Image restoration using layered neural networks and Hopfield networks

An algorithm is developed for the restoration of an image degraded by a known two-dimensional (2-D) shift-invariant point-spread function, and corrupted with white Gaussian noise. A layered neural network and the Hopfield network are used for the edge detection, and the restoration and smoothing of a blurred image, respectively. In particular, a layered neural network is proposed for exact edge detection where the inputs consist of three pixel values and a local variance in a 2-D mask. This network can detect edges and suppress the noise in an image at the same time and its performance is adjusted by learning. Finally, an example is given to illustrate the utility of the proposed algorithm