Application of fuzzy cellular neural networks to Euclidean distance transformation

A new structure of fuzzy cellular neural network (FCNN) is proposed. In this FCNN, the relationship between fuzzy templates and input or/and output is defined by addition but not multiplication. Unlike the FCNN we proposed previously, which can only implement morphological operators with flat structuring elements, this FCNN can implement morphological operators with all the types of structuring elements. This FCNN is used to implement Euclidean distance transform. Simulation results are given.