Share Email Print

Proceedings Paper

Texture classification and neural network methods
Author(s): Ari J. E. Visa
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Some neural network based methods for texture classification and segmentation have been published. The motivation for this kind of work might be doubted, because there are many traditional methods that work well. In this paper, a neural network based method for stochastic texture classification and segmentation suggested by Visa is compared with traditional K- means and k-nearest neighbor classification methods. Both simulated and real data are used. The complexity of the considered methods is also analyzed. The conclusion is the K-means method is the least successful of the three tested methods. The developed method is slightly more powerful than the k-nearest neighbor method for map sizes 9 X 9 and 10 X 10. The differences are, however, quite small. This means that the choice of classification method depends more on other aspects, like computational complexity and learning capability, than on the classification capability.

Paper Details

Date Published: 1 August 1991
PDF: 12 pages
Proc. SPIE 1469, Applications of Artificial Neural Networks II, (1 August 1991); doi: 10.1117/12.45020
Show Author Affiliations
Ari J. E. Visa, Helsinki Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 1469:
Applications of Artificial Neural Networks II
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top