Abstract
In this paper we propose a new iterative algorithm for image reconstruction from projections problem. The reconstruction problem is reformulated as a system of linear equations with a Toeplitz-block-Toeplitz coefficient matrix. The structure of the matrix enables us to use efficient methods for solving the system. We investigate the use of gradient methods benefiting from fast FFT-based matrix-vector multiplication for minimizing the quadratic form objective function. We present and compare simulation results for the algorithm with different methods for step size selection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cierniak, R.: X-Ray Computed Tomography in Biomedical Engineering. Springer, London (2011)
Laskowski, Ł.: Hybrid-maximum neural network for depth analysis from stereo-image. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS, vol. 6114, pp. 47–55. Springer, Heidelberg (2010)
Laskowski, L.: A novel continuous dual mode neural network in stereo-matching process. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS (LNAI), vol. 6354, pp. 294–297. Springer, Heidelberg (2010)
Laskowski, Ł.: Objects auto-selection from stereo-images realised by self-correcting neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS (LNAI), vol. 7267, pp. 119–125. Springer, Heidelberg (2012)
Laskowski, L.: A novel hybrid-maximum neural network in stereo-matching process. Neural Computing and Applications 23(7-8), 2435–2450 (2013)
Cichocki, A., Unbehauen, R., Lendl, M., Weinzierl, K.: Neural networks for linear inverse problems with incomplete data especially in application to signal and image reconstruction. Neurocomputing 8, 7–41 (1995)
Cierniak, R.: A 2D approach to tomographic image reconstruction using a Hopfield-type neural network. International Journal Artificial Intelligence in Medicine 43, 113–125 (2008)
Cierniak, R.: A new approach to image reconstruction from projections problem using a recurrent neural network. Applied Mathematics and Computer Science 18, 147–157 (2008)
Cierniak, R.: A novel approach to image reconstruction problem from fan-beam projections using recurrent neural network. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 752–761. Springer, Heidelberg (2008)
Cierniak, R.: New neural network algorithm for image reconstruction from fan-beam projections. Neurocomputing 72, 3238–3244 (2009)
Barzilai, J., Borwein, J.M.: Two point step size gradient method. IMA J. Numer. Anal. 8, 141–148 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Lorent, A., Cierniak, R., Dobosz, P., Rebrova, O. (2014). A New Image Reconstruction from Projections Algorithm. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2014. Lecture Notes in Computer Science(), vol 8467. Springer, Cham. https://doi.org/10.1007/978-3-319-07173-2_62
Download citation
DOI: https://doi.org/10.1007/978-3-319-07173-2_62
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07172-5
Online ISBN: 978-3-319-07173-2
eBook Packages: Computer ScienceComputer Science (R0)