A comparison of a nearest neighbor classifier and a neural network for numeric handprint character recognition

A comparison is made of two techniques for recognizing numerical handprint characters using a variety of features, including 2D fast-Fourier transform coefficients, geometrical moments, and topological features. A backpropagation network and a nearest neighbor classifier are evaluated in terms of recognition performance and computational requirements. The results indicate that for complex problems, the performance of the neural network is comparable to that of the nearest neighbor classifier while being significantly more cost effective.<>