论文信息 - Line-end detection and boundary gap completion in an EDANN module for orientation

Line-end detection and boundary gap completion in an EDANN module for orientation

Explores two sources of inaccuracies originating from the use of local line detectors for inferring curve and boundary traces: (1) due to the position uncertainty of the local line detectors, ends of thin lines are not easily detected, even if cross-orientation inhibition is applied; and (2) due to the limited ability of the local line detectors to assess more global trace information gaps appear in the curve and boundary extracted. It is shown how a single EDANN (entropy drive artificial neural networks) module processing the orientation of illumination contrast compensates for these inaccuracies by performing a two-stage detection process, a competitive and a cooperative one. In the competitive stage, a vector field of tangents to curves and boundaries is extracted by using elongated receptive fields. In the cooperative stage, line-ends are extracted and boundary gaps are bridged by broadening the neuron's orientation tuning curves.<<ETX>>

M.M. Van Hulle | T. Tollenaere | G.A. Orban

[1] Marc Van Hulle. Building blocks of a sensory artificial neural network : from neuron to symbolic analogon , 1990 .

[2] Tom Tollenaere,et al. Simulating modular neural networks on message-passing multiprocessors , 1991, Parallel Comput..

[3] S Grossberg,et al. Cortical dynamics of three-dimensional form, color, and brightness perception: II. Binocular theory , 1988, Perception & psychophysics.

[4] J. Daugman. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[5] Allen M. Waxman,et al. Spreading activation layers, visual saccades, and invariant representations for neural pattern recognition systems , 1989, Neural Networks.

[6] Steven W. Zucker,et al. The Organization Of Curve Detection: Coarse Tangent Fields And Fine Spline Coverings , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[7] Stephen Grossberg,et al. Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks , 1973 .

[8] Tom Tollenaere,et al. Parallel Implementation and Capabilities of Entropy-Driven Artifical Neural Networks , 1992, J. Parallel Distributed Comput..

[9] Marc M. Van Hulle,et al. Entropy Driven Artificial Neuronal Networks and Sensorial Representation: A Proposal , 1989, J. Parallel Distributed Comput..