Spotting segments displaying facial expression from image sequences using HMM

被引：21

作者：

Otsuka, T ^{[1
]}

Ohya, J ^{[1
]}

机构：

[1] ATR, Media Integrat & Commun Res Labs, Kyoto 61902, Japan

来源：

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/AFGR.1998.670988

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 call be spotted accurately in near real time.

引用

页码：442 / 447

页数：2