Recognizing abruptly changing facial expressions from time-sequential face images

Takahiro Otsuka, Jun Ohya

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

6 Citations (Scopus)

Abstract

This paper proposes a method that can spot and recognize each facial expression from time-sequential images that contain multiple facial expressions that could abruptly change from one expression to another expression. Previously, the authors have proposed an HMM (Hidden Markov Models) based method for recognizing a spotted facial expression. In this paper, to HMM, we add states corresponding to the simultaneous motion of two different facial expressions: i.e. a muscle relaxation for one expression and a muscle contraction for another expression. Then, the added states are each linked from the HMM apex state of one expression and are linked to that of another expression. Experimental results showed that for most pairs of expressions the change in expression can be recognized accurately. In addition, recognition rate for very fast change of expressions improved significantly. The proposed method was applied to regenerate facial expressions on a synthesized character to show the method's effectiveness in obtaining facial motion information.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages808-813
Number of pages6
DOIs
Publication statusPublished - 1998
Externally publishedYes
EventProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Santa Barbara, CA, USA
Duration: 1998 Jun 231998 Jun 25

Other

OtherProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySanta Barbara, CA, USA
Period98/6/2398/6/25

Fingerprint

Hidden Markov models
Muscle

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering

Cite this

Otsuka, T., & Ohya, J. (1998). Recognizing abruptly changing facial expressions from time-sequential face images. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 808-813) https://doi.org/10.1109/CVPR.1998.698697

Recognizing abruptly changing facial expressions from time-sequential face images. / Otsuka, Takahiro; Ohya, Jun.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. p. 808-813.

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

Otsuka, T & Ohya, J 1998, Recognizing abruptly changing facial expressions from time-sequential face images. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 808-813, Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, 98/6/23. https://doi.org/10.1109/CVPR.1998.698697
Otsuka T, Ohya J. Recognizing abruptly changing facial expressions from time-sequential face images. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. p. 808-813 https://doi.org/10.1109/CVPR.1998.698697
Otsuka, Takahiro ; Ohya, Jun. / Recognizing abruptly changing facial expressions from time-sequential face images. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. pp. 808-813
@inproceedings{a95571ec25c84be39710da0edab13f69,
title = "Recognizing abruptly changing facial expressions from time-sequential face images",
abstract = "This paper proposes a method that can spot and recognize each facial expression from time-sequential images that contain multiple facial expressions that could abruptly change from one expression to another expression. Previously, the authors have proposed an HMM (Hidden Markov Models) based method for recognizing a spotted facial expression. In this paper, to HMM, we add states corresponding to the simultaneous motion of two different facial expressions: i.e. a muscle relaxation for one expression and a muscle contraction for another expression. Then, the added states are each linked from the HMM apex state of one expression and are linked to that of another expression. Experimental results showed that for most pairs of expressions the change in expression can be recognized accurately. In addition, recognition rate for very fast change of expressions improved significantly. The proposed method was applied to regenerate facial expressions on a synthesized character to show the method's effectiveness in obtaining facial motion information.",
author = "Takahiro Otsuka and Jun Ohya",
year = "1998",
doi = "10.1109/CVPR.1998.698697",
language = "English",
isbn = "0818684976",
pages = "808--813",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Recognizing abruptly changing facial expressions from time-sequential face images

AU - Otsuka, Takahiro

AU - Ohya, Jun

PY - 1998

Y1 - 1998

N2 - This paper proposes a method that can spot and recognize each facial expression from time-sequential images that contain multiple facial expressions that could abruptly change from one expression to another expression. Previously, the authors have proposed an HMM (Hidden Markov Models) based method for recognizing a spotted facial expression. In this paper, to HMM, we add states corresponding to the simultaneous motion of two different facial expressions: i.e. a muscle relaxation for one expression and a muscle contraction for another expression. Then, the added states are each linked from the HMM apex state of one expression and are linked to that of another expression. Experimental results showed that for most pairs of expressions the change in expression can be recognized accurately. In addition, recognition rate for very fast change of expressions improved significantly. The proposed method was applied to regenerate facial expressions on a synthesized character to show the method's effectiveness in obtaining facial motion information.

AB - This paper proposes a method that can spot and recognize each facial expression from time-sequential images that contain multiple facial expressions that could abruptly change from one expression to another expression. Previously, the authors have proposed an HMM (Hidden Markov Models) based method for recognizing a spotted facial expression. In this paper, to HMM, we add states corresponding to the simultaneous motion of two different facial expressions: i.e. a muscle relaxation for one expression and a muscle contraction for another expression. Then, the added states are each linked from the HMM apex state of one expression and are linked to that of another expression. Experimental results showed that for most pairs of expressions the change in expression can be recognized accurately. In addition, recognition rate for very fast change of expressions improved significantly. The proposed method was applied to regenerate facial expressions on a synthesized character to show the method's effectiveness in obtaining facial motion information.

UR - http://www.scopus.com/inward/record.url?scp=0032291703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032291703&partnerID=8YFLogxK

U2 - 10.1109/CVPR.1998.698697

DO - 10.1109/CVPR.1998.698697

M3 - Conference contribution

AN - SCOPUS:0032291703

SN - 0818684976

SP - 808

EP - 813

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -