Identification and classification of galaxies using a biologically-inspired neutral network

Recognition/Classification of galaxies is an important issue in the large-scale study of the Universe; it is not a simple task. According to estimates computed from the Hubble Deep Field (HDF), astronomers predict that the universe may potentially contain over 100 billion galaxies. Several techniques have been reported for the classification of galaxies. Parallel developments in the field of neural networks have come to a stage that they can participate well in the recognition of objects. Recently, the Pulse-Coupled Neural Network (PCNN) has been shown to be useful for image pre-processing. In this paper, we present a novel way to identify optical galaxies by presenting the images of the galaxies to a hierarchical neural network involving two PCNNs. The image is presented to the network to generate binary barcodes (one per iteration) of the galaxies; the barcodes are unique to the input galactic image. In the current study, we exploit this property to identify optical galaxies by comparing the signatures (binary barcode) from a corresponding database.