Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.10.23.00
%2 sid.inpe.br/sibgrapi/2017/09.10.23.00.26
%T Galaxy image classification
%D 2017
%A Murrugarra-LLerena, Joseph Hans,
%A Hirata, Nina Sumiko Tomita,
%@affiliation Institute of Mathematics and Statistics of the University of São Paulo, São Paulo, Brazil
%@affiliation Institute of Mathematics and Statistics of the University of São Paulo, São Paulo, Brazil
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ
%8 Oct. 17-20, 2017
%S Proceedings
%I Sociedade Brasileira de Computação
%J Porto Alegre
%K galaxy classification, deep learning, convolutional neural networks.
%X Over the years, different methods based either on morphological features or on expert knowledge have been proposed to classify galaxies. The amount of data to be processed in large scale surveys poses a new challenge for the classification. In this preliminary study, we investigate machine learning methods for galaxy image classification. Specifically, we evaluate convolutional neural networks as tools to be used in the classification process. Different ways of using convolutional neural networks has been experimented to classify galaxies as elliptical or spiral. Classification accuracy around 90-91% for the Sloan Digital Sky Survey (SDSS) galaxy images has been achieved.
%@language en
%3 article.pdf


Close