Facial expression recognition is an important technology fundamental to realize intelligent image coding systems and advanced man-machine interfaces in visual communication systems. In computer vision field, many techniques have been developed to recognize facial expressions. However, most of those techniques are based on static features extracted from one or two still images. Those techniques are not robust against noise and cannot recognize subtle changes in facial expressions. In this paper we use hidden Markov models (HMM) with continuous output probabilities to extract a temporal pattern of facial motion. In order to improve the recognition performance, we propose a new feature obtained from wavelet transform coefficients. For the evaluation, we use 180 image sequences taken from three male subjects. Using these image sequences, the recognition rate for user trained mode achieves 98% compared with 84% using our previous method. The recognition rate for user independent mode achieves 84% when the expressions are restricted to four expressions.
|出版ステータス||Published - 1996 12 1|
|イベント||Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tsukuba, Jpn|
継続期間: 1996 11 11 → 1996 11 14
|Other||Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN|
|Period||96/11/11 → 96/11/14|
ASJC Scopus subject areas