Symmetry axis extraction by a neural network

This paper proposes an artificial neural network that extracts axes of symmetry from visual patterns. The input patterns can be plane figures, complicated line drawings or gray-scaled natural images taken by CCD cameras.The network has a hierarchical multi-layered architecture, which resembles that of the lower stages of the neocognitron. It consists of a contrast-extracting layer, edge-extracting layers (simple and complex types), and layers extracting symmetry axes. The network extracts oriented edges from the input image first, and then tries to extract axes of symmetry.Our network checks conditions of symmetry, not directly from the oriented edges, but from a blurred version of them. The use of blurred signals not only reduces the computational cost greatly, but also endows the network with a large tolerance to deformation of input patterns. It is important to get blurred signals, not directly from an input image, but from the oriented edges. Although information of edge locations becomes ambiguous after the blurring operation, most of important features of the original image can still remain stable. If the input image is directly blurred, however, most of the important features in the image will be lost.