nips nips2001 nips2001-19 nips2001-19-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Lance R. Williams, John W. Zweck
Abstract: We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input provided to V1 by LGN, the input to our computation is isotropic. That is, the input is composed of spots not edges. Second, our network computes a well defined function of the input based on a distribution of closed contours characterized by a random process. Third, even though our computation is implemented in a discrete network, its output is invariant to continuous rotations and translations of the input pattern.
[1] Cowan, J.D., Neurodynamics and Brain Mechanisms, Cognition, Computation and Consciousness, Ito, M., Miyashita, Y. and Rolls, E., (Eds.), Oxford UP, 1997. B 7 ¥X5 ¡ Figure 1: Left: The input bias function, . Twenty randomly positioned spots were added to twenty spots on the boundary of an avocado. The positions are real valued, i.e., they do not lie on the grid of basis functions. Right: The stochastic completion field, , computed using basis functions. § £ ¡ § § ¡ £ ¦ ¡ £ ¦ T i bU9 85 B T 7S £e Figure 2: Left: The input bias function from Fig. 1, rotated by and translated by half the distance between the centers of adjacent basis functions, . Right: The stochastic completion field, is identical (up to rotation and translation) to the one shown in Fig. 1. This demonstrates the Euclidean invariance of the computation. 0 0 BB CG
[2] Freeman, W., and Adelson, E., The Design and Use of Steerable Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence 13 (9), pp.891-906, 1991.
[3] Mumford, D., Elastica and Computer Vision, Algebraic Geometry and Its Applications, Chandrajit Bajaj (ed.), Springer-Verlag, New York, 1994.
[4] Golub, G.H. and C.F. Van Loan, Matrix Computations, Baltimore, MD, Johns Hopkins Univ. Press, 1996.
[5] Heitger, R. and von der Heydt, R., A Computational Model of Neural Contour Processing, Figure-ground and Illusory Contours, Proc. of 4th Intl. Conf. on Computer Vision, Berlin, Germany, 1993.
[6] Iverson, L., Toward Discrete Geometric Models for Early Vision, Ph.D. dissertation, McGill University, 1993.
[7] Li, Z., A Neural Model of Contour Integration in Primary Visual Cortex, Neural Computation 10(4), pp. 903-940, 1998.
[8] Parent, P., and Zucker, S.W., Trace Inference, Curvature Consistency and Curve Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence 11, pp. 823-889, 1989.
[9] Shashua, A. and Ullman, S., Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network, 2nd Intl. Conf. on Computer Vision, Clearwater, FL, pp. 321-327, 1988.
[10] Simoncelli, E., Freeman, W., Adelson E. and Heeger, D., Shiftable Multiscale Transforms, IEEE Trans. Information Theory 38(2), pp. 587-607, 1992.
[11] Williams, L.R., and Thornber, K.K., Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape, Neural Computation 13(8), pp. 16831711, 2001.
[12] Yen, S. and Finkel, L., Salient Contour Extraction by Temporal Binding in a Cortically-Based Network, Neural Information Processing Systems 9, Denver, CO, 1996.
[13] Zweck, J., and Williams, L., Euclidean Group Invariant Computation of Stochastic Completion Fields Using Shiftable-Twistable Functions, Proc. European Conf. on Computer Vision (ECCV ’00), Dublin, Ireland, 2000.