1 March 1992 Hierarchical neural networks for edge preservation and restoration
Author Affiliations +
In the paper, a hierarchical neural network system is designed to adjust edge measurements based on the information provided by neighboring edges. The local edge pattern is analyzed to determine and reinforce edge structures while suppressing unwanted noise and false edges. The neural network is made up of four levels of subnets. The subnet in the first level determines the potential adjustment on the element of interest by detecting edge contours according to the selected processes in the neural nets and the input local edge pattern. The second level consists of a cooperative-competitive neural net model to find the orientation of the strongest edge contour in the local edge pattern. The subnet in the third level ascertains the conditions for adjusting the gradient magnitude and determines the amount of adjustment to the gradient magnitude, and calculates the new adjusted gradient magnitude and determines if the element of interest is to be an edge element or a non-edge element. The subnet in level four is a semilinear feedforward net which is used to assign the new orientation for the element of interest. An iterative approach incorporated into the neural network system has also enabled the application of global analysis in the process of adjusting the edge measurements.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Si Wei Lu, Si Wei Lu, Anthony Szeto, Anthony Szeto, } "Hierarchical neural networks for edge preservation and restoration", Proc. SPIE 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods, (1 March 1992); doi: 10.1117/12.135116; https://doi.org/10.1117/12.135116


Perceptual Grouping Of Curved Lines
Proceedings of SPIE (March 27 1989)
Space And Time Requirements For Two Image Data Structures
Proceedings of SPIE (March 27 1989)
The Structure Of Vision Modules On A Fine-Grained Machine
Proceedings of SPIE (February 19 1988)
New entropy operator for edge abstraction
Proceedings of SPIE (August 20 1993)
Connectionist learning procedure for edge detector
Proceedings of SPIE (February 01 1992)

Back to Top