Detection and removal of long scratch lines in aged films

Timothy K. Shih; Louis H. Lin; Wonjun Lee

doi:10.1109/ICME.2006.262576

Detection and removal of long scratch lines in aged films

Timothy K. Shih^*, Louis H. Lin, Wonjun Lee

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Citations (Scopus)

Abstract

Historical films usually have defects. We study the type of defects, and propose a series of solutions to detect defects before they are repaired by our inpainting algorithms. This paper focuses on a difficult issue to locate long vertical line defects in aged films. A progressive detection algorithm is proposed. We are able to detect more than 86% (recall rate) of effective line defects. These line defects are then removed step by step. The experiments use real historical video collected from national museum and public channel, instead of using computer generated noise. The results are visually pleasant based on our subjective evaluation by volunteers.

Original language	English
Title of host publication	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings
Pages	477-480
Number of pages	4
DOIs	https://doi.org/10.1109/ICME.2006.262576
Publication status	Published - 2006
Event	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Toronto, ON, Canada Duration: 2006 Jul 9 → 2006 Jul 12

Publication series

Name	2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings
Volume	2006

Other

Other	2006 IEEE International Conference on Multimedia and Expo, ICME 2006
Country/Territory	Canada
City	Toronto, ON
Period	06/7/9 → 06/7/12

ASJC Scopus subject areas

Media Technology
Electrical and Electronic Engineering

Access to Document

10.1109/ICME.2006.262576

Cite this

Detection and removal of long scratch lines in aged films. / Shih, Timothy K.; Lin, Louis H.; Lee, Wonjun.
2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings. 2006. p. 477-480 4036640 (2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings; Vol. 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shih, TK, Lin, LH & Lee, W 2006, Detection and removal of long scratch lines in aged films. in 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings., 4036640, 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings, vol. 2006, pp. 477-480, 2006 IEEE International Conference on Multimedia and Expo, ICME 2006, Toronto, ON, Canada, 06/7/9. https://doi.org/10.1109/ICME.2006.262576

@inproceedings{a2b88ba016d24a5b9fc0d1cabd797c2f,

title = "Detection and removal of long scratch lines in aged films",

abstract = "Historical films usually have defects. We study the type of defects, and propose a series of solutions to detect defects before they are repaired by our inpainting algorithms. This paper focuses on a difficult issue to locate long vertical line defects in aged films. A progressive detection algorithm is proposed. We are able to detect more than 86\% (recall rate) of effective line defects. These line defects are then removed step by step. The experiments use real historical video collected from national museum and public channel, instead of using computer generated noise. The results are visually pleasant based on our subjective evaluation by volunteers.",

author = "Shih, \{Timothy K.\} and Lin, \{Louis H.\} and Wonjun Lee",

year = "2006",

doi = "10.1109/ICME.2006.262576",

language = "English",

isbn = "1424403677",

series = "2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings",

pages = "477--480",

booktitle = "2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings",

}

TY - GEN

T1 - Detection and removal of long scratch lines in aged films

AU - Shih, Timothy K.

AU - Lin, Louis H.

AU - Lee, Wonjun

PY - 2006

Y1 - 2006

N2 - Historical films usually have defects. We study the type of defects, and propose a series of solutions to detect defects before they are repaired by our inpainting algorithms. This paper focuses on a difficult issue to locate long vertical line defects in aged films. A progressive detection algorithm is proposed. We are able to detect more than 86% (recall rate) of effective line defects. These line defects are then removed step by step. The experiments use real historical video collected from national museum and public channel, instead of using computer generated noise. The results are visually pleasant based on our subjective evaluation by volunteers.

AB - Historical films usually have defects. We study the type of defects, and propose a series of solutions to detect defects before they are repaired by our inpainting algorithms. This paper focuses on a difficult issue to locate long vertical line defects in aged films. A progressive detection algorithm is proposed. We are able to detect more than 86% (recall rate) of effective line defects. These line defects are then removed step by step. The experiments use real historical video collected from national museum and public channel, instead of using computer generated noise. The results are visually pleasant based on our subjective evaluation by volunteers.

UR - https://www.scopus.com/pages/publications/34247647133

UR - https://www.scopus.com/inward/citedby.url?scp=34247647133&partnerID=8YFLogxK

U2 - 10.1109/ICME.2006.262576

DO - 10.1109/ICME.2006.262576

M3 - Conference contribution

AN - SCOPUS:34247647133

SN - 1424403677

SN - 9781424403677

T3 - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings

SP - 477

EP - 480

BT - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings

T2 - 2006 IEEE International Conference on Multimedia and Expo, ICME 2006

Y2 - 9 July 2006 through 12 July 2006

ER -

Detection and removal of long scratch lines in aged films

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this