This paper addresses various aspects of the problems associated with processing and recognition of printed and handwritten Bengali numerals. A scheme has been proposed for recognizing handwritten as well as printed numerals with different fonts and writing styles. The scheme was successfully used for the recognition of the writer from samples of handwritten numerals and the font from printed numerals with a high degree of accuracy. The scheme was also extended for noisy and occluded numerals. The standard multi-layer perceptron (MLP) augmented with MAXNET was used as a classifier. The experiments presented have established the superiority of the MLP and MAXNET combine over the standard MLP classifier and the classical nearest neighbour classifier. © 1992 IEEE.