Level lines based disocclusion

Simon MASNOU; Jean-Michel MOREL

doi:10.1109/ICIP.1998.999016

Level lines based disocclusion

Simon MASNOU^*
, Jean-Michel MOREL

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

484 Citations (Scopus)

Abstract

Object recognition, robotic vision, occluding noise removal or photograph design require the ability to perform disocclusion. We call disocclusion the recovery of hidden parts of objects in a digital image by interpolation from the vicinity of the occluded area. It is shown in this paper how disocclusion can be performed by means of a level lines structure, which offers a reliable, complete and contrast-invariant representation of an image, in contrast to edges. Level lines based disocclusion yields a solution that may have strong discontinuities, which is not possible with PDE-based interpolation. Moreover, the proposed method is fully compatible with Kanizsa's (1996) theory of "amodal completion".

Original language	English
Title of host publication	Proceedings: 1998 International Conference on Image Processing
Publisher	IEEE
Pages	259-263
Number of pages	5
ISBN (Print)	0818688211
DOIs	https://doi.org/10.1109/ICIP.1998.999016
Publication status	Published - 1998
Externally published	Yes
Event	1998 International Conference on Image Processing - Chicago, United States Duration: 4 Oct 1998 → 7 Oct 1998

Conference

Conference	1998 International Conference on Image Processing
Abbreviated title	ICIP'98
Country/Territory	United States
City	Chicago
Period	4/10/98 → 7/10/98

Bibliographical note

Acknowledgments:
The first author is grateful to Franc;oise Dibos for useful discussions.

Access to Document

10.1109/ICIP.1998.999016

Cite this

@inproceedings{be7adb70364748f3b0066bb3a5e5bb1f,

title = "Level lines based disocclusion",

abstract = "Object recognition, robotic vision, occluding noise removal or photograph design require the ability to perform disocclusion. We call disocclusion the recovery of hidden parts of objects in a digital image by interpolation from the vicinity of the occluded area. It is shown in this paper how disocclusion can be performed by means of a level lines structure, which offers a reliable, complete and contrast-invariant representation of an image, in contrast to edges. Level lines based disocclusion yields a solution that may have strong discontinuities, which is not possible with PDE-based interpolation. Moreover, the proposed method is fully compatible with Kanizsa's (1996) theory of {"}amodal completion{"}.",

author = "Simon MASNOU and Jean-Michel MOREL",

note = "Acknowledgments: The first author is grateful to Franc;oise Dibos for useful discussions.; 1998 International Conference on Image Processing, ICIP'98 ; Conference date: 04-10-1998 Through 07-10-1998",

year = "1998",

doi = "10.1109/ICIP.1998.999016",

language = "English",

isbn = "0818688211",

pages = "259--263",

booktitle = "Proceedings: 1998 International Conference on Image Processing",

publisher = "IEEE",

}

TY - GEN

T1 - Level lines based disocclusion

AU - MASNOU, Simon

AU - MOREL, Jean-Michel

N1 - Acknowledgments: The first author is grateful to Franc;oise Dibos for useful discussions.

PY - 1998

Y1 - 1998

N2 - Object recognition, robotic vision, occluding noise removal or photograph design require the ability to perform disocclusion. We call disocclusion the recovery of hidden parts of objects in a digital image by interpolation from the vicinity of the occluded area. It is shown in this paper how disocclusion can be performed by means of a level lines structure, which offers a reliable, complete and contrast-invariant representation of an image, in contrast to edges. Level lines based disocclusion yields a solution that may have strong discontinuities, which is not possible with PDE-based interpolation. Moreover, the proposed method is fully compatible with Kanizsa's (1996) theory of "amodal completion".

AB - Object recognition, robotic vision, occluding noise removal or photograph design require the ability to perform disocclusion. We call disocclusion the recovery of hidden parts of objects in a digital image by interpolation from the vicinity of the occluded area. It is shown in this paper how disocclusion can be performed by means of a level lines structure, which offers a reliable, complete and contrast-invariant representation of an image, in contrast to edges. Level lines based disocclusion yields a solution that may have strong discontinuities, which is not possible with PDE-based interpolation. Moreover, the proposed method is fully compatible with Kanizsa's (1996) theory of "amodal completion".

UR - https://www.scopus.com/pages/publications/0032307593

U2 - 10.1109/ICIP.1998.999016

DO - 10.1109/ICIP.1998.999016

M3 - Conference paper (refereed)

AN - SCOPUS:0032307593

SN - 0818688211

SP - 259

EP - 263

BT - Proceedings: 1998 International Conference on Image Processing

PB - IEEE

T2 - 1998 International Conference on Image Processing

Y2 - 4 October 1998 through 7 October 1998

ER -

Level lines based disocclusion

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this