基于局部流形注意力的人脸表情识别

Local-manifold Attention for Facial Expression Recognition

人脸表情识别在各种人机交互场景中有广泛的应用,但在表情模糊或存在遮挡情况下,现有的表情识别方法效果并不理想.针对表情模糊和遮挡问题,本文提出了一种基于局部流形注意力(SPD-Attention)的网络架构,利用流形学习得到具有更强描述能力的二阶统计信息以加强对表情细节特征的学习,抑制遮挡区域无关特征对网络的影响.同时,针对流形学习过程中由于对数计算导致的梯度消失和爆炸,本文提出了相应的正则约束加速网络收敛.本文在公开表情识别数据集上测试了算法效果,与VGG等经典方法相比取得了显著提升,在AffectNet、CK+、FER2013、FER2013plus、RAF-DB、SFEW上正确率分别为:57.10%、99.01%、69.51%、87.90%、86.63%、49.18%,并在模糊、遮挡表情数据集上相比于Covariance Pooling等目前先进方法提升了1.85%.

Facial expression recognition(FER)has various applications in human-computer interaction scenarios.However,existing FER methods are not that effective for blurred and occluded expression.To cope with facial expression blur and occlusion,this study proposes a novel network based on local manifold attention(SPD-Attention),which uses manifold learning to obtain the second-order statistical information with a stronger descriptive ability for strengthening the learning of facial expression details and suppressing the influence of irrelevant features in the occlusion area on the network.At the same time,in view of the disappearance and explosion of gradient caused by logarithmic calculation,this study proposes corresponding regular constraints to accelerate network convergence.The effect of the algorithm is tested on public expression recognition data sets,which is significantly improved compared with those of classic methods such as VGG.The accuracy is 57.10%,99.01%,69.51%,87.90%,86.63%,and 49.18%on AffectNet,CK+,FER2013,FER2013plus,RAF-DB,and SFEW,respectively.In addition,compared with state-of-the-art methods such as Covariance Pooling,the proposed method has an accuracy improved by 1.85%on a special blurred and occluded expression data set.