6533b832fe1ef96bd129a225
RESEARCH PRODUCT
A system based on neural architectures for the reconstruction of 3-D shapes from images
Roberto PirroneAntonio ChellaFilippo SorbelloEdoardo Ardizzonesubject
ConnectionismArtificial neural networkbusiness.industryComputer scienceTime delay neural networkDeep learningComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONsortArtificial intelligenceArchitecturebusinessBackpropagationImage (mathematics)description
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.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 1991-01-01 |