A NEURAL NET FOR 2D-SLOPE AND SINUSOIDAL SHAPE DETECTION

Authors

  • A. Bruckmann
  • F. Klefenz
  • A. Wunsche

DOI:

https://doi.org/10.47839/ijc.3.1.248

Keywords:

Orientation selectivity, frequency selectivity, delay tuning

Abstract

2D-slope and sinusoidal shape detection are application specific tasks which are widely discussed in the literature. A neural network is presented which is able to learn a set of different slopes or a set of sinusoids of different frequencies and to detect test patterns after the training stage. The neural net is composed of input neurons, delay neurons and output neurons. The delay neurons form a set of tapped delay lines. Each delay line adapts to its specific signal propagation velocity. The signal propagation velocity vector field of the delay lines is learned by collectively tuning the signal propagation velocities. The neural net is fed with a set of spatiotemporal training patterns, such as bars of different slopes or sinusoids of different frequencies. After training, the net is tested with a random set of 2D- patterns. Unsupervised learning with a Boltzmann temperature term is assumed.

References

R. Shapley, D. McLaughlin, M. Shelley. Orientation selectivity, M. A. Arbib (Editor). The Handbook of Brain Theory and Neural Networks. MIT Press. 2003. p. 831 – 835

G. Blasdel. Orientation selectivity, preference and continuity in monkey striate cortex, Journal of Neuroscience 12 (8) (1992). p. 3139 – 3161

D. H. Hubel, T. N. Wiesel, M. P. Stryker. Anatomical demonstration of orientation columns in macaque monkey, Journal of Comparative Neurology 177 (1978). p. 361 – 380

A. Epstein, G. U. Paul, B. Vettermann, C. Boulin, F. Klefenz. A parallel systolic array ASIC for real time execution of the Hough-transform, E. S. Peris, A. F. Soria, V. G. Millan (Editors). Proceedings of the 12th IEEE International Congress on Real Time for Nuclear and Plasma Sciences, Valencia, 2001. p. 68 – 72.

D. H. Ballard. Generalizing the Hough transform to detect arbitrary shapes, Pattern Recognition 13 (1981). p. 111 – 122.

P. V. C. Hough. Method and means for recognizing complex patterns, US Patent 3069654 (1962)

F. Klefenz, K. H. Noffz, R. Zoz, W. Conen, R. Manner. R. (1993) Track recognition in 4 microseconds by a systolic trigger processor using a parallel Hough transform, IEEE Tr. Nucl. Sci. 40 (4) (1993). p. 688 – 691.

Downloads

Published

2014-08-01

How to Cite

Bruckmann, A., Klefenz, F., & Wunsche, A. (2014). A NEURAL NET FOR 2D-SLOPE AND SINUSOIDAL SHAPE DETECTION. International Journal of Computing, 3(1), 21-26. https://doi.org/10.47839/ijc.3.1.248

Issue

Section

Articles