Abstract
I present some of the research activities of my group in Vision as a Grand Challenge problem whose solution is estimated to need the power of Tflop/s computers. Visual information representations which are motivated by the function of the primary visual cortex are computed. In the case of simple objects such as convex polygons, these representations allow straightforward interpretation for object recognition. Lower dimension representations which are used to simplify the problem of comparing input to prestored information have limitations. Optical flow methods applied to complete representations are studied as a possible solution to this problem. The automatic identification of persons by a face image is used as a touchstone for the proposed methods.
Preview
Unable to display preview. Download preview PDF.
References
Grand Challenges: High Performance Computing and Communications, The FY 1992 U.S. Research and Development Program.
N. Petkov, T. Lourens and P. Kruizinga: “Lateral inhibition in cortical filters”, Proc. of Int. Conf. on Digital Signal Processing and Int. Conf. on Computer Applications to Engineering Systems, July 14–16, 1993, Nicosia, Cyprus, pp. 122–129.
N. Petkov, T. Lourens and P. Kruizinga: “Orientation competition in cortical filters — An application to face recognition”, Comp. Sci. in The Netherlands 1993, Nov. 9–10, 1993, Utrecht (Stichting Math. Centrum: Amsterdam, 1993) pp.285–296.
D. Hubel and T. Wiesel: “Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex”, J. Physiol.(London), 1962, vol. 160, pp. 106–154.
J.P. Jones and L.A. Palmer: “An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex”, Journal of Neurophysiology, Vol.58 (1987) pp. 1233–1258.
J.G. Daugman: “Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression”, IEEE Trans. on Acoustics, Speech and Signal Processing, Vol.36 (1988) No. 7, pp. 1169–1179.
N. Petkov, P. Kruizinga and T. Lourens: “Biologically Motivated Approach to Face Recognition”, Proc. International Workshop on Artificial Neural Networks, June 9–11, 1993, Sitges (Barcelona), Spain (Berlin: Springer Verlag, 1993) pp.68–77
N. Petkov and T. Lourens: “Human Visual System Simulations — An Application to Face Recognition”, in H. Dedieu (ed.) Proc. 1993 European Conf. on Circuit Theory and Design, Aug. 30–Sept. 3, 1993, Davos, Switzerland (Amsterdam: Elsevier Sci. Publ., 1993) pp.821–826.
N. Petkov and T. Lourens: “Interacting cortical filters for object recognition”, Proc. of Asian Conference on Computer Vision, Nov. 23–25, 1993, Osaka, Japan
T. Lourens, N. Petkov and P. Kruizinga: “Large scale natural vision simulations”, Proc. High Performance Computing and Networking 93 Conference, 17–19 May, Amsterdam (Amsterdam: Elsevier Sci. Publ., 1994, in print)
P. Kruizinga, N. Petkov: “Optical flow applied to person identification”, in J.C. Zuidervaart and L. Dekker (eds.) Proc. of the 1994 EUROSIM Conference on Massively Parallel Processing, June 21–23, 1994, Delft, The Netherlands (Amsterdam: Elsevier Sci. Publ., 1994, in print).
D.J. Heeger: “Model for the extraction of image flow”, Journ. Opt. Soc. Am. A, Vol.3 (1987) No.8, pp.1455–1471.
J.L. Barron, D.J. Fleet, S.S. Beauchemin and T.A. Burkitt: “Performance of optical flow techniques”, Technical Report TR-299, University of Western Ontario, Dept. of Computer Science, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Petkov, N. (1994). Conceiving computationally intensive approaches to vision. In: Gentzsch, W., Harms, U. (eds) High-Performance Computing and Networking. HPCN-Europe 1994. Lecture Notes in Computer Science, vol 796. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020403
Download citation
DOI: https://doi.org/10.1007/BFb0020403
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57980-9
Online ISBN: 978-3-540-48406-6
eBook Packages: Springer Book Archive