A new approach to recognition of deformed patterns

摘要

By introducing a distance between original and deformed patterns and an adequate cost function we derive a gradient dynamics for transformation functions that transform one pattern into another one. In its simplest form the cost function is lent from an elastic medium but in further improvements the corresponding Lamé constants are chosen pattern dependent. In the case of line patterns a smearing out by means of a Gaussian distribution is introduced and made time dependent. The numerical simulations show the feasibility of the present approach, for instance, for the recognition of handwritten characters or of faces showing different facial expressions.