AN IMPROVED DOCUMENT SKEW ANGLE ESTIMATION TECHNIQUE

When a document is fed to a scanner either mechanically or by a human operator for digitization, it suffers from some degrees of skew or til t. Skew angle detection is an important component of any Optical Chara cter Recognition (OCR) and document analysis system. Tn this letter we consider skew estimation of Roman script. The method considers the lo wermost and uppermost pixels of some selected characters of the text w hich may be subject to Hough transform for skew angle detection. A fas t approach is also proposed which works almost as accurately as Hough transform. Experimental results are presented and compared with result s on several other skew detection methods.