Abstract
This paper demonstrates how multi-layered neural networks can be used to obtain the relative depth variation of textured scenes. The system employed makes use of two differently focused images taken by a tele-centric imaging setup. The relative variation of blur of corresponding regions in the two images was used to calculate the relative depth. The neural network is used to predict the degree to which a particular region is blurred. To make the neural network predict blur irrespective of the texture of the scene, it was trained on highly textured fractal images.
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 subscriptionsReferences
Pentland, A., Darrell, T., Turk, M., Huang, W.: A simple, real-time range camera. In: IEEE Proceedings of Computer Vision and Pattern Recognition (CVPR), vol. 4(8), pp. 256–261, June 1989
Ens, J., Lawrence, P.: An investigation of methods for determining depth from defocus. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 15(12), 97–108 (1993)
Jong, S.M.: Depth from defocus using radial basis function networks. In: Proceedings of the 6th International Conference on Machine Learning and Cybernetics, vol. 4, pp. 1888–1893, August 2007
Pentland, A.P.: A new sense for depth of field. IEEE Trans. Pattern Anal. Mach. Intell. 9, 523–531 (1987)
Subbarao, M., Wei, T.C.: Depth from defocus and rapid auto focussing: a practical approach. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Champaign, pp. 773–776 (1992)
Joseph-Raj, A.N.: Accurate depth from defocus estimation with video-rate implementation. Ph.D. dissertation, School of Engineering, University of Warwick, Coventry (2009)
Rajagopalan, A.N., Chaudhuri, S.: Depth from Defocus: a Real Aperture Imaging Approach. Springer, New York (1999)
Watanabe, M., Nayar, S.K.: Telecentric optics for focus. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 19(12), 1360–1365 (1997)
Shapiro, L.G., Stockman, G.C.: Computer Vision, pp. 137, 150. Prentice Hall (2001)
Watanabe, M., Nayar, S.K.: Rational filters for passive depth from defocus. Int. J. Comput. Vision 27(3), 203–225 (1998)
Martin Fodslette Meiller: A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw. 6, 525–533 (1993). University of Aarhus
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Mandelbrot, B.B.: The Fractal Geometry of Nature. W. H. Freeman and Co, New York (1982)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Joseph, K., Joseph Raj, A.N. (2018). Reconstruction of 3-Dimensional Scenes Using Depth from Defocus and Artificial Neural Networks Trained on Fractals. In: Abraham, A., Cherukuri, A., Madureira, A., Muda, A. (eds) Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016). SoCPaR 2016. Advances in Intelligent Systems and Computing, vol 614. Springer, Cham. https://doi.org/10.1007/978-3-319-60618-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-60618-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60617-0
Online ISBN: 978-3-319-60618-7
eBook Packages: EngineeringEngineering (R0)