AZERBAIJAN NATIONAL ACADEMY OF SCIENCES
APPLICATION OF SVM AND NEW FEATURES CLASS TO RECOGNITION OF AZERBAIJANI HAND-PRINTED SYMBOLS (azerb.)
Elviz A.Ismayilov

Although there are widely spread latin symbols in our alphabet, intending special symbols and morphological content of our language requires individual approach for character recognition. In this paper “soft” (close to human mind, constructed on base of characteristics which we use in alphabet learning) features and SVM for recognition of Azerbaijani hand-printed characters are used. For character classification bootstrap resampling procedure of support vector machines is used. Results are compared with results of other feature classes and methods (pp.101-108).

Keywords: “soft” features, SVM, hand-printed symbols, recognition system.