NEURAL NETWORKS FOR SHAPE RECOGNITION BY MEDIAL REPRESENTATION
The article is dedicated to the development of neural networks that process data of a special kind – a medial representation of the shape, which is considered as a special case of an undirected graph. Methods for solving problems that complicate the processing of data of this type by traditional neural networks – different length of input data, heterogeneity of its structure, unordered constituent elements – are proposed. Skeletal counterparts of standard operations used in convolutional neural networks are formulated. Experiments on character recognition for various fonts, on classification of handwritten digits and data compression using the autoencoder-style architecture are carried out.