Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2005.11
DC FieldValue
dc.title3D geometric and optical modeling of warped document images from scanners
dc.contributor.authorZhang, L.
dc.contributor.authorZhang, Z.
dc.contributor.authorTan, C.L.
dc.contributor.authorXia, T.
dc.date.accessioned2013-07-23T09:28:53Z
dc.date.available2013-07-23T09:28:53Z
dc.date.issued2005
dc.identifier.citationZhang, L.,Zhang, Z.,Tan, C.L.,Xia, T. (2005). 3D geometric and optical modeling of warped document images from scanners. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1 : 337-342. ScholarBank@NUS Repository. <a href="https://doi.org/10.1109/CVPR.2005.11" target="_blank">https://doi.org/10.1109/CVPR.2005.11</a>
dc.identifier.isbn0769523722
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/43245
dc.description.abstractWhen one scans a document page from a thick bound volume, the curvature of the page to be scanned results in two kinds of distortion in the scanned document images: i) shade along the 'spine ' of the book, ii) warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. We first build practical models namely a 3D geometric model and a 3D optical model for the practical scanning conditions to reconstruct the 3D shape of book surface. We next restore the scanned document image using this shape based on de-shading and dewarping models. Finally, we evaluate the restoration results by comparing the OCR (Optical Character Recognition) performance on the original and restored document images. The experiments show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly. © 2005 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2005.11
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.contributor.departmentINSTITUTE OF ENGINEERING SCIENCE
dc.description.doi10.1109/CVPR.2005.11
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.volume1
dc.description.page337-342
dc.description.codenPIVRE
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

9
checked on May 15, 2019

Page view(s)

129
checked on May 17, 2019

Google ScholarTM

Check

Altmetric


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