Title :
Estimation of texture element size and regularity in feature space
Author :
Benke, K. ; Nandagopal, N.
Author_Institution :
Defence Sci. & Technol. Organ., Melbourne, Vic., Australia
Abstract :
An approach is described for estimating texture element size and spacing in order to establish the optimum dimensions required for a spatial filter (or the receptive field of a neural network) when used for pattern discrimination. The method is demonstrated on samples from an international database and has potential use in the classification and segmentation of seabed textures and satellite imagery
Keywords :
image classification; image segmentation; image texture; optimisation; spatial filters; feature space; neural network; pattern discrimination; receptive field; regularity; satellite imagery; seabed textures; spacing; spatial filter; texture element size; Australia; Convolution; Energy measurement; Filtering; Matched filters; Neural networks; Optimization methods; Space technology; Spatial filters; Stochastic processes;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488957
