Towards view-invariant expression analysis using analytic shape manifolds

Sima Taheri, Pavan Turaga, Rama Chellappa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

32 Citations (Scopus)

Abstract

Facial expression analysis is one of the important components for effective human-computer interaction. However, to develop robust and generalizable models for expression analysis one needs to break the dependence of the models on the choice of the coordinate frame of the camera i.e. expression models should generalize across facial poses. To perform this systematically, one needs to understand the space of observed images subject to projective transformations. However, since the projective shape-space is cumbersome to work with, we address this problem by deriving models for expressions on the affine shape-space as an approximation to the projective shape-space by using a Riemannian interpretation of deformations that facial expressions cause on different parts of the face. We use landmark configurations to represent facial deformations and exploit the fact that the affine shape-space can be studied using the Grassmann manifold. This representation enables us to perform various expression analysis and recognition algorithms without the need for the normalization as a preprocessing step. We extend some of the available approaches for expression analysis to the Grassmann manifold and experimentally show promising results, paving the way for a more general theory of view-invariant expression analysis.

Original languageEnglish (US)
Title of host publication2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
Pages306-313
Number of pages8
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 - Santa Barbara, CA, United States
Duration: Mar 21 2011Mar 25 2011

Other

Other2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011
CountryUnited States
CitySanta Barbara, CA
Period3/21/113/25/11

Fingerprint

Human computer interaction
Cameras

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Taheri, S., Turaga, P., & Chellappa, R. (2011). Towards view-invariant expression analysis using analytic shape manifolds. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011 (pp. 306-313). [5771415] https://doi.org/10.1109/FG.2011.5771415

Towards view-invariant expression analysis using analytic shape manifolds. / Taheri, Sima; Turaga, Pavan; Chellappa, Rama.

2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 306-313 5771415.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Taheri, S, Turaga, P & Chellappa, R 2011, Towards view-invariant expression analysis using analytic shape manifolds. in 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011., 5771415, pp. 306-313, 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011, Santa Barbara, CA, United States, 3/21/11. https://doi.org/10.1109/FG.2011.5771415
Taheri S, Turaga P, Chellappa R. Towards view-invariant expression analysis using analytic shape manifolds. In 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. p. 306-313. 5771415 https://doi.org/10.1109/FG.2011.5771415
Taheri, Sima ; Turaga, Pavan ; Chellappa, Rama. / Towards view-invariant expression analysis using analytic shape manifolds. 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011. 2011. pp. 306-313
@inproceedings{6806cc3097c44a919981c7632109b743,
title = "Towards view-invariant expression analysis using analytic shape manifolds",
abstract = "Facial expression analysis is one of the important components for effective human-computer interaction. However, to develop robust and generalizable models for expression analysis one needs to break the dependence of the models on the choice of the coordinate frame of the camera i.e. expression models should generalize across facial poses. To perform this systematically, one needs to understand the space of observed images subject to projective transformations. However, since the projective shape-space is cumbersome to work with, we address this problem by deriving models for expressions on the affine shape-space as an approximation to the projective shape-space by using a Riemannian interpretation of deformations that facial expressions cause on different parts of the face. We use landmark configurations to represent facial deformations and exploit the fact that the affine shape-space can be studied using the Grassmann manifold. This representation enables us to perform various expression analysis and recognition algorithms without the need for the normalization as a preprocessing step. We extend some of the available approaches for expression analysis to the Grassmann manifold and experimentally show promising results, paving the way for a more general theory of view-invariant expression analysis.",
author = "Sima Taheri and Pavan Turaga and Rama Chellappa",
year = "2011",
doi = "10.1109/FG.2011.5771415",
language = "English (US)",
isbn = "9781424491407",
pages = "306--313",
booktitle = "2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011",

}

TY - GEN

T1 - Towards view-invariant expression analysis using analytic shape manifolds

AU - Taheri, Sima

AU - Turaga, Pavan

AU - Chellappa, Rama

PY - 2011

Y1 - 2011

N2 - Facial expression analysis is one of the important components for effective human-computer interaction. However, to develop robust and generalizable models for expression analysis one needs to break the dependence of the models on the choice of the coordinate frame of the camera i.e. expression models should generalize across facial poses. To perform this systematically, one needs to understand the space of observed images subject to projective transformations. However, since the projective shape-space is cumbersome to work with, we address this problem by deriving models for expressions on the affine shape-space as an approximation to the projective shape-space by using a Riemannian interpretation of deformations that facial expressions cause on different parts of the face. We use landmark configurations to represent facial deformations and exploit the fact that the affine shape-space can be studied using the Grassmann manifold. This representation enables us to perform various expression analysis and recognition algorithms without the need for the normalization as a preprocessing step. We extend some of the available approaches for expression analysis to the Grassmann manifold and experimentally show promising results, paving the way for a more general theory of view-invariant expression analysis.

AB - Facial expression analysis is one of the important components for effective human-computer interaction. However, to develop robust and generalizable models for expression analysis one needs to break the dependence of the models on the choice of the coordinate frame of the camera i.e. expression models should generalize across facial poses. To perform this systematically, one needs to understand the space of observed images subject to projective transformations. However, since the projective shape-space is cumbersome to work with, we address this problem by deriving models for expressions on the affine shape-space as an approximation to the projective shape-space by using a Riemannian interpretation of deformations that facial expressions cause on different parts of the face. We use landmark configurations to represent facial deformations and exploit the fact that the affine shape-space can be studied using the Grassmann manifold. This representation enables us to perform various expression analysis and recognition algorithms without the need for the normalization as a preprocessing step. We extend some of the available approaches for expression analysis to the Grassmann manifold and experimentally show promising results, paving the way for a more general theory of view-invariant expression analysis.

UR - http://www.scopus.com/inward/record.url?scp=79958745478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958745478&partnerID=8YFLogxK

U2 - 10.1109/FG.2011.5771415

DO - 10.1109/FG.2011.5771415

M3 - Conference contribution

SN - 9781424491407

SP - 306

EP - 313

BT - 2011 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops, FG 2011

ER -