On the equivalence of common approaches to lighting insensitive recognition

Margarita Osadchy; David W. Jacobs; Michael Lindenbaum

doi:10.1109/ICCV.2005.179

On the equivalence of common approaches to lighting insensitive recognition

Margarita Osadchy, David W. Jacobs, Michael Lindenbaum

Department of Computer Science

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

Abstract

Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighting conditions, even for 3D scenes. We analyze two common approaches to image comparison that are invariant, normalized correlation using small correlation windows, and comparison based on a large set of oriented difference of Gaussian filters. We show analytically that these methods calculate a monotonic (cosine) function of the gradient direction difference and hence are equivalent to the direction of gradient method. Our analysis is supported with experiments on both synthetic and real scenes.

Original language	English
Title of host publication	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages	1721-1726
Number of pages	6
DOIs	https://doi.org/10.1109/ICCV.2005.179
State	Published - 2005
Event	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China Duration: 17 Oct 2005 → 20 Oct 2005

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	II

Conference

Conference	Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Country/Territory	China
City	Beijing
Period	17/10/05 → 20/10/05

Bibliographical note

Funding Information:
Acknowledgements--This work was supported by the Hungarian Research Fund (L.N.), a fellowship from Pro Cultura Renovanda Hungariae (A.M.C.) and l'Association Franqaise contre les Myopathies.

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/ICCV.2005.179

Cite this

@inproceedings{09fd062c9db640319c1661cdc5e596ce,

title = "On the equivalence of common approaches to lighting insensitive recognition",

abstract = "Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighting conditions, even for 3D scenes. We analyze two common approaches to image comparison that are invariant, normalized correlation using small correlation windows, and comparison based on a large set of oriented difference of Gaussian filters. We show analytically that these methods calculate a monotonic (cosine) function of the gradient direction difference and hence are equivalent to the direction of gradient method. Our analysis is supported with experiments on both synthetic and real scenes.",

author = "Margarita Osadchy and Jacobs, {David W.} and Michael Lindenbaum",

note = "Funding Information: Acknowledgements--This work was supported by the Hungarian Research Fund (L.N.), a fellowship from Pro Cultura Renovanda Hungariae (A.M.C.) and l'Association Franqaise contre les Myopathies.; Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 ; Conference date: 17-10-2005 Through 20-10-2005",

year = "2005",

doi = "10.1109/ICCV.2005.179",

language = "English",

isbn = "076952334X",

series = "Proceedings of the IEEE International Conference on Computer Vision",

pages = "1721--1726",

booktitle = "Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005",

}

Osadchy, M, Jacobs, DW & Lindenbaum, M 2005, On the equivalence of common approaches to lighting insensitive recognition. in Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005., 1544924, Proceedings of the IEEE International Conference on Computer Vision, vol. II, pp. 1721-1726, Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, 17/10/05. https://doi.org/10.1109/ICCV.2005.179

On the equivalence of common approaches to lighting insensitive recognition. / Osadchy, Margarita; Jacobs, David W.; Lindenbaum, Michael.
Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005. 2005. p. 1721-1726 1544924 (Proceedings of the IEEE International Conference on Computer Vision; Vol. II).

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

TY - GEN

T1 - On the equivalence of common approaches to lighting insensitive recognition

AU - Osadchy, Margarita

AU - Jacobs, David W.

AU - Lindenbaum, Michael

N1 - Funding Information: Acknowledgements--This work was supported by the Hungarian Research Fund (L.N.), a fellowship from Pro Cultura Renovanda Hungariae (A.M.C.) and l'Association Franqaise contre les Myopathies.

PY - 2005

Y1 - 2005

N2 - Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighting conditions, even for 3D scenes. We analyze two common approaches to image comparison that are invariant, normalized correlation using small correlation windows, and comparison based on a large set of oriented difference of Gaussian filters. We show analytically that these methods calculate a monotonic (cosine) function of the gradient direction difference and hence are equivalent to the direction of gradient method. Our analysis is supported with experiments on both synthetic and real scenes.

AB - Lighting variation is commonly handled by methods invariant to additive and multiplicative changes in image intensity. It has been demonstrated that comparing images using the direction of the gradient can produce broader insensitivity to changes in lighting conditions, even for 3D scenes. We analyze two common approaches to image comparison that are invariant, normalized correlation using small correlation windows, and comparison based on a large set of oriented difference of Gaussian filters. We show analytically that these methods calculate a monotonic (cosine) function of the gradient direction difference and hence are equivalent to the direction of gradient method. Our analysis is supported with experiments on both synthetic and real scenes.

UR - http://www.scopus.com/inward/record.url?scp=33745915267&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2005.179

DO - 10.1109/ICCV.2005.179

M3 - Conference contribution

AN - SCOPUS:33745915267

SN - 076952334X

SN - 9780769523347

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1721

EP - 1726

BT - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

T2 - Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005

Y2 - 17 October 2005 through 20 October 2005

ER -

On the equivalence of common approaches to lighting insensitive recognition

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this