Handwritten Word Recognition Using Fuzzy Matching Degrees

Abstract Handwritten text recognition systems interpret the scanned script images as composed of letters. In this paper, efficient offline methods using fuzzy degrees, well interval degrees type-2, are proposed to recognize letters beforehand decomposed into strokes. For such strokes, first stage used create a set hypotheses whether group strokes matches letter or digit patterns. Subsequently, second-stage employed select most promising with use degrees. primary version system, standard memberships measure compatibility between and character As an extension system thus created, type-2 perform selection that fit multiple handwriting typefaces.