Efficient image restoration using cellular neural networks

A 3D cellular neural network (CNN) is applied for restoration of degraded images. It is known that regularized or maximum a posteriori estimation based image restoration problems can be formulated as the minimization of the Lyapunov function of the discrete-time Hopfield network. Previously, this Lyapunov function based design method has been extended to the continuous-time Hopfield network and to the continuous-time CNN operating either in a binary steady-state output mode or in a real-valued steady-state output mode. This paper considers 3D CNN in the binary mode, which needs eight binary (nonredundant) neurons only for each image pixel thus reducing the computational overhead, and introduces a hardware annealing approach to overcome the bad local minima problem due to binary mode of operation and nonredundant representation.