A system based on neural architectures for the reconstruction of 3-D shapes from images
The connectionist approach to the recovery of 3-D shape information from 2-D images developed by the authors, is based on a system made up by two cascaded neural networks. The first network is an implementation of the BCS, an architecture which derives from a biological model of the low level visual processes developed by Grossberg and Mingolla: this architecture extracts a sort of brightness gradient map from the image. The second network is a backpropagation architecture that supplies an estimate of the geometric parameters of the objects in the scene under consideration, starting from the outputs of the BCS. A detailed description of the system and the experimental results obtained by simulating it are reported in the paper.
Unable to display preview. Download preview PDF.
- Ardizzone, E., Gaglio, S., Sorbello, F. (1989). Geometric and Conceptual Knowledge Representation within a Generative Model of Visual Perception, Journal of Intelligent and Robotic Systems, 2, 381–409.Google Scholar
- Barr, A.H. (1981). Superquadrics and Angle-Preserving Trasformations, IEEE Computer Graphics and Applications, 1, 11–23.Google Scholar
- Grossberg, S., Mingolla, E. (1986). Computer Simulation of Neural Networks for Perceptual Psychology. Behavior Research Methods, Instruments and Computers, 18 (6), 601–607.Google Scholar
- Grossberg, S., Mingolla, E., (1987). Neural Dynamics of Surface Perception: Boundary Webs, Illuminants, and Shape-from-Shading. Computer Vision, Graphics and Image Processing, 37, 116–165.Google Scholar
- Horn, B.K.P. (1986). Robot Vision. MIT Press, Cambridge, MA, USA.Google Scholar
- Rumelhart, D. E., McClelland, J. L. (eds.) & PDP Research Group (1986), Parallel Distributed Processing, Vol 1, MIT Press, Cambridge, MA, USA.Google Scholar