Automated Classification of Astronomical Objects in Multispectral Wide-Field Images

Olac Fuentes, Jorge de la Calleja

In this paper we present an automated method for classifying astronomical objects in multispectral wide-field images. The method is divided into three main tasks. The first one consists of locating and matching the objects in the multispectral images. In the second task we create a new representation for each astronomical object using its multispectral images, and also we find a set of features using principal component analysis. In the last task we classify the astronomical objects using neural networks, locally weighted linear regression and random forest. Preliminary results show that the method obtains over 93\% accuracy classifying stars and galaxies.

Subjects: 13.1 Discourse

Submitted: Feb 16, 2006


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.