Real-time system for measuring gaze direction and facial features: towards automatic discrimination of lies using diverse nonverbal information

Authors:
Yoshimasa Ohmoto;Kazuhiro Ueda;Takehiko Ohno
Affiliations:
The University of Tokyo, Department of General System Studies, Graduate School of Arts and Science, 3-8-1, Komaba, Meguro-ku, 153-8902, Tokyo, Japan;The University of Tokyo, Department of General System Studies, Graduate School of Arts and Science, 3-8-1, Komaba, Meguro-ku, 153-8902, Tokyo, Japan;NTT Corporation, NTT Department II, 3-8-1, Komaba, Meguro-ku, 153-8902, Tokyo, Japan
Venue:
AI & Society - Special Issue: Social intelligence design: a junction between engineering and social sciences
Year:
2008

Citing 0
Cited 3

A Method to Detect Lies in Free Communication Using Diverse Nonverbal Information: Towards an Attentive Agent

AMT '09 Proceedings of the 5th International Conference on Active Media Technology
Capture and express behavior environment (CEBE) for realizing enculturating human-agent interaction

Culture and computing
Social intelligence design for knowledge circulation

DNIS'10 Proceedings of the 6th international conference on Databases in Networked Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Interactive and autonomous agents might be common in everyday life in the future; we expect that such agents will have the ability to communicate with people naturally. For natural communication, the agents should speculate about the intentions of the people they interact with. To enable agents to speculate about intentions like deception, we focused on unconscious expressions when people tell a lie. However, there is no system that can meet the necessary conditions for measuring nonverbal information in natural communication. Therefore, we made a real-time system for measuring gaze direction and facial features. We conducted experiments for discriminating lies by using the system in a situation similar to actual communication. As a result, we found that we could discriminate lies by using diverse nonverbal information in the same way people did.