Visualization Methods of Emotion, Atmosphere, and Kansei


Kaoru Hirota, Fangyan Dong
Tokyo Institute of Technology

Abstract:

The presenters’ group at Tokyo Institute of Technology has been studying on various visualization methods of subjective evaluation information based on mainly fuzzy theory. Three of them are introduced in this plenary talk.

A deep level emotion understanding method has been proposed for agent to agent communication, where customized learning knowledge of an observed agent is used with the observed input information from Kinect. It aims to realize agent dependent emotion understanding by utilizing special customized knowledge of the agent, rather than ordinary surface level emotion understanding by using visual/acoustic/distance information without any customized knowledge. Emotion vector is represented in the affinity pleasure arousal space [-1,1]3 on “Affinity- No-affinity”, “Pleasure-Displeasure”, and “Arousal-Sleep” axes, and.is also represented by a visualization method using shape, brightness, and size. The pleasure-displeasure axis uses a circle, cross, and the intermediate shapes to represent pleasure to displeasure. The brightness represents the arousal-sleep axis where high arousal the figure becomes white, high sleepy becomes black. Finally the size represents the affinity - no-affinity. An example of demonstration scenario is shown by using illustration program.

The second is about visualization of Fuzzy Atmosfield (FA) which is proposed to express the atmosphere in humans-robots communication. The FA is characterized by a 3D fuzzy cubic space with “friendly-hostile”, “lively-calm”, and “casual-formal” based on a cognitive science experiments and principal component analysis. The atmosphere in the communication is expressed by a point in the 3D fuzzy cubic space and is supposed to be varying/moving in the space time by time. To understand easily such movement of the atmosphere, a graphical representation method is also proposed, where “friendly-hostile” information is represented by “shape”, “lively-calm” by “color”, and “casual-formal” by “size”. To illustrate the FA and its visualization method, a demonstration scenario “enjoying home party by five eye robots and four humans” is introduced/demonstrated.

The last is about visualization of KANSEI texture which is expressed by a three-dimensional cube [-1,1]3 and aims to represent visual and/or texture information of an object photo/movie for compensating the information gap between the real object and its photo/movie image. Its graphical visualization method is also proposed. The proposal is expected to be used to get visual/tactile information of the objects in net shopping, robot vision, telemedicine, e-learning, and others, where the real objects are not available but only their still/dynamic images with brief text explanation are obtainable.

About the Speaker:

Received Dr. E. degrees from Tokyo Institute of Technology in 1979. After his career at Sagami Institute of Technology and Hosei University, he has been with Tokyo Institute of Technology. His research interests include fuzzy systems, intelligent robot, and image understanding. He experienced a president/fellow of IFSA (International Fuzzy Systems Association), and a president of SOFT (Japan Society for Fuzzy Theory and Systems.) He is a chief editor of J. of Advanced Computational Intelligence and Intelligent Informatics. Banki Donat Medal, Henri Coanda Medal, Grigore MOISIL Award, SOFT best paper award, Acoustical Society of Japan best paper award(twice), honorary professorships from de La Salle University and Changchun Univ. of Science & Technology, and Honoris Causa from Bulacan state university, Budapest Technical University, and Szechenyi Istvan University were awarded to him. He organized more than 20 international conferences/symposiums as a founding/general/program chair. He has been publishing about 300 journal papers, 50 books, and 500 conference papers.