Multi-valued and universal binary neurons: New applications in intelligent image processing

Multi-valued neurons (MVN) and universal binary neurons (UBN) are neural elements with complex-valued weights and high functionality. It is possible to implement the arbitrary mapping described by partially defined multiple-valued function on the single MVN and the arbitrary mapping described by Boolean function (which may not be threshold) on the single UBN. In this paper we consider some applications carried out using these wonderful features of MVN and UBN. Conception of cellular neural networks based on MVN and UBN becomes a base for nonlinear cellular neural filtering. Application of the corresponding filters for edge detection and solving of the super-resolution problem are considered in the paper.