …

Nested neural networks for image compression

DK Kumar, N Mahalingam - … of IEEE TENCON'98. IEEE Region …, 1998 - ieeexplore.ieee.org
Data compression occurs naturally in the human brain. The brain detects features and the
context to any input signal and associates with it a name and form. The use of artificial …

Moving image compression and generalization capability of constructive neural networks

L Ma, K Khorasani - Applications and Science of …, 2001 - spiedigitallibrary.org
To date numerous techniques have been proposed to compress digital images to ease their
storage and transmission over communication channels. Recently, a number of image …

Constructive neural networks with applications to image compression and pattern recognition

L Ma - 2001 - spectrum.library.concordia.ca
The theory of Neural Networks (NNs) has witnessed a striking progress in the past fifteen
years. The basic issues, such as determining the structure and size of the network, and …