Abstract
In this paper we investigate for two well-known machine learning methods, decision trees and neural networks, how they classify discrete images from their projections. As an example, we present classification results when the task is to guess the number of intensity values of the discrete image. Machine learning can be used in Discrete Tomography as a preprocessing step in order to choose the proper reconstruction algorithm or – with the aid of the knowledge acquired – to improve its accuracy. We also show how to design new evolutionary reconstruction methods that can exploit the information gained by machine learning classifiers.
This research was supported by the TÁMOP-4.2.2/08/1/2008-0008 program of the Hungarian National Development Agency, the European Union and the European Regional Development Fund. The work of M. Gara was also is supported by the European Union and co-funded by the European Social Fund under the project number TÁMOP-4.2.2/B-10/1-2010-0012. The work of P. Balázs was also supported by the János Bolyai Research Scholarship of the Hungarian Academy of Sciences and by the Hungarian Scientific Research Fund OTKA PD100950.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bäck, T., Fogel, D.B., Michalewicz, T. (eds.): Evolutionary Computation 1. Institute of Physics Publishing, Bristol and Philadelphia (2000)
Balázs, P.: Binary Tomography Using Geometrical Priors: Uniqueness and Reconstruction Results. PhD thesis at the University of Szeged, Szeged (2007), http://www.inf.u-szeged.hu/~pbalazs/research/bp_thesis_main.pdf
Balázs, P., Balogh, E., Kuba, A.: Reconstruction of 8-connected but not 4-connected hv-convex discrete sets. Disc. Appl. Math. 147, 149–168 (2005)
Balázs, P., Gara, M.: Decision Trees in Binary Tomography for Supporting the Reconstruction of hv-Convex Connected Images. In: Blanc-Talon, J., Bourennane, S., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2008. LNCS, vol. 5259, pp. 433–443. Springer, Heidelberg (2008)
Balázs, P., Gara, M.: An Evolutionary Approach for Object-Based Image Reconstruction Using Learnt Priors. In: Salberg, A.-B., Hardeberg, J.Y., Jenssen, R. (eds.) SCIA 2009. LNCS, vol. 5575, pp. 520–529. Springer, Heidelberg (2009)
Balogh, E., Kuba, A., Dévényi, C., Del Lungo, A.: Comparison of algorithms for reconstructing hv-convex discrete sets. Lin. Algebra and its Applications 339, 23–35 (2001)
Barcucci, E., Del Lungo, A., Nivat, M., Pinzani, R.: Medians of polyominoes: A property for the reconstruction. Int. J. Imaging Systems and Techn. 9, 69–77 (1998)
Batenburg, K.J.: An evolutionary algorithm for discrete tomography. Discrete Appl. Math. 151, 36–54 (2005)
Batenburg, K.J., Bals, S., Sijbers, J., Kuebel, C., Midgley, P.A., Hernandez, J.C., Kaiser, U., Encina, E.R., Coronado, E.A., Van Tendeloo, G.: 3D imaging of nanomaterials by discrete tomography. Ultramicroscopy 109(6), 730–740 (2009)
Batenburg, K.J., Kosters, W.A.: A Neural Network Approach to Real-Time Discrete Tomography. In: Reulke, R., Eckardt, U., Flach, B., Knauer, U., Polthier, K. (eds.) IWCIA 2006. LNCS, vol. 4040, pp. 389–403. Springer, Heidelberg (2006)
Batenburg, K.J., Van Aarle, W., Sijbers, J.: A semi-automatic algorithm for grey level estimation in tomography. Pattern Recognition Letters 32, 1395–1405 (2011)
Baumann, J., Kiss, Z., Krimmel, S., Kuba, A., Nagy, A., Rodek, L., Schillinger, B., Stephan, J.: Discrete tomography methods for nondestructive testing. In: [21], pp. 303–331 (2007)
Brunetti, S., Daurat, A.: An algorithm reconstructing convex lattice sets. Theor. Comput. Sci. 304, 35–57 (2003)
Brunetti, S., Del Lungo, A., Del Ristoro, F., Kuba, A., Nivat, M.: Reconstruction of 4- and 8-connected convex discrete sets from row and column projections. Lin. Alg. Appl. 339, 37–57 (2001)
Castiglione, G., Frosini, A., Restivo, A., Rinaldi, S.: A Tomographical Characterization of L-Convex Polyominoes. In: Andrès, É., Damiand, G., Lienhardt, P. (eds.) DGCI 2005. LNCS, vol. 3429, pp. 115–125. Springer, Heidelberg (2005)
Chrobak, M., Dürr, C.: Reconstructing hv-convex polyominoes from orthogonal projections. Inform. Process. Lett. 69(6), 283–289 (1999)
Gara, M., Tasi, T.S., Balázs, P.: Learning connectedness and convexity of binary images from their projections. Pure Math. and Appl. 20, 27–48 (2009)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA Data Mining Software: An Update. SIGKDD Explorations 11(1), 10–18 (2009)
Herman, G.T.: Fundamentals of Computerized Tomography: Image reconstruction from projections. Springer, Heidelberg (2009)
Herman, G.T., Kuba, A. (eds.): Discrete Tomography: Foundations, Algorithms and Applications. Birkhäuser, Boston (1999)
Herman, G.T., Kuba, A. (eds.): Advances in Discrete Tomography and its Applications. Birkhäuser, Boston (2007)
Kak, A.C., Slaney, M.: Principles of Computerized Tomographic Imaging. IEEE Press, New York (1999)
Kiss, Z., Rodek, L., Kuba, A.: Image reconstruction and correction methods in neutron and X-ray tomography. Acta Cybernetica 17(3), 557–587 (2006)
Kuba, A., Ruskó, L., Kiss, Z., Nagy, A.: Discrete Reconstruction Techniques. Electronic Notes in Discrete Math. 20, 385–398 (2005)
Metropolis, N., Rosenbluth, A., Rosenbluth, M., Teller, E.: Equation of state calculation by fast computing machines. J. Chem. Phys. 21, 1087–1092 (1953)
Mitchell, T.M.: Machine Learning. McGraw Hill, New York (1997)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Valenti, C.: A genetic algorithm for discrete tomography reconstruction. Genet. Program Evolvable Mach. 9, 85–96 (2008)
Van Aert, S., Batenburg, K.J., Rossell, M.D., Erni, R., Van Tendeloo, G.: Three-dimensional atomic imaging of crystalline nanoparticles. Nature 470, 374–377 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gara, M., Tasi, T.S., Balázs, P. (2012). Machine Learning as a Preprocessing Phase in Discrete Tomography. In: Köthe, U., Montanvert, A., Soille, P. (eds) Applications of Discrete Geometry and Mathematical Morphology. WADGMM 2010. Lecture Notes in Computer Science, vol 7346. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32313-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-32313-3_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32312-6
Online ISBN: 978-3-642-32313-3
eBook Packages: Computer ScienceComputer Science (R0)