We describe a neural network for segmentation of a blurred and noise-corrupted image. There may be an arbitrary number of grey levels in the restored image. The simplest system we have found to do an acceptable job has several parallel networks detecting potential edges at different orientations in the image. Their output is combined in a final network, where the restored image is formed by filling in sections with appropriate grey level values. To detect the edges the parallel networks use directional second derivatives of the image, and they only differ with respect to in which direction this derivative is taken. We find that at least two such orthogonal working networks are needed to do a reasonable segmentation. The system is tested on simple geometrical figures distorted by Gaussian blur and noise, and its performance is compared to that of other algorithms. We also comment on the existence of similar structures in natural vision.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.