基于自回归模型的动态表情识别

An Auto-regressive Model Based Approach to Dynamic Facial Expression Recognition

采用几何信息和纹理信息融合的混合特征,基于自回归(AR)模型,提出一种基于线段的相似度判决方法实现动态表情识别.首先在6种基本表情的图像序列训练集上进行训练得到6种AR模型,然后给定测试表情序列,对每一个测试序列通过6种AR模型生成6种预测序列,接着比较每种预测序列与实际给定序列的相似性,最终根据相似性判断所给序列的表情类别.为了更好地比较预测序列与给定序列的相似性,提出了一种基于线段的相似度判决方法.基于Cohn-Kanade+人脸表情库进行实验结果表明,该方法在动态表情识别上取得了良好的效果.

An auto-regressive(AR)model based approach using hybrid features of both geometric and appearancefeatures is proposed to recognize dynamic facial expression in this paper.Six AR models are first trainedfor six basic expressions based on the six groups of expression sequences.Given one sequence of expression,six predicted sequences are generated using the trained AR models.The corresponding expression is inferredfrom the most similar predicted sequence to the given one.To incorporate structure information and providebetter distinctive capability for recognition,a line segment based method is proposed to compute the similaritybetween the predicted and given expression sequences.Encouraging experimental results have been obtainedon the extended Cohn-Kanade database.