Statistical shape analysis for face movement manifold modeling

Xiaokan Wang, Xia Mao, Catalin Daniel Caleanu, Mitsuru Ishizuka

Research output: Contribution to journalArticle

Abstract

The inter-frame information for analyzing human face movement manifold is modeled by the statistical shape theory. Using the Riemannian geometry principles, we map a sequence of face shapes to a unified tangent space and obtain a curve corresponding to the face movement. The experimental results show that the face movement sequence forms a trajectory in a complex tangent space. Furthermore, the extent and type of face expression could be depicted as the range and direction of the curve. This represents a novel approach for face movement classification using shape-based analysis.

Original languageEnglish
Article number037004
JournalOptical Engineering
Volume51
Issue number3
DOIs
Publication statusPublished - 2012 Mar
Externally publishedYes

Fingerprint

Trajectories
Geometry
tangents
curves
trajectories
geometry

Keywords

  • Face movement
  • Manifold learning
  • Statistical shape theory

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

Statistical shape analysis for face movement manifold modeling. / Wang, Xiaokan; Mao, Xia; Caleanu, Catalin Daniel; Ishizuka, Mitsuru.

In: Optical Engineering, Vol. 51, No. 3, 037004, 03.2012.

Research output: Contribution to journalArticle

Wang, Xiaokan ; Mao, Xia ; Caleanu, Catalin Daniel ; Ishizuka, Mitsuru. / Statistical shape analysis for face movement manifold modeling. In: Optical Engineering. 2012 ; Vol. 51, No. 3.
@article{70e549b4d1cf45cab5bbed63f08e1b88,
title = "Statistical shape analysis for face movement manifold modeling",
abstract = "The inter-frame information for analyzing human face movement manifold is modeled by the statistical shape theory. Using the Riemannian geometry principles, we map a sequence of face shapes to a unified tangent space and obtain a curve corresponding to the face movement. The experimental results show that the face movement sequence forms a trajectory in a complex tangent space. Furthermore, the extent and type of face expression could be depicted as the range and direction of the curve. This represents a novel approach for face movement classification using shape-based analysis.",
keywords = "Face movement, Manifold learning, Statistical shape theory",
author = "Xiaokan Wang and Xia Mao and Caleanu, {Catalin Daniel} and Mitsuru Ishizuka",
year = "2012",
month = "3",
doi = "10.1117/1.OE.51.3.037004",
language = "English",
volume = "51",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "3",

}

TY - JOUR

T1 - Statistical shape analysis for face movement manifold modeling

AU - Wang, Xiaokan

AU - Mao, Xia

AU - Caleanu, Catalin Daniel

AU - Ishizuka, Mitsuru

PY - 2012/3

Y1 - 2012/3

N2 - The inter-frame information for analyzing human face movement manifold is modeled by the statistical shape theory. Using the Riemannian geometry principles, we map a sequence of face shapes to a unified tangent space and obtain a curve corresponding to the face movement. The experimental results show that the face movement sequence forms a trajectory in a complex tangent space. Furthermore, the extent and type of face expression could be depicted as the range and direction of the curve. This represents a novel approach for face movement classification using shape-based analysis.

AB - The inter-frame information for analyzing human face movement manifold is modeled by the statistical shape theory. Using the Riemannian geometry principles, we map a sequence of face shapes to a unified tangent space and obtain a curve corresponding to the face movement. The experimental results show that the face movement sequence forms a trajectory in a complex tangent space. Furthermore, the extent and type of face expression could be depicted as the range and direction of the curve. This represents a novel approach for face movement classification using shape-based analysis.

KW - Face movement

KW - Manifold learning

KW - Statistical shape theory

UR - http://www.scopus.com/inward/record.url?scp=84891775360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891775360&partnerID=8YFLogxK

U2 - 10.1117/1.OE.51.3.037004

DO - 10.1117/1.OE.51.3.037004

M3 - Article

VL - 51

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 3

M1 - 037004

ER -