This paper presents a texture image classification system based upon the use of two cascaded multi-layer feedforward neural networks (MFNNs). The first network transforms a set of high-dimensional and correlated feature images into another set of uncorrelated principal feature images with its dimensionality being significantly compressed whilst minimising the information lost. The second accomplishes the task of feature pattern classification by using only those principal features obtained by the former. A synthesised training system for synchronously learning the weights of these two networks is also presented. Important advantages of both the classification system and the associated training system are described. They are further demonstrated by detailed examples.
|Title of host publication||Plenary, Special, Audio, Underwater Acoustics, VLSI, Neural Networks|
|Publication status||Published - 1993|
|Event||18th IEEE International Conference on Acoustics, Speech and Signal Processing 1993 - Minneapolis, MN, United States|
Duration: 27 Apr 1993 → 30 Apr 1993
|Conference||18th IEEE International Conference on Acoustics, Speech and Signal Processing 1993|
|Period||27/04/93 → 30/04/93|