Autowaves for image processing on a two-dimensional CNN array of excitable nonlinear circuits: flat and wrinkled labyrinths

摘要: A two-dimensional (2-D) cellular neural network (CNN) array of resistively coupled Chua circuits which can be designed to implement some elementary aspects spatial recognition, namely, distinguishing open curves from closed ones and locating the shortest path between two locations, is described. In latter, situations are analyzed: flat wrinkled surfaces. The 2-D CNN shown capable finding points on a labyrinth. performance this parallel processing approach was examined using computer simulations, although method implemented in real time via VLSI technology. >