Title :
Neurofuzzy recognition and generation of facial features in talking heads
Author :
Garzon, Max H. ; Ankaraju, Prashant ; Drumwright, Evan ; Kozma, Robert
Author_Institution :
Dept. of Comput. Sci., Univ. of Memphis, TN, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
We show that fuzzy neural nets can rate the emotional feedback message implicit in human facial expressions at a level comparable to human performance. We also identify primitive and derived features in facial expressions and animations. We also report on a partial solution to the difficult inverse problem of generating naturalistic facial expressions from summary abstract descriptions of the emotional feedback to be conveyed
Keywords :
computer animation; face recognition; fuzzy neural nets; graphical user interfaces; inverse problems; realistic images; speech-based user interfaces; anthropomorphic representations; derived features; emotional feedback message rating; facial animations; facial features generation; facial features recognition; fuzzy neural nets; human facial expressions; human performance; inverse problem; naturalistic facial expression generation; neurofuzzy recognition; primitive features; summary abstract descriptions; talking heads; Face recognition; Facial animation; Facial features; Fuzzy neural networks; Humans; Inverse problems; Mouth; Neural networks; Neurofeedback; Ontologies;
Conference_Titel :
Fuzzy Systems, 2002. FUZZ-IEEE'02. Proceedings of the 2002 IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7280-8
DOI :
10.1109/FUZZ.2002.1006628
