Please use this identifier to cite or link to this item: https://doi.org/10.1109/TPAMI.2002.1039211
Title: Restoration of archival documents using a wavelet technique
Authors: Tan, C.L. 
Cao, R.
Shen, P.
Keywords: Bleed-through
Canny edge detector
Denoising
Document image analysis
Image segmentation
Noise cancellation
Show-through
Text extraction
Wavelet enhancement
Wavelet smearing
Issue Date: 2002
Source: Tan, C.L.,Cao, R.,Shen, P. (2002). Restoration of archival documents using a wavelet technique. IEEE Transactions on Pattern Analysis and Machine Intelligence 24 (10) : 1399-1404. ScholarBank@NUS Repository. https://doi.org/10.1109/TPAMI.2002.1039211
Abstract: This paper addresses a problem of restoring handwritten archival documents by recovering their contents from the interfering handwriting on the reverse side caused by the seeping of ink. We present a novel method that works by first matching both sides of a document such that the interfering strokes are mapped with the corresponding strokes originating from the reverse side. This facilitates the identification of the foreground and interfering strokes. A wavelet reconstruction process then iteratively enhances the foreground strokes and smears the interfering strokes so as to strengthen the discriminating capability of an improved Canny edge detector against the interfering strokes. The method has been shown to restore the documents effectively with average precision and recall rates for foreground text extraction at 84 percent and 96 percent, respectively.
Source Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
URI: http://scholarbank.nus.edu.sg/handle/10635/39281
ISSN: 01628828
DOI: 10.1109/TPAMI.2002.1039211
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

65
checked on Dec 12, 2017

Page view(s)

49
checked on Dec 8, 2017

Google ScholarTM

Check

Altmetric


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