Novel methods for slope and slant correction of off-line handwritten text word

Abstract

Slope and slant correction of off-line handwritten word are necessary to reduse the variations in writing styles. This paper presents a new technique for slope correction and two novel methods of slant correction in handwritten words. Our algorithms are tested on IAM benchmark database of cursive handwritten words. Promissing results for slope and slant angle estimation are reported and proposed slant correction techniques are compared with the methods, proposed by B. Gatos et al and Moises pastor et al.