ServicenavigationHauptnavigationTrailKarteikarten


Research unit
EU RFP
Project number
00.0504
Project title
MUHCI: Multi-modal human-Computer interaction

Texts for this project

 GermanFrenchItalianEnglish
Key words
-
-
-
Anzeigen
Alternative project number
-
-
-
Anzeigen
Research programs
-
-
-
Anzeigen
Short description
-
-
-
Anzeigen
Partners and International Organizations
-
-
-
Anzeigen
Abstract
-
-
-
Anzeigen
References in databases
-
-
-
Anzeigen

Inserted texts


CategoryText
Key words
(English)
Human-computer interaction; graphics; speech; gesture; facial animation;
Education; Training; Scientific Research; Social Aspects
Alternative project number
(English)
EU project number: HPRN-CT-00111
Research programs
(English)
EU-programme: 5. Frame Research Programme - 4.1.1 Research training networks
Short description
(English)
See abstract
Partners and International Organizations
(English)
Coordinator: Aristotle University of Thessaloniki (EL)
Abstract
(English)
The MUHCI project aims at every aspect of the interaction between humans and computers. The partners in the MUHCI project are specialists in different areas: face recognition and tracking, graphics, audio-visual speech, emotive speech and animation and more.

In the first year, MIRALab has worked on developing a set of plug-ins for 3D Studio Max that can construct and animate an MPEG-4 face. In the second year, we especially focused on testing the 3D Modelling plugin and building the 3D Animation plugin. Both use the same library for deformation, but animation requires an extra effort: partly because animation constraints were added to the original library and partly because new animation file format interfaces had to be developed.

A second task that MIRALab has performed was the development of a real-time facial expression tracker. Based on neural network technology, we developed an application that converts raw video data into FAP (MPEG-4 facial animation data). The FAP data is subsequently classified into expression data that can be used for different purposes: facial animation cloning (using the FAP data) and the expression data can be used as input for AI systems.

In the third year of the project, MIRALab will concentrate on techniques for facial animation on the web and how to obtain databases of virtual faces. Also, MIRALab will work on face cloning techniques.
References in databases
(English)
Swiss Database: Euro-DB of the
State Secretariat for Education and Research
Hallwylstrasse 4
CH-3003 Berne, Switzerland
Tel. +41 31 322 74 82
Swiss Project-Number: 00.0504