Automated Source Classification Using a Kohonen Network

Open Access

10 October 1995

journal article
research article
Published by American Astronomical Society in The Astrophysical Journal

Vol. 452 (1) , L77
https://doi.org/10.1086/309697

Abstract

We report progress in the development of an automatic star/galaxy classifier for processing images generated by large galaxy surveys like APM. Our classification method is based on neural networks using the Kohonen Self-organizing Map approach. Our method is novel, since it does not need supervised learning, i.e., the human factor, in training. The analysis presented here concentrates on separating point sources (stars) from extended ones. Using simple numerical experiments, we compare our method of image classification to the more traditional (PSF-fitting) approach of DAOFIND.

Keywords

All Related Versions

Version 1, 1995-08-04, ArXiv

This publication has 7 references indexed in Scilit:

Galaxies, Human Eyes, and Artificial Neural Networks
Science, 1995
Morphological Classification of galaxies by Artificial Neural Networks
Monthly Notices of the Royal Astronomical Society, 1992
Automated star/galaxy discrimination with neural networks
The Astronomical Journal, 1992
The self-organizing map
Proceedings of the IEEE, 1990
The Edinburgh/Durham Southern Galaxy Catalogue - II. Image classification and galaxy number counts
Monthly Notices of the Royal Astronomical Society, 1989
Self-Organization and Associative Memory
Published by Springer Nature ,1989
An introduction to computing with neural nets
IEEE ASSP Magazine, 1987