Facial expression recognition based on diffeomorphic matching

Siamak Yousefi, Minh Phuoc Nguyen, Nasser Kehtarnavaz, Yan Cao

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

9 Citations (Scopus)

Abstract

This paper presents a new framework for facial expression recognition based on diffeomorphic matching. First landmarks are selected based on a manual or automatic method. All of the landmarks from different images are registered to a reference landmark set using a rigid registration algorithm. The pair-wise geodesic distance between all sets of landmarks are then computed using diffeomorphic matching. Finally, a K-Nearest Neighbor classifier (KNN) is used to classify a query image using the geodesic distances. Both the classification and classical MultiDimensional Scaling results show that geodesic distance is more effective than Euclidean distance on capturing the face shape variation.

Original languageEnglish (US)
Title of host publication2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages4549-4552
Number of pages4
DOIs
StatePublished - Dec 1 2010
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: Sep 26 2010Sep 29 2010

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Other

Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
CountryHong Kong
CityHong Kong
Period9/26/109/29/10

Fingerprint

Classifiers

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Yousefi, S., Nguyen, M. P., Kehtarnavaz, N., & Cao, Y. (2010). Facial expression recognition based on diffeomorphic matching. In 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings (pp. 4549-4552). [5650670] (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2010.5650670

Facial expression recognition based on diffeomorphic matching. / Yousefi, Siamak; Nguyen, Minh Phuoc; Kehtarnavaz, Nasser; Cao, Yan.

2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 4549-4552 5650670 (Proceedings - International Conference on Image Processing, ICIP).

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

Yousefi, S, Nguyen, MP, Kehtarnavaz, N & Cao, Y 2010, Facial expression recognition based on diffeomorphic matching. in 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings., 5650670, Proceedings - International Conference on Image Processing, ICIP, pp. 4549-4552, 2010 17th IEEE International Conference on Image Processing, ICIP 2010, Hong Kong, Hong Kong, 9/26/10. https://doi.org/10.1109/ICIP.2010.5650670
Yousefi S, Nguyen MP, Kehtarnavaz N, Cao Y. Facial expression recognition based on diffeomorphic matching. In 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. p. 4549-4552. 5650670. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2010.5650670
Yousefi, Siamak ; Nguyen, Minh Phuoc ; Kehtarnavaz, Nasser ; Cao, Yan. / Facial expression recognition based on diffeomorphic matching. 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings. 2010. pp. 4549-4552 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{18cbbcb5bcb54aaabecbfc1613a949ca,
title = "Facial expression recognition based on diffeomorphic matching",
abstract = "This paper presents a new framework for facial expression recognition based on diffeomorphic matching. First landmarks are selected based on a manual or automatic method. All of the landmarks from different images are registered to a reference landmark set using a rigid registration algorithm. The pair-wise geodesic distance between all sets of landmarks are then computed using diffeomorphic matching. Finally, a K-Nearest Neighbor classifier (KNN) is used to classify a query image using the geodesic distances. Both the classification and classical MultiDimensional Scaling results show that geodesic distance is more effective than Euclidean distance on capturing the face shape variation.",
author = "Siamak Yousefi and Nguyen, {Minh Phuoc} and Nasser Kehtarnavaz and Yan Cao",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICIP.2010.5650670",
language = "English (US)",
isbn = "9781424479948",
series = "Proceedings - International Conference on Image Processing, ICIP",
pages = "4549--4552",
booktitle = "2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings",

}

TY - GEN

T1 - Facial expression recognition based on diffeomorphic matching

AU - Yousefi, Siamak

AU - Nguyen, Minh Phuoc

AU - Kehtarnavaz, Nasser

AU - Cao, Yan

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This paper presents a new framework for facial expression recognition based on diffeomorphic matching. First landmarks are selected based on a manual or automatic method. All of the landmarks from different images are registered to a reference landmark set using a rigid registration algorithm. The pair-wise geodesic distance between all sets of landmarks are then computed using diffeomorphic matching. Finally, a K-Nearest Neighbor classifier (KNN) is used to classify a query image using the geodesic distances. Both the classification and classical MultiDimensional Scaling results show that geodesic distance is more effective than Euclidean distance on capturing the face shape variation.

AB - This paper presents a new framework for facial expression recognition based on diffeomorphic matching. First landmarks are selected based on a manual or automatic method. All of the landmarks from different images are registered to a reference landmark set using a rigid registration algorithm. The pair-wise geodesic distance between all sets of landmarks are then computed using diffeomorphic matching. Finally, a K-Nearest Neighbor classifier (KNN) is used to classify a query image using the geodesic distances. Both the classification and classical MultiDimensional Scaling results show that geodesic distance is more effective than Euclidean distance on capturing the face shape variation.

UR - http://www.scopus.com/inward/record.url?scp=78651096059&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651096059&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5650670

DO - 10.1109/ICIP.2010.5650670

M3 - Conference contribution

SN - 9781424479948

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 4549

EP - 4552

BT - 2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings

ER -