Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICPR.2004.1334172
DC FieldValue
dc.titleEstimation of 3D shape of warped document surface for image restoration
dc.contributor.authorZhang, Z.
dc.contributor.authorTan, C.L.
dc.contributor.authorFan, L.
dc.date.accessioned2013-07-04T07:53:23Z
dc.date.available2013-07-04T07:53:23Z
dc.date.issued2004
dc.identifier.citationZhang, Z., Tan, C.L., Fan, L. (2004). Estimation of 3D shape of warped document surface for image restoration. Proceedings - International Conference on Pattern Recognition 1 : 486-489. ScholarBank@NUS Repository. https://doi.org/10.1109/ICPR.2004.1334172
dc.identifier.isbn0769521282
dc.identifier.issn10514651
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39954
dc.description.abstractWhile scanning pages from a thick, bound book, there are two sources of distortion in the document images: 1) shade along the book 'spine', and 2) warping of the book surface in the shade area. In this paper, we propose a fast method to estimate the 3D shape of a book surface. Based on this shape, we remove the shade and correct the warping to restore the document images. The experiments show that the photometric and geometric distortions are mostly removed. The OCR tests on the original and restored document images are also presented.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICPR.2004.1334172
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/ICPR.2004.1334172
dc.description.sourcetitleProceedings - International Conference on Pattern Recognition
dc.description.volume1
dc.description.page486-489
dc.description.codenPICRE
dc.identifier.isiut000223874500119
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

20
checked on Sep 28, 2022

WEB OF SCIENCETM
Citations

5
checked on Sep 28, 2022

Page view(s)

226
checked on Sep 22, 2022

Google ScholarTM

Check

Altmetric


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