IMAGE PROCESSING TECHNIQUES

On applicability of methods of recognition to research of statistical properties of sets of symbols

M. B. Gavrikov^a, N. V. Pestryakova<sup>b

a</sup> Keldysh Institute of Applied Mathematics of Russian Academy of Sciences, Moscow
^b Institute for Systems Analysis of Russian Academy of Sciences

Abstract: Effective annexes of a probabilistic high-precision method of recognition to a task of the analysis of statistical properties of sets of symbols are described.

Keywords: classification, polynomial regression, printed and hand-printed symbols.