Automatic approach to solve the morphological galaxy classification problem using the sparse representation technique and dictionary learning

Abstract

The observation of celestial objects in the sky is a practice that helps astronomers to understand the way in which the Universe is structured. However, due to the large number of observed objects with modern telescopes, the analysis of these by hand is a difficult task. An important part in galaxy research is the morphological structure classification based on the Hubble sequence. In this research, we present an approach to solve the morphological galaxy classification problem in an automatic way by using the Sparse Representation technique and dictionary learning with K-SVD. For the tests in this work, we use a database of galaxies extracted from the Principal Galaxy Catalog (PGC) and the APM Equatorial Catalogue of Galaxies obtaining a total of 2403 useful galaxies. In order to represent each galaxy frame, we propose to calculate a set of 20 features such as Hu's invariant moments, galaxy nucleus eccentricity, gabor galaxy ratio and some other features commonly used in galaxy classification. A stage of feature relevance analysis was performed using Relief-f in order to determine which are the best parameters for the classification tests using 2, 3, 4, 5, 6 and 7 galaxy classes making signal vectors of different length values with the most important features. For the classification task, we use a 20-random cross-validation technique to evaluate classification accuracy with all signal sets achieving a score of 82.27 % for 2 galaxy classes and up to 44.27 % for 7 galaxy classes.

A galaxy classification grid that better recognises early-type galaxy morphology

“…Sedmak & Lamas 1981;Huertas-Company et al 2015). Examples of this Machine Learning (de la Calleja & Fuentes 2004;Bazell & Miller 2005;Shamir 2009;Barchi et al 2019) include Support Vector Machines, statistical learning methods such as Classification Trees with Random Forest (CTRF) and Neural Networks (Huertas-Company et al 2008;Diaz-Hernandez et al 2016;Sreejith et al 2018;Sultanova 2018), and enhanced brain storm optimization techniques (Ibrahim et al 2018). Beck et al (2018) describe how the preferably-large training sets for machine learning can effectively be provided by citizen scientists.…”

Learning sparse representations on the sphere

“…Among them, sparse Dictionary Learning (DL) techniques (Engan et al 1999a;Aharon et al 2006a) have been proposed to design a dictionary directly from the data, in such a way that the data can be sparsely represented in that dictionary. DL has been used in astronomy for image denoising (Beckouche et al 2013), stellar spectral classification (Díaz-Hernández et al 2014) and morphological galaxy classification (Diaz-Hernandez et al 2016).…”

Fractal dimension analysis for automatic morphological galaxy classification

“…Recently, some significant works have been presented using new approaches. For example, the Sparse Representation technique and dictionary learning [10], and deep neural networks [11].…”