AAS 197, January 2001
Session 77. Galaxy Evolution II
Display, Wednesday, January 10, 2001, 9:30am-7:00pm, Exhibit Hall

[Previous] | [Session 77] | [Next]

[77.02] Using Neural Networks to Classify Digitized Images of Galaxies

S.N. Goderya (Illinois State U.), P.C. McGuire (U.Bielefeld)

Automated classification of Galaxies into Hubble types is of paramount importance to study the large scale structure of the Universe, particularly as survey projects like the Sloan Digital Sky Survey complete their data acquisition of one million galaxies. At present it is not possible to find robust and efficient artificial intelligence based galaxy classifiers. In this study we will summarize progress made in the development of automated galaxy classifiers using neural networks as machine learning tools. We explore the Bayesian linear algorithm, the higher order probabilistic network, the multilayer perceptron neural network and Support Vector Machine Classifier.

The performance of any machine classifier is dependant on the quality of the parameters that characterize the different groups of galaxies. Our effort is to develop geometric and invariant moment based parameters as input to the machine classifiers instead of the raw pixel data. Such an approach reduces the dimensionality of the classifier considerably, and removes the effects of scaling and rotation, and makes it easier to solve for the unknown parameters in the galaxy classifier. To judge the quality of training and classification we develop the concept of Mathews coefficients for the galaxy classification community. Mathews coefficients are single numbers that quantify classifier performance even with unequal prior probabilities of the classes.

If you would like more information about this abstract, please follow the link to http://www.phy.ilstu.edu/~goderya/vision.html. This link was provided by the author. When you follow it, you will leave the Web site for this meeting; to return, you should use the Back comand on your browser.

The author(s) of this abstract have provided an email address for comments about the abstract: goderya@phy.ilstu.edu

[Previous] | [Session 77] | [Next]