A Mask-Based Enhancement Method for Historical Documents

Elisa H. Barney Smith; Jerôme Darbon; Laurence Likforman-Sulem

doi:10.1117/12.876668

A Mask-Based Enhancement Method for Historical Documents

Elisa H. Barney Smith
, Jerôme Darbon
, Laurence Likforman-Sulem

Electrical Engineering Department

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

3 Downloads (Pure)

Abstract

This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non-Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.

Original language	American English
Journal	Proceedings of SPIE-IS&T Electronic Imaging
DOIs	https://doi.org/10.1117/12.876668
State	Published - 26 Jan 2011

Keywords

document image enhancement
image processing
non-local means
variational approach

EGS Disciplines

Electrical and Computer Engineering

Access to Document

10.1117/12.876668License: Unspecified

A Mask-Based Enhancement Method for Historical DocumentsFinal published version, 566 KBLicense: Unspecified

Cite this

@article{0699d564a5804d10a453d69b7eddf86b,

title = "A Mask-Based Enhancement Method for Historical Documents",

abstract = " This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non-Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.",

keywords = "document image enhancement, image processing, non-local means, variational approach",

author = "\{Barney Smith\}, \{Elisa H.\} and Jer{\^o}me Darbon and Laurence Likforman-Sulem",

year = "2011",

month = jan,

day = "26",

doi = "10.1117/12.876668",

language = "American English",

}

TY - JOUR

T1 - A Mask-Based Enhancement Method for Historical Documents

AU - Barney Smith, Elisa H.

AU - Darbon, Jerôme

AU - Likforman-Sulem, Laurence

PY - 2011/1/26

Y1 - 2011/1/26

N2 - This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non-Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.

AB - This paper proposes a novel method for document enhancement. The method is based on the combination of two state-of-the-art filters through the construction of a mask. The mask is applied to a TV (Total Variation) -regularized image where background noise has been reduced. The masked image is then filtered by NLmeans (Non-Local Means) which reduces the noise in the text areas located by the mask. The document images to be enhanced are real historical documents from several periods which include several defects in their background. These defects result from scanning, paper aging and bleed-through. We observe the improvement of this enhancement method through OCR accuracy.

KW - document image enhancement

KW - image processing

KW - non-local means

KW - variational approach

UR - https://scholarworks.boisestate.edu/electrical_facpubs/96

U2 - 10.1117/12.876668

DO - 10.1117/12.876668

M3 - Article

JO - Proceedings of SPIE-IS&T Electronic Imaging

JF - Proceedings of SPIE-IS&T Electronic Imaging

ER -

A Mask-Based Enhancement Method for Historical Documents

Abstract

Keywords

EGS Disciplines

Access to Document

Other files and links

Fingerprint

Cite this