Level lines based disocclusion

Simon Masnou; Jean Michel Morel

doi:10.1109/icip.1998.999016

Level lines based disocclusion

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

482 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 level lines structure, which offers a reliable, complete and contrast-invariant representation of 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 theory of 'amodal completion'.

Original language	English
Title of host publication	IEEE International Conference on Image Processing
Publisher	IEEE Computer Society
Pages	259-263
Volume	3
DOIs	https://doi.org/10.1109/icip.1998.999016
Publication status	Published - 1998
Externally published	Yes
Event	Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) - Chicago, IL, USA Duration: 4 Oct 1998 → 7 Oct 1998

Conference

Conference	Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3)
City	Chicago, IL, USA
Period	4/10/98 → 7/10/98

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Access Output

10.1109/icip.1998.999016

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{2a97ce7d5ff74b3bb713599d72c6fbde,

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 level lines structure, which offers a reliable, complete and contrast-invariant representation of 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 theory of 'amodal completion'.",

author = "Simon Masnou and Morel, {Jean Michel}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected]. ; Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) ; Conference date: 04-10-1998 Through 07-10-1998",

year = "1998",

doi = "10.1109/icip.1998.999016",

language = "English",

volume = "3",

pages = "259--263",

booktitle = "IEEE International Conference on Image Processing",

publisher = "IEEE Computer Society",

address = "United States",

}

TY - GEN

T1 - Level lines based disocclusion

AU - Masnou, Simon

AU - Morel, Jean Michel

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

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 level lines structure, which offers a reliable, complete and contrast-invariant representation of 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 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 level lines structure, which offers a reliable, complete and contrast-invariant representation of 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 theory of 'amodal completion'.

UR - http://www.scopus.com/inward/record.url?scp=0032307593&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0032307593&origin=recordpage

U2 - 10.1109/icip.1998.999016

DO - 10.1109/icip.1998.999016

M3 - RGC 32 - Refereed conference paper (with host publication)

VL - 3

SP - 259

EP - 263

BT - IEEE International Conference on Image Processing

PB - IEEE Computer Society

T2 - Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3)

Y2 - 4 October 1998 through 7 October 1998

ER -

Level lines based disocclusion

Abstract

Conference

Bibliographical note

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this