Fast and robust skew detection for scanned documents

Author

Shi Na ; Pan Jinxiao

Author_Institution

Dept. of Math., North Univ. of China, Taiyuan, China

Volume

8

fYear

2011

fDate

12-14 Aug. 2011

Firstpage

4170

Lastpage

4173

Abstract

A fast and robust skew detection for scanned document images based on the improved piecewise covering by parallelograms is proposed in this papper. Comparison with the original PCP algorithm, the skew detection of the proposed algorithm is more applicable on vertical textlines documents, and is not sensitive to the noise. The experiment results show that the computation time is short, while the detection accuracy is higher. The enhanced skew detection approach is efficient for horizontal and vertical textlines documents, and the complex documents with forms, tables and pictures.

Keywords

document image processing; text analysis; detection accuracy; document image analysis; horizontal textline document; improved PCP algorithm; improved piecewise covering by parallelograms algorithm; robust skew detection; scanned document images; vertical textline document; Correlation; Estimation; Noise; Pattern recognition; Robustness; Slabs; Transforms; document image analysis; improved PCP; skew detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronic and Mechanical Engineering and Information Technology (EMEIT), 2011 International Conference on

Conference_Location

Harbin, Heilongjiang

Print_ISBN

978-1-61284-087-1

Type

conf

DOI

10.1109/EMEIT.2011.6023104

Filename

6023104