A new hierarchical approach for recognition of unconstrained handwritten numerals

A new hierarchical approach for the recognition of unconstrained handwritten numerals is proposed. In order to obtain a reliable skeleton of the observed character, some preprocessing operations including smoothing, noise removal, normalization, and a thinning process are first applied to each character. Then, some interesting feature points are extracted from this reliable skeleton of the character. In the first stage of preclassification, a set of structural features named four-zone codes is adopted to preclassify the numerals. Due to the large degree of data and distortion of characters, a three layer fuzzy neural network is used for fine classification. Experimental results show that a high recognition rate over 99.5% is obtained