Combining statistical and structural approaches for handwritten character description

In this paper a new character description method, based on the combination of structural and statistical approaches, is presented. Characters are prel iminarily decomposed in terms of structural primitives (circular arcs) and successively described in terms of statistical features (geometric moments) . The obtained description is much more stable and yields significant impro vements in classification performance: its effectiveness has been demonstra ted by comparing the recognition results obtained by applying the geometric moments directly on the character bit maps and, as proposed, on the charac ter decomposition in circular arcs. Absolute and relative performance is si gnificant especially for particularly critical cases. Novel recurrent formu lae for evaluating in a closed form the moments of objects represented in t erms of circular arcs are also introduced; experimental results reveal a si gnificant reduction of the time needed for evaluating the moments. (C) 1999 Elsevier Science B.V. All rights reserved.