A method of complex background estimation in astronomical images

TL;DR

This paper introduces a new background estimation method for astronomical images that accurately handles complex structures and fluctuating backgrounds by removing small objects and interpolating missing pixels, outperforming existing techniques.

Contribution

The proposed method uniquely combines local neighborhood analysis and morphological distance transform, requiring no multiple tuning parameters and effectively extracting complex astronomical structures.

Findings

Higher accuracy compared to existing background estimators

Effective in challenging fluctuating backgrounds

Capable of removing various foreground structures

Abstract

In this paper, we present a novel approach to the estimation of strongly varying backgrounds in astronomical images by means of small objects removal and subsequent missing pixels interpolation. The method is based on the analysis of a pixel local neighborhood and utilizes the morphological distance transform. In contrast to popular background estimation techniques, our algorithm allows for accurate extraction of complex structures, like galaxies or nebulae. Moreover, it does not require multiple tuning parameters, since it relies on physical properties of CCD image sensors - the gain and the read-out noise characteristics. The comparison with other widely used background estimators revealed higher accuracy of the proposed technique. The superiority of the novel method is especially significant for the most challenging fluctuating backgrounds. The size of filtered out objects is tunable, therefore the algorithm may eliminate a wide range of foreground structures, including the dark current impulses, cosmic rays or even entire galaxies in deep field images.