Training edge detecting fuzzy neural networks with model-based examples
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A model-based method for training feedforward, backpropagation neural-like networks to produce edge images from data such as forward looking infrared and gray tone pictures is presented. The authors' approach is to train the network on a very small basis set of binary-valued window vectors which are first scored using the Sobel edge operator. Sobel scores are then used to select training vectors that have either crisp or fuzzy edge labels. This training scheme is independent of all real images. The method proposed is illustrated by comparing FF/BP edge images with those produced by the Sobel and Canny edge operators Author(s) Bezdek, J.C. Div. of Comput. Sci., Univ. of West Florida, Pensacola, FL, USA Kerr, D.Keywords
This publication has 7 references indexed in Scilit:
- Hierarchical artificial neural networks for edge enhancementPattern Recognition, 1993
- Endocardial boundary detection using a neural networkPattern Recognition, 1993
- Edge detection using a fuzzy neural networkPublished by SPIE-Intl Soc Optical Eng ,1992
- Artificial neural net learns the Sobel operators (and more)Published by SPIE-Intl Soc Optical Eng ,1991
- Edge detection by associative mappingPattern Recognition, 1989
- A Computational Approach to Edge DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Quantitative design and evaluation of enhancement/thresholding edge detectorsProceedings of the IEEE, 1979