基于协作表示的人脸表情识别
|
摘要
针对基于稀疏表示的分类(SRC)算法因采用l1范数最小化求解稀疏表示系数的计算复杂度高,由此提出一种基于协作表示的分类(CRC)算法,并应用于人脸表情识别中。首先,将归一化后的人脸图像分割为若干个互不重叠的子块,采用均匀LBP算子分别提取各个子块的特征向量,并依据每个子块图像的信息熵大小对各个特征向量进行加权后串接组合起来,构成一个联合特征向量,作为描述该图像的特征向量;然后,采用主成分分析(PCA)方法对测试样本和训练样本图像的特征向量进行降维;最后,采用基于协作表示的分类(CRC)算法,将测试样本图像的表情分为7类:生气、厌恶、恐惧、中性、悲伤、高兴和惊讶。在JAFFE数据库上的实验结果表明了本文算法的有效性,CRC算法的识别率与SRC算法几乎相当,但大大降低了计算复杂度,识别时间约为SRC算法的1/60。
Aiming at the high computational complexity for solving sparse representation coefficients by using l_1 norm minimization in sparse representation based classification( SRC) algorithm,this paper proposes a collaborative representation based classification( CRC) algorithm for facial expression recognition.Firstly,the normalized face image is divided into many non-overlapped sub-blocks,the feature vector for each sub-block is extracted using the uniform local binary pattern( LBP) operator and is weighted according to the information entropy of each sub-block image. A joint feature vector for describing the face image is obtained by concatenating the weighted feature vectors of all sub-blocks. Then,the principal component analysis( PCA) method is used to reduce the dimensions of the feature vector of test samples and training samples. Finally,the CRC algorithm is used to classify the test sample into seven categories: anger,disgust,fear,neutral,happy,sad,and surprised. The experimental results on JAFFE database demonstrate the effectiveness of the proposed algorithm. The recognition rate of CRC algorithm is almost the same as that of SRC algorithm,but the computational complexity is greatly reduced,and the recognition time is about 1/60 of SRC algorithm.
Aiming at the high computational complexity for solving sparse representation coefficients by using l_1 norm minimization in sparse representation based classification( SRC) algorithm,this paper proposes a collaborative representation based classification( CRC) algorithm for facial expression recognition.Firstly,the normalized face image is divided into many non-overlapped sub-blocks,the feature vector for each sub-block is extracted using the uniform local binary pattern( LBP) operator and is weighted according to the information entropy of each sub-block image. A joint feature vector for describing the face image is obtained by concatenating the weighted feature vectors of all sub-blocks. Then,the principal component analysis( PCA) method is used to reduce the dimensions of the feature vector of test samples and training samples. Finally,the CRC algorithm is used to classify the test sample into seven categories: anger,disgust,fear,neutral,happy,sad,and surprised. The experimental results on JAFFE database demonstrate the effectiveness of the proposed algorithm. The recognition rate of CRC algorithm is almost the same as that of SRC algorithm,but the computational complexity is greatly reduced,and the recognition time is about 1/60 of SRC algorithm.
引文
[1]ZHANG H H,ZHANG B L,HUANG W M,et al.Gabor wavelet associative memory for face recognition[J].IEEE Transactions on Neural Networks,2005,16(1):275-278.
[2]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:886-893.
[3]OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[4]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[5]卢官明,左加阔.基于不相关局部敏感鉴别分析的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2013,33(6):1-7.LU Guanming,ZUO Jiakuo.Neonatal pain expression recognition based on uncorrelated locality sensitive discriminant analysis[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2013,33(6):1-7.(in Chinese)
[6]卢官明,左加阔.基于二维局部保持鉴别分析的特征提取算法[J].南京邮电大学学报(自然科学版),2014,34(5):1-8.LU Guanming,ZUO Jiakuo.Feature extraction based on two-dimensional locality preserving discriminant analysis[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2014,34(5):1-8.(in Chinese)
[7]AHONEN T,HADID A,PIETIKAINEN M.Face description with local binary patterns:application to face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041.
[8]ZHANG H C,NASRABADI N M,ZHANG Y N,et al.Joint dynamic sparse representation for multi-view face recognition[J].Pattern Recognition,2012,45(4):1290-1298.
[9]SHAN C,GONG S,MCOWAN P W.Facial expression recognition based on local binary patterns:a comprehensive study[J].Image and Vision Computing,2009,27(6):803-816.
[10]卢官明,石婉婉,李旭,等.基于LBP特征和稀疏表示的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2015,35(1):19-25.LU Guanming,SHI Wanwan,LI Xu,et al.Neonatal pain expression recognition based on LBP feature and sparse representation[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2015,35(1):19-25.(in Chinese)
[11]卢官明,郭旻,李晓南,等.基于SVM的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2008,28(6):7-11.LU Guanming,GUO Min,LI Xiaonan,et al.Recognition for expression of pain in neonate using support vector machine[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2008,28(6):7-11.(in Chinese)
[12]卢官明,何嘉利,闫静杰,等.一种用于人脸表情识别的卷积神经网络[J].南京邮电大学学报(自然科学版),2016,36(1):16-22.LU Guanming,HE Jiali,YAN Jingjie,et al.Convolutional neural network for facial expression recognition[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2016,36(1):16-22.(in Chinese)
[13]WRIGHT J,MA Y,MAIRAL J,et al.Sparse representation for computer vision and pattern recognition[J].Proceedings of the IEEE,2010,98(6):1031-1044.
[14]WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[15]SHI Q,ERIKSSON A,et al.Is face recognition really a compressive sensing problem?[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2011:553-560.
[16]ZHANG L,YANG M,FENG X.Sparse representation or collaborative representation:which helps face recognition?[C]∥IEEE International Conference on Computer Vision(ICCV).2011:471-478.
[17]JOARDAR S,CHATTERJEE A.Collaborative representation based face recognition using a hybrid similarity measure with single training sample per person[C]∥International Conference on Control,Instrumentation,Energy and Communication(CIEC).2014:631-635.
[18]WANG B,LI W,POH N,et al.Kernel collaborative representation-based classifier for face recognition[C]∥IEEE International Conference on Acoustics,Speech,and Signal Processing.2013,32(3):2877-2881.
[19]CAI S,ZHANG L,ZUO W,et al.A probabilistic collaborative representation based approach for pattern classification[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:2950-2959.
[20]张青苗,殷爱菡,姜辉明.基于降维字典的L2范数人脸识别方法研究[J].计算机工程与设计,2013,34(10):3625-3628.ZHANG Qingmiao,YIN Aihan,JIANG Huiming.Research of face recognition based on L2 norm using dimension-reducing dictionary[J].Computer Engineering and Design,2013,34(10):3625-3628.
[21]陈书贞,于倩,练秋生.联合多尺度分块和协作表示的虹膜识别算法[J].信号处理,2014,30(9):1025-1033.CHEN Shuzhen,YU Qian,LIAN Qiusheng.An iris recognition algorithm combined multi-scale patch and collaborative representation[J].Journal of Signal Processing,2014,30(9):1025-1033.
[22]CANDES E J,ROMBERG J,TAO T.Robust uncertainty principles:exact signal reconstruction from highly incomplete frequency information[J].IEEE Transactions on Information Theory,2006,52(2):489-509.
[23]CANDES E J,ROMBERG J.Quantitative robust uncertainty principles and optimally sparse decompositions[J].Foundations of Computational Mathematics,2006,6(2):227-254.
[24]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[25]KIM S J,KOH K,LUSTIG M,et al.An interior-point method for large-scale-regularized least squares[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):606-617.
[26]FIGUEIREDO M A T,NOWAK R D,WRIGHT S J.Gradient projection for sparse reconstruction:application to compressed sensing and other inverse problems[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):586-597.
[27]LYONS M,AKEMASTU S,KAMACHI M,et al.Coding facial expressions with Gabor wavelets[C]∥3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998:200-205.
[2]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2005:886-893.
[3]OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[4]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[5]卢官明,左加阔.基于不相关局部敏感鉴别分析的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2013,33(6):1-7.LU Guanming,ZUO Jiakuo.Neonatal pain expression recognition based on uncorrelated locality sensitive discriminant analysis[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2013,33(6):1-7.(in Chinese)
[6]卢官明,左加阔.基于二维局部保持鉴别分析的特征提取算法[J].南京邮电大学学报(自然科学版),2014,34(5):1-8.LU Guanming,ZUO Jiakuo.Feature extraction based on two-dimensional locality preserving discriminant analysis[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2014,34(5):1-8.(in Chinese)
[7]AHONEN T,HADID A,PIETIKAINEN M.Face description with local binary patterns:application to face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041.
[8]ZHANG H C,NASRABADI N M,ZHANG Y N,et al.Joint dynamic sparse representation for multi-view face recognition[J].Pattern Recognition,2012,45(4):1290-1298.
[9]SHAN C,GONG S,MCOWAN P W.Facial expression recognition based on local binary patterns:a comprehensive study[J].Image and Vision Computing,2009,27(6):803-816.
[10]卢官明,石婉婉,李旭,等.基于LBP特征和稀疏表示的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2015,35(1):19-25.LU Guanming,SHI Wanwan,LI Xu,et al.Neonatal pain expression recognition based on LBP feature and sparse representation[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2015,35(1):19-25.(in Chinese)
[11]卢官明,郭旻,李晓南,等.基于SVM的新生儿疼痛表情识别[J].南京邮电大学学报(自然科学版),2008,28(6):7-11.LU Guanming,GUO Min,LI Xiaonan,et al.Recognition for expression of pain in neonate using support vector machine[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2008,28(6):7-11.(in Chinese)
[12]卢官明,何嘉利,闫静杰,等.一种用于人脸表情识别的卷积神经网络[J].南京邮电大学学报(自然科学版),2016,36(1):16-22.LU Guanming,HE Jiali,YAN Jingjie,et al.Convolutional neural network for facial expression recognition[J].Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition),2016,36(1):16-22.(in Chinese)
[13]WRIGHT J,MA Y,MAIRAL J,et al.Sparse representation for computer vision and pattern recognition[J].Proceedings of the IEEE,2010,98(6):1031-1044.
[14]WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[15]SHI Q,ERIKSSON A,et al.Is face recognition really a compressive sensing problem?[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2011:553-560.
[16]ZHANG L,YANG M,FENG X.Sparse representation or collaborative representation:which helps face recognition?[C]∥IEEE International Conference on Computer Vision(ICCV).2011:471-478.
[17]JOARDAR S,CHATTERJEE A.Collaborative representation based face recognition using a hybrid similarity measure with single training sample per person[C]∥International Conference on Control,Instrumentation,Energy and Communication(CIEC).2014:631-635.
[18]WANG B,LI W,POH N,et al.Kernel collaborative representation-based classifier for face recognition[C]∥IEEE International Conference on Acoustics,Speech,and Signal Processing.2013,32(3):2877-2881.
[19]CAI S,ZHANG L,ZUO W,et al.A probabilistic collaborative representation based approach for pattern classification[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:2950-2959.
[20]张青苗,殷爱菡,姜辉明.基于降维字典的L2范数人脸识别方法研究[J].计算机工程与设计,2013,34(10):3625-3628.ZHANG Qingmiao,YIN Aihan,JIANG Huiming.Research of face recognition based on L2 norm using dimension-reducing dictionary[J].Computer Engineering and Design,2013,34(10):3625-3628.
[21]陈书贞,于倩,练秋生.联合多尺度分块和协作表示的虹膜识别算法[J].信号处理,2014,30(9):1025-1033.CHEN Shuzhen,YU Qian,LIAN Qiusheng.An iris recognition algorithm combined multi-scale patch and collaborative representation[J].Journal of Signal Processing,2014,30(9):1025-1033.
[22]CANDES E J,ROMBERG J,TAO T.Robust uncertainty principles:exact signal reconstruction from highly incomplete frequency information[J].IEEE Transactions on Information Theory,2006,52(2):489-509.
[23]CANDES E J,ROMBERG J.Quantitative robust uncertainty principles and optimally sparse decompositions[J].Foundations of Computational Mathematics,2006,6(2):227-254.
[24]DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
[25]KIM S J,KOH K,LUSTIG M,et al.An interior-point method for large-scale-regularized least squares[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):606-617.
[26]FIGUEIREDO M A T,NOWAK R D,WRIGHT S J.Gradient projection for sparse reconstruction:application to compressed sensing and other inverse problems[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):586-597.
[27]LYONS M,AKEMASTU S,KAMACHI M,et al.Coding facial expressions with Gabor wavelets[C]∥3rd IEEE International Conference on Automatic Face and Gesture Recognition.1998:200-205.