Comparison of the Multi Layer Perceptron and the Nearest Neighbor Classifier for Handwritten Numeral Recognition

The work presents the results of an investigation conducted to compare the per- formances of the Multi Layer Perceptron (MLP) and the Nearest Neighbor (NN) classi- fier for handwritten numeral recognition problem. The comparison is drawn in terms of the recognition performance and the computational requirements of the individual classi- fiers. The results show that a two-layer perceptron performs comparably to a NN like standard pattern classifier in recognizing unconstrained handwritten numerals, while be- ing computationally more cost effective. The work signifies the usefulness of the MLP as a standard pattern classifier for recognition of handwritten numerals with a large feature set of 96 features.