A New Method to Estimate Skew Angle in Printed and Historical Document Images

Abstract

In this paper, a new approach to assess the skew angle for scanned/printed documents and historical document images has been proposed. This is substantial for an automatic document processing system (as text and image segmentation) to avert errors in auxiliary stages. The proposed tactic is based on the statistical analysis of the slope of the connected lines in the document. The proposed technique detects skew and corrects it by initial letter (X1, Y1+200) from left margin of the resized (800X800) image and (X1+200, Y1) from top margin. Final letter (X2, Y2-200) and (X2-200, Y2) were chosen from right and bottom margins of the same image. The skew angle estimation is done for standard skewed dataset and effective correction of the same is performed with minimum errors.