A New Method to Estimate Skew Angle in Printed and Historical Document Images
Banumathi K L1, Jagadeesh Chandra A P2
1Banumathi K L, Research Scholar, Department of Electronics and Communication, Adichunchangiri Institute of Technology, Chickmagalore, India.
2Jagadeesh Chandra A P, Professor, Department of Electronics and Communication, Adichunchangiri Institute of Technology, Chickmagalore, India.
Manuscript received on November 10, 2019. | Revised Manuscript received on November 17, 2019. | Manuscript published on 30 November, 2019. | PP: 3936-3943 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8057118419/2019©BEIESP | DOI: 10.35940/ijrte.D8057.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, a new approach to assess the skew angle for scanned/printed documents and historical document images has been proposed.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.
Keywords: Printed Text, Multiple Skew, Skew Detection and Correction.
Scope of the Article: 3D Printing.