Machine vision recognition of fuzzy objects using a new fuzzy neural network

In this paper, a new fuzzy neural network, termed FUZAMP, is used to deal with situations where the available training data from a machine vision system include uncertainty. The data with uncertainty are transformed into fuzzy sets, which then become inputs to FUZAMP. Several simulation examples demonstrate the effectiveness of FUZAMP, which is also implemented in a real system to solve a sorting problem in large commercial dish washing operations. FUZAMP performed well when used to recognize different types of fuzzy objects presented at different locations and orientations in the camera field of view. Results were compared to those obtained using the so-called fuzzy ARTMAP neural network, with FUZAMP achieving better accuracy than the fuzzy ARTMAP using the same training exemplars