基于时序分析的微弱表情识别方法  

Micro-Expression Recognition Framework Using Time Series Analysis

作　　者：王上飞[1] 张锋[1] 王煦法[1] 

机构地区：[1]中国科学技术大学计算机科学与技术学院安徽省计算与通讯软件重点实验室,合肥230027

出　　处：《模式识别与人工智能》2010年第2期148-153,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家863计划项目(No.2008AA01Z122);安徽省自然科学基金项目(No.070412056)资助

摘　　要：依赖现有夸张的表情图像序列数据库,将微弱表情看成是整个夸张表情图像序列中的前面一段,提出基于时序分析的微弱表情识别方法.首先融合二值图像和灰度图像序列的光流运动场,提取眉毛、鼻子和嘴巴的动作方向及强度共5维特征序列.接着采用夸张表情特征序列训练隐马尔科夫模型(HMM),分析特征序列与夸张表情的关系.通过HMM前向学习识别微弱表情序列.同时采用Boosting算法提高识别精度.在Cohn Kanade表情数据库上进行实验验证,取得较好的实验效果.Relying on existing exaggerated expression video database and micro-expression being regarded as former part of exaggerated expression image series, a micro-expression recognition framework based on time series analysis is presented. Firstly, five dimensions feature series, action direction and intensity rate of eyebrows, nose and mouth, are extracted by fusing optical flow field of binary videos and gray ones. Secondly, hidden Markov models are trained by adopting exaggerated expression feature series, the relationship being analyzed between feature series and exaggerated expressions. Finally, these models are used to predict the variety trend of micro-expressions and recognize them and employed to increase recognition Kanade facial expression database accuracy. The effectiveness of the and a preferable experiment result is boosting algorithm is approach is evaluated on Cohn obtained.

关 键 词：微弱表情识别 时序分析 动作方向 动作强度 隐马尔科夫模型(HMM) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]