Abstract
A feed-forward artificial neural network has been implemented to the problem of removing cosmic-ray hits (CRH) from CCD images. The results of a number of tests demonstrate the effectiveness of this method especially for undersampled stellar profiles. The problem of optimal and low price preparing of training data, which could enable real-time or at least fast post-processing filtering out of CRH is discussed. The training and test ensembles were composed of a number of synthetic stellar profiles involving different S/N ratios and CRH images taken from real data. Certain aspects of the network’s architecture and its training efficiency for different modes of the back-propagation procedure as well as for the pre-process normalization of data have been examined. It is shown that for training set composed of stellar images and CRH at a ratio of 1:2 recognition can reach 99% in the case of stars and 96% for CRH. To determine the extent to which the cognition power of a network trained using an ensemble of circular symmetric stellar profiles of a given radius can be generalised the test data included stellar profiles of different radii, as well as elongated profiles. The goal was to mimic temporal changes in seeing as well as such problems as image defocusing, the lack of isoplanatism and improper sideral tracking of a telescope. The experiments provided us with the conclusion that for S/N > 10 excellent classification property is maintained in cases where the change in the radius of a circular profile is up to 30%, as well as for elongated profiles where the longest dimension is almost double that of the shortest one. Moreover, the generalization capability has been investigated for test images of synthetic pairs of overlapping stars with different distances between components. Almost 99% recognition efficiency was achieved even if the separation was nearly three times the radius of the stellar profile, a case when two stars could be analyzed by appropriate software as separate objects. The example of removal of CRH from real CCD images is presented to give an idea of how an algorithm based on a neural network can work in practice. The result of such an experiment appears fully consistent with the conclusions drawn from the tests made on synthetic data.
Similar content being viewed by others
References
Bazell, D., Peng, Y.: A comparison of neural network algorithms and preprocessing methods for star–galaxy discrimination. Astrophys. J. Suppl. Ser. 116, 47–55 (1998)
Bazell, D., Miller, D.J.: Class discovery in galaxy classification. Astron. J. 618, 723–732 (2005)
Belokurov, V., Evans, N.W., Le Du, Y.: Light-curve classification in massive variability surveys—I. Microlensing. Mon. Not. R. Astron. Soc. 341, 1373–1384 (2003)
Buonanno, R., Iannicola, G.: Stellar photometry with big pixels. Publ. Astron. Soc. Pac. 101, 294–301 (1989)
El-Bassuny Alawy, A., et al.: CCD image identification: An artificial neural approach. In: HIPPARCOS and the Luminosity Calibration of the Nearer Stars, 24th meeting of the IAU, Joint Discussion 13, Manchester, August 2000
Feeney, S.M., Belokurov, V., Evans, N.W., An, J., Hewett, P.C., Bode, M., Darnley, M., Kerins, E., Baillon, P., Carr, B.J., Paulin-Henriksson, S., Gould, A.: Automated detection of classical novae with neural networks. Astron. J. 130, 84–94 (2005)
Gulati, R.K., Gupta, R., Rao, N.K.: A comparison of synthetic and observed spectra for G-K dwarfs using artificial neural networks. Astron. Astrophys. 322, 933–937 (1997)
Hinton, G.E., Sejnowski, T.J.: Learning and relearning in Boltzmann machines. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Exploration in the Microstructure of Cognition, pp. 282–317. MIT, Cambridge (1986)
Holtzman, J., Hester, J.J., Casertano, S., Trauger, J.T., Watson, A.M., Ballester, G.E., Burrows, C.J., Clarke, J.T., Crisp, D., Evans, R.W., Gallagher III, J.S., Griffiths, R.E., Hoessel, J.G., Matthews, L.D., Mould, J.R., Scowen, P.A., Stapelfeldt, K.R., Westphal, J.A.: The performance and calibration of WFPC2 on the Hubble Space Telescope. Publ. Astron. Soc. Pac. 107, 156–178 (1995)
Klusch, M., Napiwotzki, R.: HNS: a hybrid neural system and its use for the classification of stars. Astron. Astrophys. 276, 309–319 (1993)
Lahav, O., Naim, A., Sodré, Jr, L., Storrie-Lombardi, M.C.: Neural computation as a tool for galaxy classification: methods and examples. Mon. Not. R. Astron. Soc. 283, 207–221 (1996)
Lauer, T.R.: The photometry of undersampled point-spread functions. Publ. Astron. Soc. Pac. 111, 1434–1443 (1999)
Martens, T.: Practical neural networks recipes in C++. Academic, New York (1993)
Moffat, A.F.J.: A theoretical investigation of focal stellar images in the photographic emulsion and application to photographic photometry. Astron. Astrophys. 3, 455–461 (1969)
Murtagh, F.D.: Cosmic ray discrimination on HST/PC images: Object recognition-by-example. In: Worrall, D.M., Biemesderfer, C., Barnes, J. (eds.) Astronomical Data Analysis Software and Systems I. ASP Conf. Ser. 25, pp. 265–273 (1992)
Odewahn, S.C., Stockwell, E.B., Pennington, R.L., Humphreys, R.M., Zumach, W.A.: Automated star/galaxy discrimination with neural networks. Astron. J. 103, 318–331 (1992)
Philip, N.S., Wadadekar, Y., Kembhavi, A., Joseph, K.B.: A difference boosting neural network for automated star–galaxy classification. Astron. Astrophys. 385, 1119–1126 (2002)
Plaut, D., Nowlan, S., Hinton, G.: Experiments on learning by back propagation. Technical Report CMU-CS-86-126, Department of Computer Science, Carnegie Mellon University, Pittsburgh (1986)
Racine, R.: The telescopic point-spread function. Publ. Astron. Soc. Pac. 108, 699–705 (1996)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(9), 533–536 (1986)
Storrie-Lombardi, M.C., Lahav, O., Sodré, Jr, L., Storrie-Lombardi, L.J.: Morphological classification of galaxies by artificial neural networks. Mon. Not. R. Astron. Soc. 259, 8–12 (1992) (Short Communication)
Tagliaferri, R., Ciaramella, A., Milano, L., Barone, F., Longo, G.: Spectral analysis of stellar light curves by means of neural networks. Astron. Astrophys. Suppl. Ser. 137, 391–405 (1999)
Willemsen, P.G., Hilker, M., Kayser, A., Bailer-Jones, C.A.L.: Analysis of medium resolution spectra by automated methods—application to M55 and ω Centauri. Astron. Astrophys. 436, 379–390 (2005)
Windhorst, R.A., Franklin, B.E., Neuschaefer, L.W.: Removing cosmic-ray hits from multiorbit HST wide field camera images. Publ. Astron. Soc. Pac. 106, 798–806 (1994)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Waniak, W. Removing cosmic-ray hits from CCD images in real-time mode by means of an artificial neural network. Exp Astron 21, 151–168 (2006). https://doi.org/10.1007/s10686-007-9079-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10686-007-9079-0