Neural network texture classifiers using direct input cooccurrence matrices

Authors:
Anwar K. Muhamad;Farzin Deravi
Affiliations:
Dept. of Electrical and Electronic Engineering, University of Wales, Swansea, UK;Dept. of Electrical and Electronic Engineering, University of Wales, Swansea, UK
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
Year:
1993

Citing 1
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a visual comparison between cooccurrence matrices representing 9 different natural texture classes is described. Based on these comparisons, matrices of greatly reduced sizes are utilized directly, without computing secondary features, to train a feed-forward neural classifier in order to distinguish among the various texture classes. It is shown that recognition rates, higher than those obtained using a selected set of conventional features, can be obtained. Next, a practical application concerning the classification of wear particles by their surface texture is addressed. Again, it is shown that high recognition rates can be achieved in distinguishing among samples belonging to 5 different wear particle classes.