Fourier fuzzy neural network for clustering of visual objects based on their gross shape and its application to handwritten character recognition

In this paper, an unsupervised feedforward Fourier fuzzy neural network (FFNN) is proposed which is suitable for clustering of object images based on their gross shapes. This 3-layer feedforward neural network is described along with its training. Its performance is tested for synthetic image database containing objects of various shapes and with realistic image database of handwritten Devanagari digits. FFNN is found as superior to the fuzzy min-max neural network (FMN) clustering, and it takes less recall time per pattern than FMN.