Blotch and scratch removal in archived film using a semi-transparent corruption model and a ground-truth generation technique

Mohamed Elgharib, François Pitié, Anil Kokaram

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper has two main contributions. The first is a Bayesian framework for removing two common types of degradations on video known as blotches and line scratches. Most removal techniques assume complete obliteration of the original data at the corrupted sites. This often leads to the introduction of restoration artifacts during removal. Our framework is based on modeling corruption as a semi-transparent layer. This model was introduced earlier by Ahmed et al. (ICIP 2009) for the problem of blotch removal. We show much more blotch removal results than the previous work, and we extend the semi-transparent corruption model to the problem of line removal. The second contribution of this paper is an automated technique for ground-truth generation from infrared scans of corruptions. Previous ground-truth generation efforts require manually inpainting the corrupted regions. The restoration results are evaluated by comparing the reconstructed data against the ground-truth estimates. Comparisons with current blotch and line removal techniques show that the proposed corruption removal framework produces better removal and generates less restoration artifacts.

Original languageEnglish
Article number33
JournalEurasip Journal on Image and Video Processing
Volume2013
DOIs
Publication statusPublished - 11 Nov 2013
Externally publishedYes

Fingerprint

Restoration
Infrared radiation
Degradation

Keywords

  • Bayesian matting
  • Blotch
  • graph-cut
  • ground-truth
  • infrared
  • line scratch
  • transparency

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Information Systems

Cite this

@article{7b893ce8961d4ed793d7333279120f69,
title = "Blotch and scratch removal in archived film using a semi-transparent corruption model and a ground-truth generation technique",
abstract = "This paper has two main contributions. The first is a Bayesian framework for removing two common types of degradations on video known as blotches and line scratches. Most removal techniques assume complete obliteration of the original data at the corrupted sites. This often leads to the introduction of restoration artifacts during removal. Our framework is based on modeling corruption as a semi-transparent layer. This model was introduced earlier by Ahmed et al. (ICIP 2009) for the problem of blotch removal. We show much more blotch removal results than the previous work, and we extend the semi-transparent corruption model to the problem of line removal. The second contribution of this paper is an automated technique for ground-truth generation from infrared scans of corruptions. Previous ground-truth generation efforts require manually inpainting the corrupted regions. The restoration results are evaluated by comparing the reconstructed data against the ground-truth estimates. Comparisons with current blotch and line removal techniques show that the proposed corruption removal framework produces better removal and generates less restoration artifacts.",
keywords = "Bayesian matting, Blotch, graph-cut, ground-truth, infrared, line scratch, transparency",
author = "Mohamed Elgharib and Fran{\cc}ois Piti{\'e} and Anil Kokaram",
year = "2013",
month = "11",
day = "11",
doi = "10.1186/1687-5281-2013-33",
language = "English",
volume = "2013",
journal = "Eurasip Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",

}

TY - JOUR

T1 - Blotch and scratch removal in archived film using a semi-transparent corruption model and a ground-truth generation technique

AU - Elgharib, Mohamed

AU - Pitié, François

AU - Kokaram, Anil

PY - 2013/11/11

Y1 - 2013/11/11

N2 - This paper has two main contributions. The first is a Bayesian framework for removing two common types of degradations on video known as blotches and line scratches. Most removal techniques assume complete obliteration of the original data at the corrupted sites. This often leads to the introduction of restoration artifacts during removal. Our framework is based on modeling corruption as a semi-transparent layer. This model was introduced earlier by Ahmed et al. (ICIP 2009) for the problem of blotch removal. We show much more blotch removal results than the previous work, and we extend the semi-transparent corruption model to the problem of line removal. The second contribution of this paper is an automated technique for ground-truth generation from infrared scans of corruptions. Previous ground-truth generation efforts require manually inpainting the corrupted regions. The restoration results are evaluated by comparing the reconstructed data against the ground-truth estimates. Comparisons with current blotch and line removal techniques show that the proposed corruption removal framework produces better removal and generates less restoration artifacts.

AB - This paper has two main contributions. The first is a Bayesian framework for removing two common types of degradations on video known as blotches and line scratches. Most removal techniques assume complete obliteration of the original data at the corrupted sites. This often leads to the introduction of restoration artifacts during removal. Our framework is based on modeling corruption as a semi-transparent layer. This model was introduced earlier by Ahmed et al. (ICIP 2009) for the problem of blotch removal. We show much more blotch removal results than the previous work, and we extend the semi-transparent corruption model to the problem of line removal. The second contribution of this paper is an automated technique for ground-truth generation from infrared scans of corruptions. Previous ground-truth generation efforts require manually inpainting the corrupted regions. The restoration results are evaluated by comparing the reconstructed data against the ground-truth estimates. Comparisons with current blotch and line removal techniques show that the proposed corruption removal framework produces better removal and generates less restoration artifacts.

KW - Bayesian matting

KW - Blotch

KW - graph-cut

KW - ground-truth

KW - infrared

KW - line scratch

KW - transparency

UR - http://www.scopus.com/inward/record.url?scp=84887103493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887103493&partnerID=8YFLogxK

U2 - 10.1186/1687-5281-2013-33

DO - 10.1186/1687-5281-2013-33

M3 - Article

AN - SCOPUS:84887103493

VL - 2013

JO - Eurasip Journal on Image and Video Processing

JF - Eurasip Journal on Image and Video Processing

SN - 1687-5176

M1 - 33

ER -