| |
 |
| Paper: |
Advances in Automated Algorithms For Morphological Classification of Galaxies Based on Shape Features |
| Volume: |
314, Astronomical Data Analysis Software and Systems XIII |
| Page: |
617 |
| Authors: |
Goderya, S.; Andreasen, J.D.; Philip, N.S. |
| Abstract: |
Among the many celestial objects in the universe, galaxies offer insights as to how the universe was formed and is continuing to develop. The morphological classification of galaxies is important just for this reason. The challenge lies in classifying the estimated billions of galaxies that are in the universe, a very small amount of which are now being studied by various sky survey like the Hubble Deep Field and the Sloan Digital Sky Survey. The automated procedure described here uses an image enhancing technique, segmentation, shape feature extraction and a supervised artificial neural network to classify the galaxies. When trained to classify galaxies as E/S0 or S, the network is able to learn 98.3% of the galaxies correctly and identify 89.9% of galaxy images in a test set. The major challenge is in the development of robust and automated segmentation schemes. With manually threshold images and Difference Boosting Neutral Networks we were able to achieve considerable success in developing a supervised classifier capable of sorting galaxies into subclasses. |
|
|
|
|
|
