Open AccessA New Method to Estimate Skew Angle in Printed and Historical Document Images
Author(s) -
Banumathi K L*,
Jagadeesh Chandra A P
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d8057.118419
Subject(s) - skew , margin (machine learning) , segmentation , computer science , image (mathematics) , artificial intelligence , computer vision , image segmentation , pattern recognition (psychology) , computer graphics (images) , telecommunications , machine learning
In this paper, a new approach to assess the skew angle for scanned/printed documents and historical document images has been proposed.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