Automatic detection of peculiar galaxies in large
datasets of galaxy images
L. Shamir. Journal of Computational Science, 3 (3):
181--189(2012)Scientific Computation Methods and Applications.
DOI: 10.1016/j.jocs.2012.03.004
Abstract
We propose an image analysis unsupervised learning
algorithm that can detect peculiar galaxies in datasets
of galaxy images. The algorithm first computes a large
set of calculated characteristics reflecting different
aspects of the visual content, and then weighs them
based on the σ of the values computed from the galaxy
images. The weighted Euclidean distance of each galaxy
image from the median is measured, and the peculiarity
of each galaxy is determined based on that distance.
Experimental results using irregular galaxy images show
that the method can effectively detect peculiar
galaxies. Code and data used in the experiments are
freely available.
%0 Journal Article
%1 shamir-detection-peculiar-galaxies-2012
%A Shamir, Lior
%D 2012
%J Journal of Computational Science
%K anomaly detection galaxy
%N 3
%P 181--189
%R 10.1016/j.jocs.2012.03.004
%T Automatic detection of peculiar galaxies in large
datasets of galaxy images
%U http://www.sciencedirect.com/science/article/pii/S1877750312000245
%V 3
%X We propose an image analysis unsupervised learning
algorithm that can detect peculiar galaxies in datasets
of galaxy images. The algorithm first computes a large
set of calculated characteristics reflecting different
aspects of the visual content, and then weighs them
based on the σ of the values computed from the galaxy
images. The weighted Euclidean distance of each galaxy
image from the median is measured, and the peculiarity
of each galaxy is determined based on that distance.
Experimental results using irregular galaxy images show
that the method can effectively detect peculiar
galaxies. Code and data used in the experiments are
freely available.
@article{shamir-detection-peculiar-galaxies-2012,
abstract = {We propose an image analysis unsupervised learning
algorithm that can detect peculiar galaxies in datasets
of galaxy images. The algorithm first computes a large
set of calculated characteristics reflecting different
aspects of the visual content, and then weighs them
based on the σ of the values computed from the galaxy
images. The weighted Euclidean distance of each galaxy
image from the median is measured, and the peculiarity
of each galaxy is determined based on that distance.
Experimental results using irregular galaxy images show
that the method can effectively detect peculiar
galaxies. Code and data used in the experiments are
freely available.},
added-at = {2016-07-12T19:24:18.000+0200},
author = {Shamir, Lior},
biburl = {https://www.bibsonomy.org/bibtex/278f665dfe2dcbe351a8d603938f27da8/mhwombat},
doi = {10.1016/j.jocs.2012.03.004},
interhash = {c1b67540489b482651ddb3c94e5eb54b},
intrahash = {78f665dfe2dcbe351a8d603938f27da8},
issn = {1877-7503},
journal = {Journal of Computational Science},
keywords = {anomaly detection galaxy},
note = {Scientific Computation Methods and Applications},
number = 3,
pages = {181--189},
timestamp = {2016-07-12T19:25:30.000+0200},
title = {Automatic detection of peculiar galaxies in large
datasets of galaxy images},
url = {http://www.sciencedirect.com/science/article/pii/S1877750312000245},
volume = 3,
year = 2012
}