Face feature extraction from spatial frequency for dynamic expression recognition

Tatsumi Sakaguchi, Shigeo Morishima

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

A new facial feature extraction technique for expression recognition is proposed. We employ the spatial frequency domain information to obtain robust performance to the random noise on a image or the lighting conditions. It exhibited high ability sufficiently even if combined with a low-performance region tracking method. As an application of this technique, we have constructed a dynamic facial expression recognition system. We use hidden Markov models to utilize temporal changes in the facial expressions. The spatial frequency information and the temporal information make better rates of facial expression recognition. In the experiment, we established a correct response rate of approximately 84.1% of recognition with six categories.

本文言語English
ホスト出版物のタイトルTrack C
ホスト出版物のサブタイトルApplications and Robotic Systems
出版社Institute of Electrical and Electronics Engineers Inc.
ページ451-455
ページ数5
ISBN(印刷版)081867282X, 9780818672828
DOI
出版ステータスPublished - 1996
外部発表はい
イベント13th International Conference on Pattern Recognition, ICPR 1996 - Vienna, Austria
継続期間: 1996 8 251996 8 29

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
3
ISSN(印刷版)1051-4651

Conference

Conference13th International Conference on Pattern Recognition, ICPR 1996
国/地域Austria
CityVienna
Period96/8/2596/8/29

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Face feature extraction from spatial frequency for dynamic expression recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル