Distance preserving 1D Turing-wave models via CNN, implementation of complex-valued CNN and solving a simple inverse pattern problem (detection)

摘要

In this paper a cellular neural network (CNN) implementation of a reaction-diffusion system is described, which produces distance preserving periodic Turing patterns. The CNN with complex-valued templates are introduced, presenting an application for pattern generation. Finally a method for black-and-white pattern detection is described.