Affective Facial Expressions Using Auto-Associative Neural Network in Kansei Robot ‘‘Ifbot’’

Affective Facial Expressions Using Auto-Associative Neural Network in Kansei Robot ‘‘Ifbot’’

Masayoshi Kanoh (Chukyo University, Japan), Tsuyoshi Nakamura (Nagoya Institute of Technology, Japan), Shohei Kato (Nagoya Institute of Technology, Japan) and Hidenori Itoh (Nagoya Institute of Technology, Japan)
Copyright: © 2011 |Pages: 22
DOI: 10.4018/978-1-61692-797-4.ch012
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

The authors propose three methods of enabling a Kansei robot, Ifbot, to convey affective expressions using an emotion space composed of an auto-associative neural network. First, the authors attempt to extract the characteristics of Ifbot‘s facial expressions by mapping them to its emotion space using an auto-associative neural network, and create its emotion regions. They then propose a method for generating affective facial expressions using these emotion regions. The authors also propose an emotion-transition method using a path that minimizes the amount of change in an emotion space. Finally, they propose a method for creating personality using the face.
Chapter Preview
Top

2. Ifbot

Front and side views of Ifbot are shown in Figure 1. Ifbot is 45 cm tall, weighs 9.5 kg, has two arms, and moves on wheels. Ifbot received the 2003 Good Design Award #03A02002 in the product design section and in the amusement products and devices category from the Japan Industrial Design Promotion Organization.

Figure 1.

Front and side views of Ifbot

Complete Chapter List

Search this Book:
Reset