Persian writer identification using extended gabor filter

Abstract

Writer identification using handwritten documents is an interesting field in image processing and machine vision. Many researchers have presented methods to do this, but most of these methods are based on English language. In this paper we have presented a method to identify writer of Persian (Farsi) handwritten documents. The proposed method is based on new filter which we called it extended Gabor filter. This method has no constraint on input data and the experimental results showed that the proposed method worked well. © 2008 Springer-Verlag Berlin Heidelberg.