Skip to content

trakhimov/galaxy-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

Galaxy Classification

Astronomers classify galaxies based on their visual appearance and the presence of certain features, and their shape. The most popular classification scheme is the Hubble Classification Scheme.

There are three broad categories of galaxy: Spirals, Lenticulars and Ellpticals. Also there are irregular galaxies which do not fit into the Hubble Classification Scheme. On a subordinate level, galaxies may or may not features such as spiral arms, bulges, bars. The apperance of a galaxy is also changed by its apparent inclination, varying between being "face-on" and "edge-on".

We aim to classify galaxies using their broader shape and their finer features.

Relevant Papers

  1. Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey
  2. Machine and Deep Learning Applied to Galaxy Morphology - A Comparative Study
  3. A CATALOG OF DETAILED VISUAL MORPHOLOGICAL CLASSIFICATIONS FOR 14,034 GALAXIES IN THE SLOAN DIGITAL SKY SURVEY
  4. Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
  5. Galaxy Zoo: reproducing galaxy morphologies via machine learning
  6. Galaxy Classification Using Transfer Learning and Ensemble of CNNs With Multiple Colour Spaces
  7. Rotation-invariant convolutional neural networks for galaxy morphology prediction

About

Classification of Images of Astronomical Objects from Sloan Digital Sky Survey

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published