[Previous] | [Session 7] | [Next]
S. Goderya, S. Lolling, R. Ahmed (Illinois State U.)
The morphology of galaxies is an important issue in the large scale study of the Universe. Recent pictures from the Hubble Deep Field (HDF) project and initiation of several large scale sky surveys is producing an ever growing extra-galactic database. One of the challenges facing astronomers today is in the automated identification and classification of galaxies in these databases. Fortunately, recent advances in computer vision and artificial intelligence technology can now be put to practical use in solving this problem. In this poster we describe three variation of a computational scheme to build an automatic galaxy classifier. Our concentration is on the computational scheme that utilizes shape features extracted by using computer vision techniques and a classifier that is built upon artificial neural networks. This method of classification has not been fully explored in the past. We report here a prototype model and our effort to embark on a full scale study.
If the author provided an email address or URL for general inquiries, it is a
s follows:
http://www.phy.ilstu.edu/~goderya/vision.html