Title
Shape from Shading Based on Lax-Friedrichs Fast Sweeping and Regularization Techniques With Applications to Document Image Restoration
Abstract
In this paper, we describe a 2-pass iterative scheme to solve the generalpartialdifferentialequation(PDE)related to the Shape-from-Shading (SFS) problem under both dis- tant and close point light sources. In particular, we discuss its applications in restoring warped document images that often appear in the daily snapshots. The proposed method consists of two steps. First the image irradiance equation is formulated as a static Hamilton-Jacobi (HJ) equation and solved using a fast sweeping strategy with Lax-Friedrichs Hamiltonian. However, abrupt errors may arise when ap- plying to real document images due to noises in the approx- imated shading image. To reduce the noise sensitivity, a minimization method thus follows to smooth out the abrupt ridges in the initial result and produce a better reconstruc- tion. Experiments on synthetic surfaces show promising re- sults comparing to the ground truth data. Moreover, a gen- eral framework is developed, which demonstrates that the SFS method can help to remove both geometric and pho- tometric distortions in warped document images for better visual appearance and higher recognition rate.
Year
DOI
Venue
2007
10.1109/CVPR.2007.383287
Minneapolis, MN
Keywords
Field
DocType
document image processing,image restoration,iterative methods,minimisation,partial differential equations,2-pass iterative scheme,Lax-Friedrichs Hamiltonian,Lax-Friedrichs fast sweeping,document image restoration,general partial differential equation,image irradiance equation,minimization method,regularization techniques,shape-from-shading problem,static Hamilton-Jacobi equation,warped document images
Iterative reconstruction,Noise reduction,Computer vision,Iterative method,Computer science,Ground truth,Regularization (mathematics),Artificial intelligence,Image restoration,Partial differential equation,Photometric stereo
Conference
ISSN
ISBN
Citations 
1063-6919 E-ISBN : 1-4244-1180-7
1-4244-1180-7
3
PageRank 
References 
Authors
0.39
21
3
Name
Order
Citations
PageRank
Zhang, L.130.39
Andy M. Yip223220.65
Chew Lim Tan34484284.26