Shape recognition algorithm robust under partial occlusions and affine deformations

J. L. LISANI; L. MOISAN; P. MONASSE; J. M. MOREL

doi:10.1007/10722604_2

Shape recognition algorithm robust under partial occlusions and affine deformations

J. L. LISANI
, L. MOISAN
, P. MONASSE
, J. M. MOREL

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

Abstract

We design a generic contrast and affine invariant planar shape recognition algorithm. By generic, we mean an algorithm which delivers a list of all shapes two digital images have in common, up to any affine transform or contrast change. Affine invariance must not be considered as a weak requirement in shape recognition since it is well known that if 3D objects with smooth boundaries are being observed, then the deformation of the objects’ images, far enough from the occlusion boundaries, is locally an affine transform. We define as ”shape elements” all pieces of level lines of the image. We then discuss an efficient local encoding of the shape elements. We finally show experiments. Applications aimed at include image registration, image indexing, optical flow.

Original language	English
Title of host publication	Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings
Editors	Hans-Hellmut NAGEL, Francisco J. PERALES LOPEZ
Publisher	Springer
Pages	15-26
Number of pages	12
ISBN (Electronic)	9783540445913
ISBN (Print)	9783540679127
DOIs	https://doi.org/10.1007/10722604_2
Publication status	Published - 2000
Externally published	Yes

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	1899
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name	International Conference on Articulated Motion and Deformable Objects
Publisher	Springer
Volume	AMDO 2000

Access to Document

10.1007/10722604_2

Cite this

LISANI, J. L., MOISAN, L., MONASSE, P., & MOREL, J. M. (2000). Shape recognition algorithm robust under partial occlusions and affine deformations. In H.-H. NAGEL, & F. J. PERALES LOPEZ (Eds.), Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings (pp. 15-26). (Lecture Notes in Computer Science; Vol. 1899), (International Conference on Articulated Motion and Deformable Objects; Vol. AMDO 2000). Springer. https://doi.org/10.1007/10722604_2

LISANI, J. L. ; MOISAN, L. ; MONASSE, P. et al. / Shape recognition algorithm robust under partial occlusions and affine deformations. Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings. editor / Hans-Hellmut NAGEL ; Francisco J. PERALES LOPEZ. Springer, 2000. pp. 15-26 (Lecture Notes in Computer Science). (International Conference on Articulated Motion and Deformable Objects).

@inproceedings{064bee35da8a48dfaa3180d0e002c7ec,

title = "Shape recognition algorithm robust under partial occlusions and affine deformations",

abstract = "We design a generic contrast and affine invariant planar shape recognition algorithm. By generic, we mean an algorithm which delivers a list of all shapes two digital images have in common, up to any affine transform or contrast change. Affine invariance must not be considered as a weak requirement in shape recognition since it is well known that if 3D objects with smooth boundaries are being observed, then the deformation of the objects{\textquoteright} images, far enough from the occlusion boundaries, is locally an affine transform. We define as ”shape elements” all pieces of level lines of the image. We then discuss an efficient local encoding of the shape elements. We finally show experiments. Applications aimed at include image registration, image indexing, optical flow.",

author = "LISANI, \{J. L.\} and L. MOISAN and P. MONASSE and MOREL, \{J. M.\}",

year = "2000",

doi = "10.1007/10722604\_2",

language = "English",

isbn = "9783540679127",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "15--26",

editor = "Hans-Hellmut NAGEL and \{PERALES LOPEZ\}, \{Francisco J.\}",

booktitle = "Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings",

}

LISANI, JL, MOISAN, L, MONASSE, P & MOREL, JM 2000, Shape recognition algorithm robust under partial occlusions and affine deformations. in H-H NAGEL & FJ PERALES LOPEZ (eds), Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings. Lecture Notes in Computer Science, vol. 1899, International Conference on Articulated Motion and Deformable Objects, vol. AMDO 2000, Springer, pp. 15-26. https://doi.org/10.1007/10722604_2

Shape recognition algorithm robust under partial occlusions and affine deformations. / LISANI, J. L.; MOISAN, L.; MONASSE, P. et al.
Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings. ed. / Hans-Hellmut NAGEL; Francisco J. PERALES LOPEZ. Springer, 2000. p. 15-26 (Lecture Notes in Computer Science; Vol. 1899), (International Conference on Articulated Motion and Deformable Objects; Vol. AMDO 2000).

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

TY - GEN

T1 - Shape recognition algorithm robust under partial occlusions and affine deformations

AU - LISANI, J. L.

AU - MOISAN, L.

AU - MONASSE, P.

AU - MOREL, J. M.

PY - 2000

Y1 - 2000

N2 - We design a generic contrast and affine invariant planar shape recognition algorithm. By generic, we mean an algorithm which delivers a list of all shapes two digital images have in common, up to any affine transform or contrast change. Affine invariance must not be considered as a weak requirement in shape recognition since it is well known that if 3D objects with smooth boundaries are being observed, then the deformation of the objects’ images, far enough from the occlusion boundaries, is locally an affine transform. We define as ”shape elements” all pieces of level lines of the image. We then discuss an efficient local encoding of the shape elements. We finally show experiments. Applications aimed at include image registration, image indexing, optical flow.

AB - We design a generic contrast and affine invariant planar shape recognition algorithm. By generic, we mean an algorithm which delivers a list of all shapes two digital images have in common, up to any affine transform or contrast change. Affine invariance must not be considered as a weak requirement in shape recognition since it is well known that if 3D objects with smooth boundaries are being observed, then the deformation of the objects’ images, far enough from the occlusion boundaries, is locally an affine transform. We define as ”shape elements” all pieces of level lines of the image. We then discuss an efficient local encoding of the shape elements. We finally show experiments. Applications aimed at include image registration, image indexing, optical flow.

UR - https://www.scopus.com/pages/publications/84944052005

U2 - 10.1007/10722604_2

DO - 10.1007/10722604_2

M3 - Conference paper (refereed)

AN - SCOPUS:84944052005

SN - 9783540679127

T3 - Lecture Notes in Computer Science

SP - 15

EP - 26

BT - Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings

A2 - NAGEL, Hans-Hellmut

A2 - PERALES LOPEZ, Francisco J.

PB - Springer

ER -

LISANI JL, MOISAN L, MONASSE P, MOREL JM. Shape recognition algorithm robust under partial occlusions and affine deformations. In NAGEL HH, PERALES LOPEZ FJ, editors, Articulated Motion and Deformable Objects: First International Workshop, AMDO 2000, Palma de Mallorca, Spain, September 2000, ProceedingsProceedings. Springer. 2000. p. 15-26. (Lecture Notes in Computer Science). (International Conference on Articulated Motion and Deformable Objects). doi: 10.1007/10722604_2

Shape recognition algorithm robust under partial occlusions and affine deformations

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this