Automatic morphological classification of galaxy images

TL;DR

This paper presents a supervised learning algorithm that automatically classifies galaxy images into categories like spiral, elliptical, and edge-on with high accuracy, utilizing feature selection and weighted nearest neighbor classification.

Contribution

It introduces a novel automated classification method for galaxy images that combines feature selection with a weighted nearest neighbor approach, achieving around 90% accuracy.

Findings

Achieved ~90% classification accuracy on Galaxy Zoo images.

Demonstrated effectiveness of Fisher score-based feature selection.

Provided open-source implementation for broader use.

Abstract

We describe an image analysis supervised learning algorithm that can automatically classify galaxy images. The algorithm is first trained using a manually classified images of elliptical, spiral, and edge-on galaxies. A large set of image features is extracted from each image, and the most informative features are selected using Fisher scores. Test images can then be classified using a simple Weighted Nearest Neighbor rule such that the Fisher scores are used as the feature weights. Experimental results show that galaxy images from Galaxy Zoo can be classified automatically to spiral, elliptical and edge-on galaxies with accuracy of ~90% compared to classifications carried out by the author. Full compilable source code of the algorithm is available for free download, and its general-purpose nature makes it suitable for other uses that involve automatic image analysis of celestial objects.