Expression analysis/synthesis system based on emotion space constructed by multilayered neural network

Nobuo Ueki, Shigeo Morishima, Hiroshi Yamada, Hiroshi Harashima

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

To realize a user-friendly interface where a human and a computer can engage in face-to-face communication, the computer must be able to recognize the emotional state of the human by facial expressions, then synthesize and display a reasonable facial image in response. To describe this analysis and synthesis of facial expressions easily, the computer itself should have some kind of emotion model. By using a five-layered neural network which has generalization and superior nonlinear mapping performance, identity mapping training was performed using parameterized facial expressions. With respect to the space built in the middle layer of the five-layered neural network as an emotion model, emotion space was constructed. Based on this emotion space an attempt was made to build a system which can realize mappings from an expression to an emotion and from an emotion to an expression simultaneously. Moreover, to recognize a facial expression from the actual facial image of a human, the method of extracting the facial parameter from the facial points movement, is investigated.

Original languageEnglish
Pages (from-to)95-107
Number of pages13
JournalSystems and Computers in Japan
Volume25
Issue number13
Publication statusPublished - 1994 Nov 1
Externally publishedYes

Fingerprint

Neural Networks
Synthesis
Neural networks
Facial Expression
User interfaces
Identity mapping
Communication
Nonlinear Mapping
Emotion
User Interface
Model
Human

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

Expression analysis/synthesis system based on emotion space constructed by multilayered neural network. / Ueki, Nobuo; Morishima, Shigeo; Yamada, Hiroshi; Harashima, Hiroshi.

In: Systems and Computers in Japan, Vol. 25, No. 13, 01.11.1994, p. 95-107.

Research output: Contribution to journalArticle

@article{73c88856e68041f79061785d171e2720,
title = "Expression analysis/synthesis system based on emotion space constructed by multilayered neural network",
abstract = "To realize a user-friendly interface where a human and a computer can engage in face-to-face communication, the computer must be able to recognize the emotional state of the human by facial expressions, then synthesize and display a reasonable facial image in response. To describe this analysis and synthesis of facial expressions easily, the computer itself should have some kind of emotion model. By using a five-layered neural network which has generalization and superior nonlinear mapping performance, identity mapping training was performed using parameterized facial expressions. With respect to the space built in the middle layer of the five-layered neural network as an emotion model, emotion space was constructed. Based on this emotion space an attempt was made to build a system which can realize mappings from an expression to an emotion and from an emotion to an expression simultaneously. Moreover, to recognize a facial expression from the actual facial image of a human, the method of extracting the facial parameter from the facial points movement, is investigated.",
author = "Nobuo Ueki and Shigeo Morishima and Hiroshi Yamada and Hiroshi Harashima",
year = "1994",
month = "11",
day = "1",
language = "English",
volume = "25",
pages = "95--107",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "13",

}

TY - JOUR

T1 - Expression analysis/synthesis system based on emotion space constructed by multilayered neural network

AU - Ueki, Nobuo

AU - Morishima, Shigeo

AU - Yamada, Hiroshi

AU - Harashima, Hiroshi

PY - 1994/11/1

Y1 - 1994/11/1

N2 - To realize a user-friendly interface where a human and a computer can engage in face-to-face communication, the computer must be able to recognize the emotional state of the human by facial expressions, then synthesize and display a reasonable facial image in response. To describe this analysis and synthesis of facial expressions easily, the computer itself should have some kind of emotion model. By using a five-layered neural network which has generalization and superior nonlinear mapping performance, identity mapping training was performed using parameterized facial expressions. With respect to the space built in the middle layer of the five-layered neural network as an emotion model, emotion space was constructed. Based on this emotion space an attempt was made to build a system which can realize mappings from an expression to an emotion and from an emotion to an expression simultaneously. Moreover, to recognize a facial expression from the actual facial image of a human, the method of extracting the facial parameter from the facial points movement, is investigated.

AB - To realize a user-friendly interface where a human and a computer can engage in face-to-face communication, the computer must be able to recognize the emotional state of the human by facial expressions, then synthesize and display a reasonable facial image in response. To describe this analysis and synthesis of facial expressions easily, the computer itself should have some kind of emotion model. By using a five-layered neural network which has generalization and superior nonlinear mapping performance, identity mapping training was performed using parameterized facial expressions. With respect to the space built in the middle layer of the five-layered neural network as an emotion model, emotion space was constructed. Based on this emotion space an attempt was made to build a system which can realize mappings from an expression to an emotion and from an emotion to an expression simultaneously. Moreover, to recognize a facial expression from the actual facial image of a human, the method of extracting the facial parameter from the facial points movement, is investigated.

UR - http://www.scopus.com/inward/record.url?scp=0028550762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028550762&partnerID=8YFLogxK

M3 - Article

VL - 25

SP - 95

EP - 107

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 13

ER -