2
on LSBG samples have been identified and investigated.
Matthews & Gao (2001) selected eight nearby, edge-on
LSBGs using the National Radio Astronomy Observa-
tory 12 m telescope and made CO observations of them.
Bizyaev & Kajsin (2004) selected a sample of 11 edge-
on galaxies from the faintest surface-brightness galaxies
in the Revised Catalog of Flat Galaxies (Karachentsev
et al. 1999). Matthews et al. (2005) selected 15 late-
type edge-on LSBGs with the IRAM 30 m telescope and
made CO observations. Caldwell & Bergvall (2006) se-
lected a sample of 970 edge-on LSBGs from the SDSS
DR4 data to study the galactic halo emission. Bergvall
et al. (2010) selected a sample of 1510 edge-on LSBGs in
the SDSS DR5 database to explain the “red halo” phe-
nomenon. Bizyaev et al. (2014) obtained 5747 edge-on
galaxies by parameter cutting and visual inspection of
SDSS DR7 (Abazajian et al. 2009). Du et al. (2017) se-
lected a sample of 12 edge-on LSBGs from the catalog of
Bizyaev et al. (2014) and made spectral observations of
them. He et al. (2020) selected a sample of 281 edge-on
LSBG candidates from the catalog obtained by cross-
matching SDSS DR7 with 40% of the Arecibo Legacy
Fast ALFA survey (ALFALFA; Giovanelli 2007) and an-
alyzed the optical and HI properties of the sample.
In previous studies, edge-on LSBGs have primarily
been obtained by selecting a central surface brightness
and axis ratio. The process of selecting edge-on LSBG
samples often involved complicated steps. In addition,
the inclusion of skylight contamination in faint galaxies
(Du et al. 2015) and the sensitivity of edge-on galax-
ies to initial parameters of the profile fitting (He et al.
2020) have further complicated the selection process, re-
quiring more manual intervention. Consequently, it be-
comes challenging to conduct a large-scale, automated
search for edge-on LSBGs across sky surveys.
Some machine learning methods have been applied to
identify and classify LSBGs to improve efficiency. Tra-
ditional machine-learning methods such as support vec-
tor machines (SVMs; Platt 1998) and random forest
(Breiman 2001) have been employed for LSBG selec-
tion. However, their accuracy in identifying LSBGs is
only around 50%, often necessitating a combination with
manual inspection (Greco et al. 2018; Tanoglidis et al.
2021b). The low efficiency of these methods in identi-
fying LSBGs is primarily due to using galaxy parame-
ters as training data. The faint surface brightness and
complex morphologies of LSBGs make their features dif-
ficult to be accurately extracted, leading to significant
recognition errors in the identification process. Fortu-
nately, in recent years, deep learning has made signifi-
cant advancements, greatly enhancing the image analy-
sis capabilities of machine-learning models. Neural net-
works, with their powerful feature extraction capabil-
ities, can learn galaxy features directly from images,
thereby enhancing the ability to identify LSBGs. For ex-
ample, by using convolutional neural networks (CNNs;
LeCun et al. 1998) to differentiate between LSBG images
and artifact images, the model named DeepShadows
achieved an accuracy of 92% (Tanoglidis et al. 2021a).
The premise of using cutout galaxy images to identify
LSBGs is that a galaxy list has already been success-
fully obtained. However, some faint galaxies are chal-
lenging to be accurately recognized, especially irregu-
lar or peculiar galaxies. Additionally, there may be
instances where the components of a large galaxy are
mistakenly identified as multiple small galaxies, lead-
ing to errors in the subsequent identification of LSBGs.
Deep-learning-based object detection provides a poten-
tial approach for automatically identifying LSBGs. This
technique enables the direct recognition and localization
of multiple objects from a large image. For example, Yi
et al. (2022) developed an automated detection model
to mainly identify face-on LSBGs in SDSS images and
achieved a detection accuracy of 92%.
In this study, we aim to detect wide-area edge-on LS-
BGs from SDSS DR16 (Ahumada et al. 2020). Initially,
we selected edge-on LSBG candidates using photomet-
ric parameters (expAB g ≤ 0.3 or expAB r ≤ 0.3, µ
0,B
≥ 22 mag arcsec
−2
) and obtained 875,993 candidates.
However, by examining a subsample of 500 sources, we
found that more than half of the samples do not exhibit
the morphology of edge-on LSBGs, but rather dense
stellar streams, star wings of bright stars, galaxies of
nonelongated shape, or irregular morphology. Obtaining
true LSBGs requires time-consuming manual inspection
of candidates. In this study, we automate the detec-
tion of edge-on LSBGs using both object detection and
anomaly detection techniques. The constructed object
detection model was utilized to automatically identify
edge-on LSBGs from SDSS field images, providing both
the classification and location of these galaxies.
The layout of this paper is as follows. Section 2 in-
troduces the training and test samples used for build-
ing our object detection model. The development of
the detection model is described in Section 3. In Sec-
tion sec:searching, we present detection results in SDSS
DR16 and the process of purifying the candidates. In
Section 5, we introduce the properties of the candidate
LSBGs. We summarize and conclude our study in Sec-
tion 6.
2. DATA PREPARATION
In this study, we used an edge-on LSBG sample set
from He et al. (2020) to build an object detection