Galaxy Zoo Talk

Computer classifies SDSS galaxies as well as GZ1!

  • JeanTate by JeanTate

    "Computer-generated visual morphology catalog of ~3,000,000 SDSS galaxies", by Evan Kuminski and Lior Shamir appeared on astro-ph yesterday (link to abstract). Here's the abstract:

    We applied computer analysis to classify the broad morphological type of ~3,000,000 SDSS galaxies. The catalog provides for each galaxy the DR8 object ID, right ascension, declination, and the certainty of the automatic classification to spiral or elliptical. The certainty of the classification allows controlling the accuracy of a subset of galaxies by sacrificing some of the least certain classifications. The accuracy of the catalog was tested using galaxies that were classified by the manually annotated Galaxy Zoo catalog. The results show that the catalog contains ~900,000 spiral galaxies and ~600,000 elliptical galaxies with classification certainty that has a statistical agreement rate of ~98% with Galaxy Zoo debiased 'superclean' dataset. That also demonstrates the ability of computers to turn large datasets of galaxy images into structured catalogs of galaxy morphology. The catalog can be downloaded at this http URL The image analysis software that was used to create the catalog is also publicly available.

    Posted

  • Ghost_Sheep_SWR by Ghost_Sheep_SWR

    So this might even be of use for GZ.

    When using this analysis software before creating a classifying dataset of galaxies it would be possible to omit the 'superclean' ones, and mostly use the 'difficult', or more interesting, galaxies?

    (Impressive btw)

    Posted