<title>Classification of optical galaxies using a PCNN</title>

Abstract

Hubbies pioneering discovery of the distance to the Andromeda galaxy opened the frontiers of extragalactic research.According to estimates computed from the Hubble Deep Field, astronomers predict that the universe may potentially contain over 50 billion galaxies. RecognitionlClassification of galaxies is an important issue in the large-scale study of the Universe and is not a simple task. Several techniques have been reported for the classification of galaxies. Artificial neural networks are being successfully used for classification in various applications. Recently, the Pulse-Coupled Neural Network (PCNN) has been shown to be useful for image pre-processing. When a digital image is applied to the input of a PCNN, the network groups image pixels based on spatial proximity and brightness similarity. A time signal can be obtamed by computing the number of "on pixels" for each iteration; the time signal being an encoded one-dimensional signature of a two-dimensional image. There is a one-to-one correspondence between images and their time signatures. In the current study, we exploit this property to obtain time signatures of optical galaxies. Our results on spirals, ellipticals and irregulars are very promising and the work is being extended towards the development of an efficient and robust computer automated classifier.

Image Processing Using Pulse-Coupled Neural Networks

“…Several authors have reported work along this line [see Refs. 28-37 in [99]]. The techniques studied include the use of statistical model fitting, fuzzy algebra, decision tree, PCA, and wavelet-based image analysis.…”

“…Some work has been reported on the use of artificial neural networks for automatic morphological classification of galaxies; using feed-forward neural network, self-organizing maps, computer vision technique -see Refs. 32-34 in [99]. These techniques, however, require extensive training, hence are computationally demanding and may not be appropriate for the classification of a large number of galaxies.…”

“…These techniques, however, require extensive training, hence are computationally demanding and may not be appropriate for the classification of a large number of galaxies. A galaxy classifier/identifier using PCNN has also been reported [99,106]; initial results of which are promising. These authors have been able to classify galaxies according to an index parameter obtained from the time signature of the galaxies.…”