ARTEX: A Self-Organizing Architecture for Classifying Image Regions
Abstract
A self-organizing architecture is developed for image region classi(cid:173) fication. The system consists of a preprocessor that utilizes multi(cid:173) scale filtering, competition, cooperation, and diffusion to compute a vector of image boundary and surface properties, notably texture and brightness properties. This vector inputs to a system that incrementally learns noisy multidimensional mappings and their probabilities. The architecture is applied to difficult real-world image classification problems, including classification of synthet(cid:173) ic aperture radar and natural texture images, and outperforms a recent state-of-the-art system at classifying natural textures.
Cite
Text
Grossberg and Williamson. "ARTEX: A Self-Organizing Architecture for Classifying Image Regions." Neural Information Processing Systems, 1996.Markdown
[Grossberg and Williamson. "ARTEX: A Self-Organizing Architecture for Classifying Image Regions." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/grossberg1996neurips-artex/)BibTeX
@inproceedings{grossberg1996neurips-artex,
title = {{ARTEX: A Self-Organizing Architecture for Classifying Image Regions}},
author = {Grossberg, Stephen and Williamson, James R.},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {873-879},
url = {https://mlanthology.org/neurips/1996/grossberg1996neurips-artex/}
}