Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system

In this paper, we propose a shape reconstruction and image restoration method for paper documents with curved surfaces or fold lines by using a stereo vision system. Characters in images of thick book's pages acquired with an image scanner are difficult to recognize because they are deformed under the influence of curved surface. Therefore, 3-D shape reconstruction of the book's surface is executed from the result of the stereoscopic measurement by putting the book upward, and an image of a flat surface is recovered from the curved or folded surface. The validity of the proposed method is shown through experiments.

[1]  W. Brent Seales,et al.  Document restoration using 3D shape: a general deskewing algorithm for arbitrarily warped documents , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

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

[3]  Takashi Matsuyama,et al.  Shape from Shading with Interreflections Under a Proximal Light Source: Distortion-Free Copying of an Unfolded Book , 1997, International Journal of Computer Vision.

[4]  Changsong Liu,et al.  A cylindrical surface model to rectify the bound document image , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Tetsuo Iyoda,et al.  Development of the next-generation document reader: Eye Scanner , 2002, IS&T/SPIE Electronic Imaging.

[6]  Maurizio Pilu.  Undoing paper curl distortion using applicable surfaces , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  小沢 慎治,et al.  Shape Recovery of Book Surface Using Two Shade Images Under Perspective Condition (特集:街に出るマシンビジョン) , 1997 .