4 March 2015 The development of automated behavior analysis software
Author Affiliations +
Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 944335 (2015) https://doi.org/10.1117/12.2180113
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China
The measurement of behavior for participants in a conversation scene involves verbal and nonverbal communications. The measurement validity may vary depending on the observers caused by some aspects such as human error, poorly designed measurement systems, and inadequate observer training. Although some systems have been introduced in previous studies to automatically measure the behaviors, these systems prevent participants to talk in a natural way. In this study, we propose a software application program to automatically analyze behaviors of the participants including utterances, facial expressions (happy or neutral), head nods, and poses using only a single omnidirectional camera. The camera is small enough to be embedded into a table to allow participants to have spontaneous conversation. The proposed software utilizes facial feature tracking based on constrained local model to observe the changes of the facial features captured by the camera, and the Japanese female facial expression database to recognize expressions. Our experiment results show that there are significant correlations between measurements observed by the observers and by the software.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yuki Jaana, Yuki Jaana, Oky Dicky Ardiansyah Prima, Oky Dicky Ardiansyah Prima, Takashi Imabuchi, Takashi Imabuchi, Hisayoshi Ito, Hisayoshi Ito, Kumiko Hosogoe, Kumiko Hosogoe, } "The development of automated behavior analysis software", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 944335 (4 March 2015); doi: 10.1117/12.2180113; https://doi.org/10.1117/12.2180113

Back to Top