Skew Detection and Correction of Devanagari Script Using Hough Transform

In this paper we have proposed a method for skew detection and correction of handwritten Devanagari script using Hough transform. In this approach we used Hough transform algorithm for skew detection at word level. Skew of the word is the angle of distortion from horizontal line. The image is acquired using scanner or camera and pre-processed for noise removal. After removing noise, each word of document is extracted. Finally Hough transform is applied on each word for skew detection and rotation transformation is used for skew correction. If skew of the word is in positive angle then it is corrected by rotating it in clockwise direction, otherwise it will be rotated in anti-clockwise direction. The proposed system segment words with 97% accuracy and corrects skew with 92.88% accuracy.