摘要
针对现有表情识别算法未考虑头部姿态及不能使用高像素图像的问题,提出一种基于随机森林算法的头部姿态估计(RF-HPE)网络与卷积神经网络相结合的模型。首先对输入图像作强度归一化,然后利用RF-HPE确定脸部标志关键点,从而确定脸部标志的位置,最后使用卷积神经网络提取特征并训练模型。该模型降低了光线强度对识别结果的影响,并且在不牺牲算法效率的情况下提高了训练精度。实验结果表明,所提出的改进模型的学习能力相比其他同类模型有较大优势,分类精度也显著提高。
Aiming at the problem that the existing expression recognition algorithm does not consider the head pose and cannot use the high-pixel picture,this paper proposed a model based on the random forest algorithm-head pose estimation(RF-HPE) network combining a convolutional neural network.First,the input image is normalized by intensity.Then the key points of the face marker are determined by using RF-HPE to determine the position of the face marker.Finally,a convolutional neural network is used to extract features and train model.This model reduces the influence of light intensity on the recognition result and improves the training accuracy without sacrificing the efficiency of the algorithm.Experimental results show that the improved model has greater advantages than other similar models,and the classification accuracy is also significantly improved.
引文
[1] ZOU G F,FU G X,LI H T,et al.A Survey of Multi-pose Face Recognition [J].Pattern Recognition and Artificial Intelligence,2015,28(7):613-625.(in Chinese)邹国锋,傅桂霞,李海涛,等.多姿态人脸识别综述[J].模式识别与人工智能,2015,28(7):613-625.
[2] LEVI G,HASSNER T.Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns[C]//ACM on International Conference on Multimodal Interaction.ACM,2015:503-510.
[3] WANG D W,ZHOU J,MEI H Y,et al.Summary of facial expression recognition[J].Computer Engineering and Applications,2014,50(20):149-157.(in Chinese)王大伟,周军,梅红岩,等.人脸表情识别综述[J].计算机工程与应用,2014,50(20):149-157.
[4] ZHANG Z,LUO P,CHEN C L,et al.From Facial Expression Recognition to Interpersonal Relation Prediction[J].International Journal of Computer Vision,2018,126(5):550-569.
[5] HAPPY S L,ROUTRAY A.Automatic facial expression recog- nition using features of salient facial patches[J].IEEE Transactions on Affective Computing,2015,6(1):1-12.
[6] GIRSHICK R.Fast R-CNN[J].Computer Science,arXiv:1504.08083.
[7] ZHOU E,FAN H,CAO Z,et al.Extensive Facial Landmark Lo- calization with Coarse-to-Fine Convolutional Network Cascade[C]//IEEE International Conference on Computer Vision Workshops.IEEE Computer Society,2013:386-391.
[8] KOTSIA I,ZAFEIRIOU S,PITAS I.Texture and shape information fusion for facial expression and facial action unit recognition[C]//First International Conference on Advances in Computer-Human Interaction.IEEE,2008:833-851.
[9] PIETIKINEN M,HADID A,ZHAO G,et al.Computer Vision Using Local Binary Patterns[M].Springer London,2011.
[10] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[11] LOPES A T,AGUIAR E D,SOUZA A F D,et al.Facial Expression Recognition with Convolutional Neural Networks:Co-ping with Few Data and the Training Sample Order[J].Pattern Recognition,2016,61:610-628.
[12] WANI F J,RIZVI S E H,SHARMA M K,et al.A study on cross validation for model selection and estimation[J].International Journal of Agricultural Sciences,2018,14:165-172.
[13] LIU M,SHAN S,WANG R,et al.Learning Expressionlets on Spatio-temporal Manifold for Dynamic Facial Expression Recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2014:1749-1756.
[14] JUNG H,LEE S,YIM J,et al.Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition[C]//IEEE International Conference on Computer Vision.IEEE Computer Society,2015:2983-2991.
[15] VALSTAR M F,JIANG B,MEHU M,et al.The first facial expression recognition and analysis challenge[C]//IEEE International Conference on Automatic Face & Gesture Recognition and Workshops.IEEE,2011:921-926.