Detection and Recovery of Film Dirt for Archive Restoration Applications

Jinchang Ren, T. Vlachos

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

6 Citations (Scopus)

Abstract

A novel spatio-temporal method is proposed for film dirt
detection and recovery. Firstly, a more reliable confidence
measurement of dirt is extracted for color films.
False alarms caused by motion are filtered using consistency
checks among several measurements. Then, candidate
dirt is detected by filtering and thresholding this
confidence measurement. Finally, bi-directional local
motion compensation and ML3Dex filtering are taken for
the recovery of dirt pixels. Experiments on real data
demonstrate the efficiency and effectiveness of our
method in terms of both detection and recovery of dirt.
Original languageEnglish
Title of host publicationProceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007)
PublisherIEEE
Pages21-24
Number of pages4
Volume4
ISBN (Print)978-1-4244-1437-6
DOIs
Publication statusPublished - 2007
Event2007 14th IEEE International Conference on Image Processing - Hyatt Regency San Antonio, San Antonio, United States
Duration: 16 Sep 200719 Sep 2007

Conference

Conference2007 14th IEEE International Conference on Image Processing
Abbreviated titleICIP 2007
CountryUnited States
CitySan Antonio
Period16/09/0719/09/07

Fingerprint

Restoration
Recovery
Color films
Pixels
Experiments
Compensation and Redress

Keywords

  • film dirt detection
  • archive restoration

Cite this

Ren, J., & Vlachos, T. (2007). Detection and Recovery of Film Dirt for Archive Restoration Applications. In Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007) (Vol. 4, pp. 21-24). IEEE. https://doi.org/10.1109/ICIP.2007.4379943
Ren, Jinchang ; Vlachos, T. / Detection and Recovery of Film Dirt for Archive Restoration Applications. Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007). Vol. 4 IEEE, 2007. pp. 21-24
@inproceedings{1b05f8dab2cc4931a6aef2aef25cad98,
title = "Detection and Recovery of Film Dirt for Archive Restoration Applications",
abstract = "A novel spatio-temporal method is proposed for film dirtdetection and recovery. Firstly, a more reliable confidencemeasurement of dirt is extracted for color films.False alarms caused by motion are filtered using consistencychecks among several measurements. Then, candidatedirt is detected by filtering and thresholding thisconfidence measurement. Finally, bi-directional localmotion compensation and ML3Dex filtering are taken forthe recovery of dirt pixels. Experiments on real datademonstrate the efficiency and effectiveness of ourmethod in terms of both detection and recovery of dirt.",
keywords = "film dirt detection, archive restoration",
author = "Jinchang Ren and T. Vlachos",
year = "2007",
doi = "10.1109/ICIP.2007.4379943",
language = "English",
isbn = "978-1-4244-1437-6",
volume = "4",
pages = "21--24",
booktitle = "Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007)",
publisher = "IEEE",

}

Ren, J & Vlachos, T 2007, Detection and Recovery of Film Dirt for Archive Restoration Applications. in Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007). vol. 4, IEEE, pp. 21-24, 2007 14th IEEE International Conference on Image Processing , San Antonio, United States, 16/09/07. https://doi.org/10.1109/ICIP.2007.4379943

Detection and Recovery of Film Dirt for Archive Restoration Applications. / Ren, Jinchang; Vlachos, T.

Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007). Vol. 4 IEEE, 2007. p. 21-24.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Detection and Recovery of Film Dirt for Archive Restoration Applications

AU - Ren, Jinchang

AU - Vlachos, T.

PY - 2007

Y1 - 2007

N2 - A novel spatio-temporal method is proposed for film dirtdetection and recovery. Firstly, a more reliable confidencemeasurement of dirt is extracted for color films.False alarms caused by motion are filtered using consistencychecks among several measurements. Then, candidatedirt is detected by filtering and thresholding thisconfidence measurement. Finally, bi-directional localmotion compensation and ML3Dex filtering are taken forthe recovery of dirt pixels. Experiments on real datademonstrate the efficiency and effectiveness of ourmethod in terms of both detection and recovery of dirt.

AB - A novel spatio-temporal method is proposed for film dirtdetection and recovery. Firstly, a more reliable confidencemeasurement of dirt is extracted for color films.False alarms caused by motion are filtered using consistencychecks among several measurements. Then, candidatedirt is detected by filtering and thresholding thisconfidence measurement. Finally, bi-directional localmotion compensation and ML3Dex filtering are taken forthe recovery of dirt pixels. Experiments on real datademonstrate the efficiency and effectiveness of ourmethod in terms of both detection and recovery of dirt.

KW - film dirt detection

KW - archive restoration

U2 - 10.1109/ICIP.2007.4379943

DO - 10.1109/ICIP.2007.4379943

M3 - Conference contribution book

SN - 978-1-4244-1437-6

VL - 4

SP - 21

EP - 24

BT - Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007)

PB - IEEE

ER -

Ren J, Vlachos T. Detection and Recovery of Film Dirt for Archive Restoration Applications. In Proceedings of IEEE International Conference on Image Processing, 2007. (ICIP 2007). Vol. 4. IEEE. 2007. p. 21-24 https://doi.org/10.1109/ICIP.2007.4379943