Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.patcog.2009.03.025
Title: A unified framework for document restoration using inpainting and shape-from-shading
Authors: Zhang, L. 
Yip, A.M. 
Brown, M.S. 
Tan, C.L. 
Keywords: Digital inpainting
Document image restoration
Geometric warping
Perspective distortion
Physically based flattening
RBF-based smoothing
Shading distortion
Shape-from-shading
Issue Date: 2009
Source: Zhang, L., Yip, A.M., Brown, M.S., Tan, C.L. (2009). A unified framework for document restoration using inpainting and shape-from-shading. Pattern Recognition 42 (11) : 2961-2978. ScholarBank@NUS Repository. https://doi.org/10.1016/j.patcog.2009.03.025
Abstract: We present a restoration framework to reduce undesirable distortions in imaged documents. Our framework is based on two components: (1) an image inpainting procedure that can separate non-uniform illumination (and other) artifacts from the printed content and (2) a shape-from-shading (SfS) formulation that can reconstruct the 3D shape of the document's surface. Used either piecewise or in its entirety, this framework can correct a variety of distortions including shading, shadow, ink-bleed, show-through, perspective and geometric distortions, for both camera-imaged and flatbed-imaged documents. Our overall framework is described in detail. In addition, our SfS formulation can be easily modified to target various illumination conditions to suit different real-world applications. Results on images of synthetic and real documents demonstrate the effectiveness of our approach. OCR results are also used to gauge the performance of our approach. © 2009 Elsevier Ltd. All rights reserved.
Source Title: Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/43047
ISSN: 00313203
DOI: 10.1016/j.patcog.2009.03.025
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

22
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

15
checked on Nov 16, 2017

Page view(s)

57
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.