A fuzzy neural network and its application to motion detection and velocity estimation
Abbas Z. Kouzani · Adelaide Research & Scholarship (AR&S) (University of Adelaide) · 1995
The advantages of fuzzy sets and neural networks in emulating the human brain capabilities motivated the development of fuzzy neural networks.various models of luzzyneurons have been proposed as the basic element of fuzzy neural networks' In this thesis, we introduce a generic luzzy neuron as an extension of existing fuzzy neuron models.In our model, all the states of activity are given in terms of ruzzy sets with relative grades of membership distributed over the interval [0, 1].The inputs and outputs arefuzzysets over different universes of discourse' The connection' aggregation' and activation functions, which determine the operation of the neuront are fuzzy relations.When the inputs to a function are fuzzy sets over the same universe of discourse, the function can be any hnzy operation in class of triangular norms or triangular conornrs.To evaluate the operation of the fuzzy neuront a fuzzy neural network architechrre based on the generic fuzzy neuron has been developed for motion estimation.The fiveJayer feedforwar druzzy neural network emulates a spatio-temporal image-matctring algorithm.seven simplifred versions of.fuzzyneurons are defined and utilized in the lvzzyneural network.The results of simulations on thousands o1 64 x 64 ' 6-bit image frames containing moving objects under different conditions are reported' ,v 1l .