Skew Detection and Correction in Scanned Document Images.

Abstract

During document scanning, skew is inevitably introduced into the incoming document image. Skew detection is one the first operations to be applied to scanned documents when converting data to a digital format. Its aim is to align an image before processing because text segmentation and recognition methods require properly aligned next lines.
Different algorithms of skew detection are implemented. The first one is Scan line based skew detection. In this method the image is projected at several angles and the variance in the number of black pixels per projected scan line is determined. The angle at which the maximum variance occurs is the angle of skew.The second one is based on the Hough transform. Hough transform is performed on the scanned document image and the variance in ρ values is calculated for each value of θ. The angle that gives the maximum variance is the skew angle.The third approach is based on the base-point method. Here a concept of basepoint is introduced. After the successive base-points in every text line within a suitable sub-region were selected as samples for the straight-line fitting. The average of these baseline directions is computed, which corresponds to the degree of skew of the whole document image.All the above mentioned algorithm have been implemented and the results of each have been compared for accuracy.