This paper primarily concerns the problem of isolated handwritten numeral recognition of major Indian scripts. The principal contributions presented here are 1) pioneering development of two databases for handwritten numerals of the two most popular Indian scripts, 2) a multistage cascaded recognition scheme using wavelet-based multiresolution representations and multilayer perceptron (MLP) classifiers, and 3) application of 2 for the recognition of mixed handwritten numerals of three Indian scripts-Devanagari, Bangla, and English. The present databases include, respectively, 22,556 and 23,392 handwritten isolated numeral samples of Devanagari and Bangla collected from real-life situations, and these can be made available free of cost to researchers of other academic institutions. In the proposed scheme, a numeral is subjected to three MLP classifiers corresponding to three coarse-to-fine resolution levels in a cascaded manner. If rejection occurs even at the highest resolution, another MLP is used as the final attempt to recognize the input numeral by combining the outputs of three classifiers of the previous stages. This scheme has been extended to the situation when the script of a document is not known a priori or the numerals written on a document belong to different scripts. Handwritten numerals in mixed scripts are frequently found in Indian postal mail and tabular form documents.
