Detecting facial expressions from face images using a genetic algorithm

Jun Ohya, Fumio Kishino

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

2 Citations (Scopus)

Abstract

A new method to detect deformations of facial parts from a face image regardless of changes in the position and orientation of a face using the genetic algorithm is proposed. Facial expression parameters that are used to deform and position a 3D face model are assigned to the genes of an individual in a population. The face model is deformed and positioned according to the gene values of each individual and is observed by a virtual camera, and a face image is synthesized. The fitness which evaluates to what extent the real and synthesized face images are similar to each other is calculated. After this process is repeated for sufficient generations, the parameter estimation is obtained from the genes of the individual with the best fitness. Experimental results demonstrate the effectiveness of the method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages649-653
Number of pages5
Volume3
ISBN (Print)081867282X, 9780818672828
DOIs
Publication statusPublished - 1996
Externally publishedYes
Event13th International Conference on Pattern Recognition, ICPR 1996 - Vienna
Duration: 1996 Aug 251996 Aug 29

Other

Other13th International Conference on Pattern Recognition, ICPR 1996
CityVienna
Period96/8/2596/8/29

Fingerprint

Genes
Genetic algorithms
Parameter estimation
Cameras

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ohya, J., & Kishino, F. (1996). Detecting facial expressions from face images using a genetic algorithm. In Proceedings - International Conference on Pattern Recognition (Vol. 3, pp. 649-653). [547026] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1996.547026

Detecting facial expressions from face images using a genetic algorithm. / Ohya, Jun; Kishino, Fumio.

Proceedings - International Conference on Pattern Recognition. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 1996. p. 649-653 547026.

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

Ohya, J & Kishino, F 1996, Detecting facial expressions from face images using a genetic algorithm. in Proceedings - International Conference on Pattern Recognition. vol. 3, 547026, Institute of Electrical and Electronics Engineers Inc., pp. 649-653, 13th International Conference on Pattern Recognition, ICPR 1996, Vienna, 96/8/25. https://doi.org/10.1109/ICPR.1996.547026
Ohya J, Kishino F. Detecting facial expressions from face images using a genetic algorithm. In Proceedings - International Conference on Pattern Recognition. Vol. 3. Institute of Electrical and Electronics Engineers Inc. 1996. p. 649-653. 547026 https://doi.org/10.1109/ICPR.1996.547026
Ohya, Jun ; Kishino, Fumio. / Detecting facial expressions from face images using a genetic algorithm. Proceedings - International Conference on Pattern Recognition. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 1996. pp. 649-653
@inproceedings{bbdf8168d5974d3b9c9817f4999c9303,
title = "Detecting facial expressions from face images using a genetic algorithm",
abstract = "A new method to detect deformations of facial parts from a face image regardless of changes in the position and orientation of a face using the genetic algorithm is proposed. Facial expression parameters that are used to deform and position a 3D face model are assigned to the genes of an individual in a population. The face model is deformed and positioned according to the gene values of each individual and is observed by a virtual camera, and a face image is synthesized. The fitness which evaluates to what extent the real and synthesized face images are similar to each other is calculated. After this process is repeated for sufficient generations, the parameter estimation is obtained from the genes of the individual with the best fitness. Experimental results demonstrate the effectiveness of the method.",
author = "Jun Ohya and Fumio Kishino",
year = "1996",
doi = "10.1109/ICPR.1996.547026",
language = "English",
isbn = "081867282X",
volume = "3",
pages = "649--653",
booktitle = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Detecting facial expressions from face images using a genetic algorithm

AU - Ohya, Jun

AU - Kishino, Fumio

PY - 1996

Y1 - 1996

N2 - A new method to detect deformations of facial parts from a face image regardless of changes in the position and orientation of a face using the genetic algorithm is proposed. Facial expression parameters that are used to deform and position a 3D face model are assigned to the genes of an individual in a population. The face model is deformed and positioned according to the gene values of each individual and is observed by a virtual camera, and a face image is synthesized. The fitness which evaluates to what extent the real and synthesized face images are similar to each other is calculated. After this process is repeated for sufficient generations, the parameter estimation is obtained from the genes of the individual with the best fitness. Experimental results demonstrate the effectiveness of the method.

AB - A new method to detect deformations of facial parts from a face image regardless of changes in the position and orientation of a face using the genetic algorithm is proposed. Facial expression parameters that are used to deform and position a 3D face model are assigned to the genes of an individual in a population. The face model is deformed and positioned according to the gene values of each individual and is observed by a virtual camera, and a face image is synthesized. The fitness which evaluates to what extent the real and synthesized face images are similar to each other is calculated. After this process is repeated for sufficient generations, the parameter estimation is obtained from the genes of the individual with the best fitness. Experimental results demonstrate the effectiveness of the method.

UR - http://www.scopus.com/inward/record.url?scp=84898789371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898789371&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1996.547026

DO - 10.1109/ICPR.1996.547026

M3 - Conference contribution

SN - 081867282X

SN - 9780818672828

VL - 3

SP - 649

EP - 653

BT - Proceedings - International Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

ER -