Title :
A facial expression recognition for a speaker of a phoneme of vowel using thermal image processing and a speech recognition system
Author :
Koda, Y. ; Yoshitomi, Y. ; Nakano, M. ; Tabuse, M.
Author_Institution :
Yamaha Motor Co. Ltd., Iwata, Japan
fDate :
Sept. 27 2009-Oct. 2 2009
Abstract :
We have proposed a method for facial expression recognition for a speaker using thermal image processing and a speech recognition system. In this study, using a speech recognition system, we have improved our system to save thermal images at the three timing positions of just before speaking, and just speaking phonemes of the first and last vowels. In this method, the facial expressions were discriminable with the average recognition accuracy of 81% for four subjects, when he or she exhibited one of the intentional facial expressions of ldquoangryrdquo, ldquohappyrdquo, ldquoneutralrdquo, ldquosadrdquo, and ldquosurpriserdquo.
Keywords :
emotion recognition; face recognition; infrared imaging; robot vision; speaker recognition; facial expression recognition; speech recognition system; thermal image processing; vowel phoneme speaker; Data mining; Face recognition; Human robot interaction; Image processing; Image recognition; Interactive systems; Robustness; Speech recognition; Timing; Training data;
Conference_Titel :
Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium on
Conference_Location :
Toyama
Print_ISBN :
978-1-4244-5081-7
Electronic_ISBN :
1944-9445
DOI :
10.1109/ROMAN.2009.5326321
