Visual enhancement of old documents with hyperspectral imaging

Seon Joo Kim, Fanbo Deng, Michael S. Brown

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

Hyperspectral imaging (HSI) of historical documents is becoming more common at national libraries and archives. HSI is useful for many tasks related to document conservation and management as it provides detailed quantitative measurements of the spectral reflectance of the document that is not limited to the visible spectrum. In this paper, we focus on how to use the invisible spectra, most notably near-infrared (NIR) bands, to assist in visually enhancing old documents. Specifically, we demonstrate how to use the invisible bands to improve the visual quality of text-based documents corrupted with undesired artifacts such as ink-bleed, ink-corrosion, and foxing. For documents of line drawings that suffer from low contrast, we use details found in the invisible bands to enhance legibility. The key components of our framework involve detecting regions in the document that can be enhanced by the NIR spectra, compositing the enhanced gradient map using the NIR bands, and reconstructing the final image from the composited gradients. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed specially for historical documents. Our approach is evaluated on historical documents from NAN that exhibit degradations common to documents found in most archives and libraries.

Original languageEnglish
Pages (from-to)1461-1469
Number of pages9
JournalPattern Recognition
Volume44
Issue number7
DOIs
Publication statusPublished - 2011 Jul 1

Fingerprint

Infrared radiation
Ink
Drawing (graphics)
Conservation
Innovation
Corrosion
Hardware
Degradation
Hyperspectral imaging

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Kim, Seon Joo ; Deng, Fanbo ; Brown, Michael S. / Visual enhancement of old documents with hyperspectral imaging. In: Pattern Recognition. 2011 ; Vol. 44, No. 7. pp. 1461-1469.
@article{3dcfccf904f44926bc4c4b391b418e68,
title = "Visual enhancement of old documents with hyperspectral imaging",
abstract = "Hyperspectral imaging (HSI) of historical documents is becoming more common at national libraries and archives. HSI is useful for many tasks related to document conservation and management as it provides detailed quantitative measurements of the spectral reflectance of the document that is not limited to the visible spectrum. In this paper, we focus on how to use the invisible spectra, most notably near-infrared (NIR) bands, to assist in visually enhancing old documents. Specifically, we demonstrate how to use the invisible bands to improve the visual quality of text-based documents corrupted with undesired artifacts such as ink-bleed, ink-corrosion, and foxing. For documents of line drawings that suffer from low contrast, we use details found in the invisible bands to enhance legibility. The key components of our framework involve detecting regions in the document that can be enhanced by the NIR spectra, compositing the enhanced gradient map using the NIR bands, and reconstructing the final image from the composited gradients. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed specially for historical documents. Our approach is evaluated on historical documents from NAN that exhibit degradations common to documents found in most archives and libraries.",
author = "Kim, {Seon Joo} and Fanbo Deng and Brown, {Michael S.}",
year = "2011",
month = "7",
day = "1",
doi = "10.1016/j.patcog.2010.12.019",
language = "English",
volume = "44",
pages = "1461--1469",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "7",

}

Visual enhancement of old documents with hyperspectral imaging. / Kim, Seon Joo; Deng, Fanbo; Brown, Michael S.

In: Pattern Recognition, Vol. 44, No. 7, 01.07.2011, p. 1461-1469.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visual enhancement of old documents with hyperspectral imaging

AU - Kim, Seon Joo

AU - Deng, Fanbo

AU - Brown, Michael S.

PY - 2011/7/1

Y1 - 2011/7/1

N2 - Hyperspectral imaging (HSI) of historical documents is becoming more common at national libraries and archives. HSI is useful for many tasks related to document conservation and management as it provides detailed quantitative measurements of the spectral reflectance of the document that is not limited to the visible spectrum. In this paper, we focus on how to use the invisible spectra, most notably near-infrared (NIR) bands, to assist in visually enhancing old documents. Specifically, we demonstrate how to use the invisible bands to improve the visual quality of text-based documents corrupted with undesired artifacts such as ink-bleed, ink-corrosion, and foxing. For documents of line drawings that suffer from low contrast, we use details found in the invisible bands to enhance legibility. The key components of our framework involve detecting regions in the document that can be enhanced by the NIR spectra, compositing the enhanced gradient map using the NIR bands, and reconstructing the final image from the composited gradients. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed specially for historical documents. Our approach is evaluated on historical documents from NAN that exhibit degradations common to documents found in most archives and libraries.

AB - Hyperspectral imaging (HSI) of historical documents is becoming more common at national libraries and archives. HSI is useful for many tasks related to document conservation and management as it provides detailed quantitative measurements of the spectral reflectance of the document that is not limited to the visible spectrum. In this paper, we focus on how to use the invisible spectra, most notably near-infrared (NIR) bands, to assist in visually enhancing old documents. Specifically, we demonstrate how to use the invisible bands to improve the visual quality of text-based documents corrupted with undesired artifacts such as ink-bleed, ink-corrosion, and foxing. For documents of line drawings that suffer from low contrast, we use details found in the invisible bands to enhance legibility. The key components of our framework involve detecting regions in the document that can be enhanced by the NIR spectra, compositing the enhanced gradient map using the NIR bands, and reconstructing the final image from the composited gradients. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed specially for historical documents. Our approach is evaluated on historical documents from NAN that exhibit degradations common to documents found in most archives and libraries.

UR - http://www.scopus.com/inward/record.url?scp=79952189309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952189309&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2010.12.019

DO - 10.1016/j.patcog.2010.12.019

M3 - Article

AN - SCOPUS:79952189309

VL - 44

SP - 1461

EP - 1469

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 7

ER -