Spotting segments displaying facial expression from image sequences using HMM

Takahiro Otsuka, Jun Ohya

研究成果: Conference contribution

46 被引用数 (Scopus)

抄録

A method that can be used for spotting segments that display facial expression is proposed. The motion of the face is modeled by HMM in such a way that each state corresponds to the conditions of facial muscles, e.g., relaxed, contracting, apex and relaxing. The probability assigned to each state is updated iteratively as the feature vector is obtained from image processing. A spotted segment is placed into a certain category when the probability of that category exceeds a threshold value. Experiments show that the segments for the six basic expressions can be spotted accurately in near real time.

本文言語English
ホスト出版物のタイトルProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
出版社IEEE Computer Society
ページ442-447
ページ数6
ISBN(印刷版)0818683449, 9780818683442
DOI
出版ステータスPublished - 1998 1 1
外部発表はい
イベント3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara, Japan
継続期間: 1998 4 141998 4 16

出版物シリーズ

名前Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

Conference

Conference3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
国/地域Japan
CityNara
Period98/4/1498/4/16

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

「Spotting segments displaying facial expression from image sequences using HMM」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