DocumentCode
2021147
Title
Robust Document Warping with Interpolated Vector Fields
Author
Schneider, David C. ; Block, Marco ; Rojas, Raúl
Author_Institution
Freie Univ. Berlin, Berlin
Volume
1
fYear
2007
fDate
23-26 Sept. 2007
Firstpage
113
Lastpage
117
Abstract
This paper describes a new versatile algorithm for correcting nonlinear distortions, such as curvature of book pages, in camera based document processing. We introduce the idea of using local orientation features to interpolate a vector field from which a warping mesh is derived. Ultimately, the image is corrected by approximating the nonlinear distortion with multiple linear projections. Since the algorithm does not derive the mesh directly from text baselines it is robust over arbitrarily complex text layouts. We describe a baseline detector for extracting the required local orientation features. We also sketch a method for correcting nonlinear distortions of a document´s vertical axis with our algorithm.
Keywords
document image processing; feature extraction; interpolation; mesh generation; nonlinear distortion; baseline detector; document image warping; interpolated vector field; local orientation feature extraction; mesh construction; nonlinear distortion; Books; Cameras; Character recognition; Detectors; Image recognition; Nonlinear distortion; Optical character recognition software; Optical distortion; Robustness; Shape;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location
Parana
ISSN
1520-5363
Print_ISBN
978-0-7695-2822-9
Type
conf
DOI
10.1109/ICDAR.2007.4378686
Filename
4378686
Link To Document