DaLI

Deformation and Light Invariant Descriptor

Edgar Simo Serra, Carme Torras, Francesc Moreno-Noguer

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.

Original languageEnglish
Pages (from-to)136-154
Number of pages19
JournalInternational Journal of Computer Vision
Volume115
Issue number2
DOIs
Publication statusPublished - 2015 Feb 14
Externally publishedYes

Fingerprint

Invariance
Lighting
Principal component analysis
Fourier transforms
Sampling
Hot Temperature

Keywords

  • Deformation and illumination invariance
  • Diffusion equation
  • Heat kernel descriptors
  • Local image descriptors

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

DaLI : Deformation and Light Invariant Descriptor. / Simo Serra, Edgar; Torras, Carme; Moreno-Noguer, Francesc.

In: International Journal of Computer Vision, Vol. 115, No. 2, 14.02.2015, p. 136-154.

Research output: Contribution to journalArticle

Simo Serra, Edgar ; Torras, Carme ; Moreno-Noguer, Francesc. / DaLI : Deformation and Light Invariant Descriptor. In: International Journal of Computer Vision. 2015 ; Vol. 115, No. 2. pp. 136-154.
@article{eefbe31dec63425b9fdc3e3c6aabe246,
title = "DaLI: Deformation and Light Invariant Descriptor",
abstract = "Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.",
keywords = "Deformation and illumination invariance, Diffusion equation, Heat kernel descriptors, Local image descriptors",
author = "{Simo Serra}, Edgar and Carme Torras and Francesc Moreno-Noguer",
year = "2015",
month = "2",
day = "14",
doi = "10.1007/s11263-015-0805-1",
language = "English",
volume = "115",
pages = "136--154",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - DaLI

T2 - Deformation and Light Invariant Descriptor

AU - Simo Serra, Edgar

AU - Torras, Carme

AU - Moreno-Noguer, Francesc

PY - 2015/2/14

Y1 - 2015/2/14

N2 - Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.

AB - Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description can be used to characterize 2D image patches, and introduce DaLI, a novel feature point descriptor with high resilience to non-rigid image transformations and illumination changes. In order to build the descriptor, 2D image patches are initially treated as 3D surfaces. Patches are then described in terms of a heat kernel signature, which captures both local and global information, and shows a high degree of invariance to non-linear image warps. In addition, by further applying a logarithmic sampling and a Fourier transform, invariance to photometric changes is achieved. Finally, the descriptor is compacted by mapping it onto a low dimensional subspace computed using Principal Component Analysis, allowing for an efficient matching. A thorough experimental validation demonstrates that DaLI is significantly more discriminative and robust to illuminations changes and image transformations than state of the art descriptors, even those specifically designed to describe non-rigid deformations.

KW - Deformation and illumination invariance

KW - Diffusion equation

KW - Heat kernel descriptors

KW - Local image descriptors

UR - http://www.scopus.com/inward/record.url?scp=84942980371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942980371&partnerID=8YFLogxK

U2 - 10.1007/s11263-015-0805-1

DO - 10.1007/s11263-015-0805-1

M3 - Article

VL - 115

SP - 136

EP - 154

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 2

ER -