Missing-data recovery from dirt sparkles on degraded color films

Jinchang Ren, T. Vlachos

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A novel spatiotemporal method is proposed for detection of and recovery from dirt sparkles on degraded color films. Firstly, a confidence measurement of dirt is extracted by comparing pixel values per color component after global motion compensation. Then, candidate dirt is detected by filtering and thresholding this confidence measurement. For each candidate region of dirt, bidirectional local motion compensation is employed, and motion-compensated pixels are selected according to their confidence values, using an improved ML3Dex filter to preserve details and avoid oversmoothing of images. Experiments on real data demonstrate that our method outperforms several well-established algorithms in accuracy, efficiency, and robustness.
LanguageEnglish
Pages077001
JournalOptical Engineering : Journal of the Society of Photo-Optical Instrumentation Engineers
Volume46
Issue number7
DOIs
Publication statusPublished - 2007

Fingerprint

Color films
dirt
Motion compensation
Pixels
recovery
color
Recovery
confidence
pixels
Color
Experiments
filters

Keywords

  • image restoration
  • colour
  • optical films
  • image colour

Cite this

@article{c5c9d950ef1f42fda27dd8f94a075142,
title = "Missing-data recovery from dirt sparkles on degraded color films",
abstract = "A novel spatiotemporal method is proposed for detection of and recovery from dirt sparkles on degraded color films. Firstly, a confidence measurement of dirt is extracted by comparing pixel values per color component after global motion compensation. Then, candidate dirt is detected by filtering and thresholding this confidence measurement. For each candidate region of dirt, bidirectional local motion compensation is employed, and motion-compensated pixels are selected according to their confidence values, using an improved ML3Dex filter to preserve details and avoid oversmoothing of images. Experiments on real data demonstrate that our method outperforms several well-established algorithms in accuracy, efficiency, and robustness.",
keywords = "image restoration, colour, optical films , image colour",
author = "Jinchang Ren and T. Vlachos",
year = "2007",
doi = "10.1117/1.2751162",
language = "English",
volume = "46",
pages = "077001",
journal = "Optical Engineering : Journal of the Society of Photo-Optical Instrumentation Engineers",
issn = "0091-3286",
number = "7",

}

TY - JOUR

T1 - Missing-data recovery from dirt sparkles on degraded color films

AU - Ren, Jinchang

AU - Vlachos, T.

PY - 2007

Y1 - 2007

N2 - A novel spatiotemporal method is proposed for detection of and recovery from dirt sparkles on degraded color films. Firstly, a confidence measurement of dirt is extracted by comparing pixel values per color component after global motion compensation. Then, candidate dirt is detected by filtering and thresholding this confidence measurement. For each candidate region of dirt, bidirectional local motion compensation is employed, and motion-compensated pixels are selected according to their confidence values, using an improved ML3Dex filter to preserve details and avoid oversmoothing of images. Experiments on real data demonstrate that our method outperforms several well-established algorithms in accuracy, efficiency, and robustness.

AB - A novel spatiotemporal method is proposed for detection of and recovery from dirt sparkles on degraded color films. Firstly, a confidence measurement of dirt is extracted by comparing pixel values per color component after global motion compensation. Then, candidate dirt is detected by filtering and thresholding this confidence measurement. For each candidate region of dirt, bidirectional local motion compensation is employed, and motion-compensated pixels are selected according to their confidence values, using an improved ML3Dex filter to preserve details and avoid oversmoothing of images. Experiments on real data demonstrate that our method outperforms several well-established algorithms in accuracy, efficiency, and robustness.

KW - image restoration

KW - colour

KW - optical films

KW - image colour

U2 - 10.1117/1.2751162

DO - 10.1117/1.2751162

M3 - Article

VL - 46

SP - 077001

JO - Optical Engineering : Journal of the Society of Photo-Optical Instrumentation Engineers

T2 - Optical Engineering : Journal of the Society of Photo-Optical Instrumentation Engineers

JF - Optical Engineering : Journal of the Society of Photo-Optical Instrumentation Engineers

SN - 0091-3286

IS - 7

ER -