基于Gabor小波和主成分分析的人脸表情识别
|
摘要
设计一种基于Gabor小波和主成分分析(PCA)的人脸表情识别方法。首先对每一张表情图像采用Haar特征进行人脸检测,然后选择合适的Gabor小波滤波器组进行表情特征提取,最后采用PCA对提取的高维Gabor小波特征进行特征降维,输入到K近邻法(KNN)分类器实现表情分类任务。在标准的JAFFE表情数据集的试验结果表明,PCA方法提取90维的Gabor小波特征用于表情识别时表现最好,能够取得89.52%的人脸表情识别性能。可见,该方法是一种可行的人脸表情识别方法。
Facial expression recognition is a very challenging research subject and has extensive applications. A method of facial expression recognition based on Gabor wavelet and principle component analysis(PCA) is designed. Face detection is firstly conducted based on the Haar features for each facial expression image. Then,facial feature extraction is implemented by using a set of suitable Gabor wavelets filters. Finally, PCA is used to perform dimensionality reduction on the extracted high-dimensional Gabor wavelet features, followed by Knearest neighbor(KNN) as a facial expression classifier. Experimental results on the benchmarking JAFFE facial expression database shows that PCA performs best when extracting 90-dimension Gabor wavelet features,giving an accuracy of 89.52 % on facial expression recognition tasks. Accordingly, this method is feasible for facial expression recognition.
Facial expression recognition is a very challenging research subject and has extensive applications. A method of facial expression recognition based on Gabor wavelet and principle component analysis(PCA) is designed. Face detection is firstly conducted based on the Haar features for each facial expression image. Then,facial feature extraction is implemented by using a set of suitable Gabor wavelets filters. Finally, PCA is used to perform dimensionality reduction on the extracted high-dimensional Gabor wavelet features, followed by Knearest neighbor(KNN) as a facial expression classifier. Experimental results on the benchmarking JAFFE facial expression database shows that PCA performs best when extracting 90-dimension Gabor wavelet features,giving an accuracy of 89.52 % on facial expression recognition tasks. Accordingly, this method is feasible for facial expression recognition.
引文
[1]Zhao X,Zhang S.A Review on Facial Expression Recognition:Feature Extraction and Classification[J].IETE Technical Review,2016,33(5):505-517.
[2]Sariyanidi E,Gunes H,Cavallaro A.Automatic Analysis of Facial Affect:A Survey of Registration,Representation,and Recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(6):1113-1133.
[3]Viola P,Jones M.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[4]Happy S,Routray A.Automatic facial expression recognition using features of salient facial patches[J].IEEETransactions on Affective Computing,2015,6(1):1-12.
[5]刘帅师,田彦涛,万川.基于Gabor多方向特征融合与分块直方图的人脸表情识别方法[J].自动化学报,2012,37(12):1455-1463.
[6]Luo Y,Wu C-m,Zhang Y.Facial expression recognition based on fusion feature of PCA and LBP with SVM[J].Optik-International Journal for Light and Electron Optics,2013,124(17):2767-2770.
[7]Deng H,Jin L,Zhen L,et al.A new facial expression recognition method based on local gabor filter bank and pca plus lda[J].International Journal of Information Technology,2005,11(11):86-96.
[8]Peterson LE.K-nearest neighbor[J].Scholarpedia,2009,4(2):1883.
[9]Shih FY,Chuang CF,Wang PSP.Performance comparisons of facial expression recognition in JAFFE database[J].International Journal of Pattern Recognition and Artificial Intelligence,2008,22(3):445-460.
[10]Lyons MJ,Akamatsu S,Kamachi M,et al.The Japanese female facial expression(JAFFE)database[C].Proceedings of third international conference on automatic face and gesture recognition,Nara,Japan,1998,14-16.
[11]贲晛烨,杨明强,张鹏,等.微表情自动识别综述[J].计算机辅助设计与图形学学报,2014,26(9):1385-1395.
[2]Sariyanidi E,Gunes H,Cavallaro A.Automatic Analysis of Facial Affect:A Survey of Registration,Representation,and Recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(6):1113-1133.
[3]Viola P,Jones M.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[4]Happy S,Routray A.Automatic facial expression recognition using features of salient facial patches[J].IEEETransactions on Affective Computing,2015,6(1):1-12.
[5]刘帅师,田彦涛,万川.基于Gabor多方向特征融合与分块直方图的人脸表情识别方法[J].自动化学报,2012,37(12):1455-1463.
[6]Luo Y,Wu C-m,Zhang Y.Facial expression recognition based on fusion feature of PCA and LBP with SVM[J].Optik-International Journal for Light and Electron Optics,2013,124(17):2767-2770.
[7]Deng H,Jin L,Zhen L,et al.A new facial expression recognition method based on local gabor filter bank and pca plus lda[J].International Journal of Information Technology,2005,11(11):86-96.
[8]Peterson LE.K-nearest neighbor[J].Scholarpedia,2009,4(2):1883.
[9]Shih FY,Chuang CF,Wang PSP.Performance comparisons of facial expression recognition in JAFFE database[J].International Journal of Pattern Recognition and Artificial Intelligence,2008,22(3):445-460.
[10]Lyons MJ,Akamatsu S,Kamachi M,et al.The Japanese female facial expression(JAFFE)database[C].Proceedings of third international conference on automatic face and gesture recognition,Nara,Japan,1998,14-16.
[11]贲晛烨,杨明强,张鹏,等.微表情自动识别综述[J].计算机辅助设计与图形学学报,2014,26(9):1385-1395.