Hand written letter recognition with neural networks

摘要: Summary form only given, as follows. Neural networks that can recognize 36 handwritten alphanumeric characters are studied. Thin line letters, in 32*32 binary arrays, used the input pattern. The system is built from two major units, a three-layered preprocessing unit and recognition unit. Shift, scale, deformation tolerance provided through reprocessing. Three learning paradigms including an error backpropagation learning, simple perceptron competitive examined compared. >