A single layer neural network for texture discrimination
Authors:
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2656-2660 vol.5
Abstract
The authors present a neural net texture classification strategy, consisting of a novel feature extraction scheme and a neural network discriminator. Texture recognition is based on the co-occurrence of n-pixel groups in the images. This results in a state vector transformation of the image. The vectors are then classified using a single layer neural network in order to identify the textures. The procedure has been tested on natural textures and the results achieved have been promising.<>Keywords
This publication has 8 references indexed in Scilit:
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Adaptive Windows for Texture Discrimination1987
- Texture analysis Anno 1983Computer Vision, Graphics, and Image Processing, 1985
- WISARD·a radical step forward in image recognitionSensor Review, 1984
- Image Texture Analysis Techniques - A Survey1981
- Statistical and structural approaches to textureProceedings of the IEEE, 1979
- Guide to pattern recognition using random-access memoriesIEE Journal on Computers and Digital Techniques, 1979
- A Comparative Study of Texture Measures for Terrain ClassificationIEEE Transactions on Systems, Man, and Cybernetics, 1976