Principal Component Analysis Neural Network Hybrid Classification Approach for Galaxies Images
This article presents an automatic hybrid approach for galaxies images classification based on principal component analysis (PCA) neural network and moment-based features extraction algorithms. The proposed approach is consisted of four phases; namely image denoising, feature extraction, reduct generation, and classification phases. For the denoising phase, noise pixels are removed from input images, then input galaxy image is normalized to a uniform scale and Hu seven invariant moment algorithm is applied to reduce the dimensionality of the feature space during the feature extraction phase. Subsequently, for reduct generation phase, attributes in the information system table that is more important to the knowledge is generated as a subset of attributes. Rough set is used as feature reduction approach. The subset of attributed, which is called a reduct, is fully characterizing the knowledge in the database. Finally, during the classification phase, principal component analysis neural network algorithm is utilized for classifying the input galaxies images into one of four obtained source catalogue types. Experimental results showed that combining PCA and rough set as feature reduction techniques along with invariant moments for feature extraction provided better classification results than having no rough set feature reduction technique applied. It is also concluded that a small set of features is sufficient to classify galaxy images and provide a fast classification.
KeywordsPCA neural network rough set moment invariant fisher score galaxy images
Unable to display preview. Download preview PDF.
- 2.Lahav, O.: Artificial neural networks as a tool for galaxy classification. In: Data Analysis in Astronomy, Erice, Italy (1996)Google Scholar
- 3.Pettini, M., Christensen, L., D’Odorico, S., Belokurov, V., Evans, N.W., Hewett, P.C., Koposov, S., Mason, E., Vernet, J.: CASSOWARY20: a wide separation Einstein Cross identified with the X-shooter spectrograph. Monthly Notices of the Royal Astronomical Society 402, 2335–2343 (2010)CrossRefGoogle Scholar
- 4.Frei, Z.: Zsolt Frei Galaxy Catalog, Princeton University, Department of Astrophysical Sciences (1999), http://www.astro.princeton.edu/frei/catalog.htm (retrieved 2002)
- 6.Mohamed, M.A., Atta, M.M.: Automated Classification of Galaxies Using Transformed Domain Features. IJCSNS International Journal of Computer Science and Network Security 10(2) (2010)Google Scholar
- 8.Duda, Stork, D.G.: Pattern Classification. Wiley-Interscience Publication (2001)Google Scholar
- 9.Hsieh, W.W.: Nonlinear Principal Component Analysis by Neural Network. Univeristy of British Columbia, Appeared in Tellus 53A, 559–615 (2001)Google Scholar
- 10.Jahanbani, A., Karimi, H.: A new Approach for Detecting Intrusions Based on the PCA Neural Networks. J. Basic. Appl. Sci. Res. 2(1), 672–679 (2012)Google Scholar
- 12.Pawlak, Z.: Rough sets – Theoretical aspects of reasoning about data. Kluwer (1991)Google Scholar
- 14.Polkowski, L.: Rough Sets: Mathematical Foundations. Physica-Verlag (2003)Google Scholar
- 15.Frei, Z.: Zsolt Frei Galaxy Catalog, Princeton University, Department of Astrophysical Sciences (1999), http://www.astro.princeton.edu/frei/catalog.htm (retrieved 2002)
- 16.Banerji, M., Lahav, O., Lintott, C.J., Abdala, F., Schawinski, K., Bamford, S., Andreescu, D., Raddick, M., Murray, P., Jordan, M., Slosar, A., Szalay, A., Thomas, D., Vandenberg, J.: Galaxy Zoo: reproducing galaxy morphologies via machine learning. Monthly Notices of the Royal Astronomical Society 406, 342–353 (2010)CrossRefGoogle Scholar