Abstract
A non-linear projection-based deskewing algorithm for documents and newspaper images is presented. Project profiles are among the most popular methods for skew estimation. Deskewing strategy is obtained with a three steps procedure: focus of attention selection, skew estimation and skew correction. The algorithm works on text lines and space lines projection profiles, and the dominant orientation of these lines represents the skew angle of the page.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
T.]Akiyama and N.Hagita “Automated entry system for printed documents” Pattern Recognition, 23(11),1990 pp 1141–1154
T.Pavlidis and J.Zhou, “Page Segmentation by White Streams” Proc 1th ICDAR 1991 pp 945–953
H.S.Baird “The skew angle of printed documents” Proc. Conf. Phot. Sc. and Engin. SPIE 1987 pp 14–21
S.C.Hinds et al. “A document skew detection method using run length encoding and the Hough transform” Proc 10th ICPR Los Alamitos 1990, pp 464–468
Y.Nakano et al. “An algorithm for skew normalisation of document images” Proc. 10th ICPR Los Alamitos 1990, pp 8–13.
B.Yu and A.K.Jain “A robust and fast skew detection algorithm for generic documents” Patt. Rec. 29(10) 1996 pp 1599–1629.
L.O'Gorman “The document spectrum for structural page layout analysis” PAMI 15(11) 1993 pp 1162–1173.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
del Ninno, E., Nicchiotti, G., Ottaviani, E. (1997). A general and flexible deskewing method based on generalized projection. In: Del Bimbo, A. (eds) Image Analysis and Processing. ICIAP 1997. Lecture Notes in Computer Science, vol 1311. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63508-4_177
Download citation
DOI: https://doi.org/10.1007/3-540-63508-4_177
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63508-6
Online ISBN: 978-3-540-69586-8
eBook Packages: Springer Book Archive