Robust Document Warping with Interpolated Vector Fields

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.

[1]  Matthew Harker,et al.  Computation of Homographies , 2005, BMVC.

[2]  Gady Agam,et al.  Document Image De-warping for Text/Graphics Recognition , 2002, SSPR/SPR.

[3]  Zhao Zhang,et al.  Estimation of 3D shape of warped document surface for image restoration , 2004, ICPR 2004.

[4]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[5]  Yu Zhang,et al.  A fast and stable approach for restoration of warped document images , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[6]  Maurizio Pilu,et al.  Undoing page curl distortion using applicable surfaces , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[7]  Chew Lim Tan,et al.  Warped image restoration with applications to digital libraries , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[8]  Changsong Liu,et al.  Rectifying the bound document image captured by the camera: a model based approach , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[9]  Isaac Amidror,et al.  Scattered data interpolation methods for electronic imaging systems: a survey , 2002, J. Electronic Imaging.