Methods and Models for Identifying Human Emotions by Recognition Gestures and Motion

DOI

10.2991/3ca-13.2013.17How to use a DOI?

Keywords

human emotions, gestures and movements, fuzzy temporal event, Kinect

Abstract

The paper describes a methodology, models and automated system for an identification of human emotions based on analysis of body movements, a recognition of characteristic gestures and poses. In the model of person emotions, the typical body movements are formalized with linguistic variables and fuzzy hypergraphs for temporal events. Emotional states of the real person recognized with the automated system are presented in a limited natural language. Shown the allocation of granules and related postures. Compliance granules poses and basic emotional states by K. Izard is presented. The article shows how to apply system for recognition and translation in real time gestures of the Russian deaf language in the text and the text in gestures. The system is intended for training of children with hearing disabilities and adults who need to learn sign language.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - V.L. Rozaliev
AU  - A.V. Zaboleeva-Zotova
PY  - 2013/04
DA  - 2013/04
TI  - Methods and Models for Identifying Human Emotions by Recognition Gestures and Motion
BT  - Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation
PB  - Atlantis Press
SP  - 67
EP  - 70
SN  - 1951-6851
UR  - https://doi.org/10.2991/3ca-13.2013.17
DO  - 10.2991/3ca-13.2013.17
ID  - Rozaliev2013/04
ER  -