The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - April (2008 vol.30)
pp: 728-734
ABSTRACT
In document digitization through camera-based systems, simple imaging setups often produce geometric distortions in the resultant 2D images because of the non-planar geometric shapes of certain documents such as thick bound books, rolled, folded or crumpled materials, etc. Previous works [1]?[4] have demonstrated that arbitrary warped documents can be successfully restored by flattening a 3D scan of the document. These approaches use physically-based or relaxation-based techniques in their flattening process. While this has been demonstrated to be effective in rectifying the image content and improving OCR, these previous approaches have several limitations in terms of speed and stability. In this paper, we propose a distance-based penalty metric to replace the mass-spring model and introduce additional bending resistance and drag forces to improve the efficiency of the existing approaches. The use of Verlet integration and special plane collision handling schemes also help to achieve better stability without sacrificing efficiency. Experiments on various document images captured from books, brochures and historical documents with arbitrary warpings have demonstrated large improvements over the existing approaches in terms of stability and efficiency.
INDEX TERMS
Warped Image Restoration, Geometric Correction, Phyiscally-based Modeling, Numerical Integration
CITATION
Li Zhang, Yu Zhang, Chew Tan, "An Improved Physically-Based Method for Geometric Restoration of Distorted Document Images", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 4, pp. 728-734, April 2008, doi:10.1109/TPAMI.2007.70831
REFERENCES
[1] M. Pilu, “Undoing Page Curl Distortion Using Applicable Surfaces,” Computer Vision and Pattern Recognition, vol. 1, pp. 67-72, 2001.
[2] M. Brown and W. Seales, “Document Restoration Using 3D Shape: A General Deskewing Algorithm for Arbitrarily Warped Documents,” Proc. Int'l Conf. Computer Vision, vol. 2, pp. 367-374, 2001.
[3] M. Brown and W. Seales, “Image Restoration of Arbitrarily Warped Documents,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 10, pp. 1295-1306, Oct. 2004.
[4] M. Brown and C. Pisula, “Conformal Deskewing of Non-Planar Documents,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 998-1004, 2005.
[5] J. Liang, D. DeMenthon, and D. Doermann, “Camera-Based Analysis of Text and Documents: A Survey,” Int'l J. Document Analysis and Recognition, vol. 7, nos. 2-3, pp. 83-104, 2005.
[6] Y.Y. Tang and C.Y. Suen, “Image Transformation Approach to Nonlinear Shape Restoration,” IEEE Trans. Systems, Man, and Cybernetics, vol. 1, no. 23, pp. 155-171, 1993.
[7] Z. Zhang and C.L. Tan, “Straightening Warped Text Lines Using Polynomial Regression,” Proc. Int'l Conf. Image Processing, pp. 977-980, 2002.
[8] Y.C. Tsoi and M.S. Brown, “Geometric and Shading Correction for Images of Printed Materials—A Unified Approach Using Boundary,” Computer Vision and Pattern Recognition, vol. 1, pp. 240-246, 2004.
[9] M. Sun, R. Yang, L. Yun, G. Landon, B. Seales, and M. Brown, “Geometric and Photometric Restoration of Distorted Documents,” Proc. 10th IEEE Int'l Conf. Computer Vision, vol. 2, pp. 17-21, 2005.
[10] K.B. Chua, L. Zhang, Y. Zhang, and C.L. Tan, “A Fast and Stable Approach for Restoration of Warped Document Images,” Proc. IAPR Int'l Conf. Document Analysis and Recognition, no. 1, pp. 384-388, 2005.
[11] T. Amano, T. Abe, T. Iyoda, O. Nishikawa, and Y. Sato, “Camera-Based Document Image Mosaicing,” Proc. SPIE, vol. 4669, pp. 250-258, 2002.
[12] W. Seales and Y. Lin, “Digital Restoration Using Volumetric Scanning,” Proc. Joint ACM/IEEE Conf. Digital Libraries, vol. 1, pp. 117-124, 2004.
[13] Y. Lin and W. Seales, “Opaque Document Imaging: Building Images of Inaccessible Texts,” Proc. 10th IEEE Int'l Conf. Computer Vision, vol. 1, pp.662-669, 2005.
[14] A. Yamashita, A. Kawarago, T. Kaneko, and K.T. Miura, “Shape Reconstruction and Image Restoration for Non-Flat Surface of Document with a Stereo Vision System,” Proc. IEEE Int'l Conf. Pattern Recognition, pp.482-485, 2004.
[15] A. Iketani, T. Sato, and S. Ikeda, “Video Mosaicing for Curved Documents Based on Structure from Motion,” Proc. 18th Int'l Conf. Pattern Recognition, vol. 1, pp. 391-396, 2006.
[16] “3D Digitizers—Non-Contact Laser Range Scanner,” Ramsey, USA, Konica Minolta, http:/www.minolta3d.com, 2007.
[17] A. Witkin, “An Introduction to Physically Based Modeling: Particle System Dynamics,” Proc. ACM SIGGRAPH, 1997.
[18] D. Baraff, “An Introduction to Physically Based Modeling: Rigid Body Simulation I—Unconstrained Rigid Body Dynamics,” Proc. ACM SIGGRAPH Tutorial Notes, 1997.
[19] G. Oliveira, “Exploring Spring Models,” Game Developer, 2001.
[20] X. Provot, “Deformation Constraints in a Mass-Spring Model to Describe Rigid Cloth Behaviour,” Graphics Interface, pp. 155-174, 1995.
[21] T. Jakobsen, “Advanced Character Physics,” Game Developer, 2003.
[22] K.J. Choi and H.S. Ko, “Extending the Immediate Buckling Model to Triangular Meshes for Simulating Complex Clothes,” Proc. EUROGRAPHICS, pp. 187-191, 2003.
[23] P. Volino and N. Magnenat-Thalmann, “Efficient Self-Collision Detection on Smoothly Discretized Surface Animations Using Geometrical Shape Regularity,” Proc. EUROGRAPHICS, no. 13, pp. 155-166, 1994.
[24] P. Volino and N. Magnenat-Thalmann, “Implementing Fast Cloth Simulation with Collision Response,” Proc. Computer Graphics Int'l, pp. 257-268, 2000.
[25] X. Provot, “Collision and Self-Collision Detection Handling in Cloth Model Dedicated to Design Garments,” Graphics Interface, pp. 177-189, 1997.
[26] A. Witkin, “Physically Based Modeling - Particle System Dynamics,” Proc. ACM SIGGRAPH Course Notes, 2001.
[27] W.H. Press, B.P. Fannery, S.A. Teukolsky, and W.T. Verrerling, Numerical Recipes: The Art of Scientific Computing. Cambridge Univ. Press, 1986.
[28] L. Zhang, A. Yip, and C. Tan, “Photometric and Geometric Restoration of Document Images Using Inpainting and Shape-from-Shading,” Proc. 22nd Conf. Artificial Intelligence, 2007.
[29] S. Farsiu, D. Robinson, M. Elad, and P. Milanfar, “Fast and Robust Super-Resolution,” Proc. IEEE Int'l Conf. Image Processing, pp. 291-294, 2003.
[30] J. Liang, D. DeMenthon, and D. Doermann, “Camera-Based Document Image Mosaicing,” Proc. Int'l Conf. Pattern Recognition, no. 2, pp. 476-479, 2006.
20 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool