一种具有噪声鲁棒性的人脸表情识别算法研究
|
摘要
为降低噪声对人脸表情识别的影响,首先提出具有人眼视觉特性的各向异性扩散滤波方法,对图像进行滤波预处理;同时采用改进HOG算子提取人脸表情特征。实验结果表明,改进的各向异性扩散滤波算法在滤除噪声的同时能更好地保留表情图像的弱小细节信息,改进HOG算子相比传统特征提取算子可以更准确地描述人脸表情特征。因此,该算法是一种有效的、具有一定噪声鲁棒性的人脸表情识别算法。
In order to reduce the interference of noise with facial expression recognition. Firstly,a new anisotropic diffusion algorithm based on human visual system is proposed in this paper. Meanwhile,the paper makes improvements on HOG algorithm,and uses the advanced method to extract facial expression feature. The experimental results show that the improved anisotropic diffusion algorithm can preserve small details much better while filtering out noise and the improved HOG algorithm can describe the facial expression much more accurately compared with some other traditional descriptors. Therefore the proposed algorithm is an effective facial expression recognition algorithm with strong noise robustness.
In order to reduce the interference of noise with facial expression recognition. Firstly,a new anisotropic diffusion algorithm based on human visual system is proposed in this paper. Meanwhile,the paper makes improvements on HOG algorithm,and uses the advanced method to extract facial expression feature. The experimental results show that the improved anisotropic diffusion algorithm can preserve small details much better while filtering out noise and the improved HOG algorithm can describe the facial expression much more accurately compared with some other traditional descriptors. Therefore the proposed algorithm is an effective facial expression recognition algorithm with strong noise robustness.
引文
[1]SONG K T,CHIEN S C.Facial expression recognition based on mixture of basic expressions and intensities[C]//Proc.2012 IEEE International Conference on Systems,Man,and Cybernetics.[S.l.]:IEEE Press,2012:3123-3128.
[2]ZHAO Lihong,YANG Caikun,PAN Feng,et al.Face recognition based on gabor with 2DPCA and PCA[C]//Proc.2012 24th Chines Control and Decision Conference.[S.l.]:IEEE Press,2012:2632-2635.
[3]BECKMANN C F,SMITH S M.Probabilistic independent component analysis for functional magnetic resonance imaging[J].IEEE Trans.Med.Imaging,2004(23):137-152
[4]阮锦新.多姿态人脸检测与表情识别关键技术研究[D].广州:华南理工大学,2010:64-83
[5]OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996,29(1):51-59
[6]GENG Cong,JIANG Xudong.Face recognition using SIFT features[C]//Proc.2009 16th IEEE International Conference on Image Processing.[S.l.]:IEEE Press,2009:3313-3316.
[7]DALA N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proc.IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition(CVPR'05).San Diego,CA,USA:IEEE Press,2005:886-893.
[8]李丽萍.图像去噪方法研究[D].武汉:长江大学,2012.
[9]PERONA P,MALIK J.Scale space and edge detection using anisotropic diffusion[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[10]严哲,顾汉明,蔡成国.基于各向异性扩散滤波的地震图像增强处理[J].石油地球物理学报,2013,48(3):390-394.
[11]陈金林,刘谢进.基于异性扩撒方法的数字图像水印研究[J].计算机应用与软件,2013,30(7):151-153.
[12]付丽娟,姚宇,付忠良.中值滤波与各向异性扩散相结合的医学图像滤波方法[J].计算机应用,2014,34(1):145-148.
[13]FERWERDA J A.Element of early vision for computer graphics[J].IEEE Computer Graphics and Applications,2001,21(5):22-33.
[14]MARIOS K,ANASTASIOS T,IOANNIS P.Salient feature and reliable classifier selection for facial expression classification[J].Pattern Recognition,2010(43):972-986.
[15]付晓峰.基于二元模式的人脸识别与表情识别研究[D].杭州:浙江大学,2008.
[16]DENIZ O,BUENO G,SALIDO J,et al.Face recognition using histograms of oriented gradients[J].Pattern Recognition Letters,2011(32):1598-1603.
[17]SONG Fengyi,TAN Xiaoyang,LIU Xue,et al.Eyes closeness detection from still images with multi-scale histograms of principal ori ented gradients[J].Pattern Recognition,2014,47(9):2825-2838.
[2]ZHAO Lihong,YANG Caikun,PAN Feng,et al.Face recognition based on gabor with 2DPCA and PCA[C]//Proc.2012 24th Chines Control and Decision Conference.[S.l.]:IEEE Press,2012:2632-2635.
[3]BECKMANN C F,SMITH S M.Probabilistic independent component analysis for functional magnetic resonance imaging[J].IEEE Trans.Med.Imaging,2004(23):137-152
[4]阮锦新.多姿态人脸检测与表情识别关键技术研究[D].广州:华南理工大学,2010:64-83
[5]OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996,29(1):51-59
[6]GENG Cong,JIANG Xudong.Face recognition using SIFT features[C]//Proc.2009 16th IEEE International Conference on Image Processing.[S.l.]:IEEE Press,2009:3313-3316.
[7]DALA N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proc.IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition(CVPR'05).San Diego,CA,USA:IEEE Press,2005:886-893.
[8]李丽萍.图像去噪方法研究[D].武汉:长江大学,2012.
[9]PERONA P,MALIK J.Scale space and edge detection using anisotropic diffusion[J].IEEE Trans.Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[10]严哲,顾汉明,蔡成国.基于各向异性扩散滤波的地震图像增强处理[J].石油地球物理学报,2013,48(3):390-394.
[11]陈金林,刘谢进.基于异性扩撒方法的数字图像水印研究[J].计算机应用与软件,2013,30(7):151-153.
[12]付丽娟,姚宇,付忠良.中值滤波与各向异性扩散相结合的医学图像滤波方法[J].计算机应用,2014,34(1):145-148.
[13]FERWERDA J A.Element of early vision for computer graphics[J].IEEE Computer Graphics and Applications,2001,21(5):22-33.
[14]MARIOS K,ANASTASIOS T,IOANNIS P.Salient feature and reliable classifier selection for facial expression classification[J].Pattern Recognition,2010(43):972-986.
[15]付晓峰.基于二元模式的人脸识别与表情识别研究[D].杭州:浙江大学,2008.
[16]DENIZ O,BUENO G,SALIDO J,et al.Face recognition using histograms of oriented gradients[J].Pattern Recognition Letters,2011(32):1598-1603.
[17]SONG Fengyi,TAN Xiaoyang,LIU Xue,et al.Eyes closeness detection from still images with multi-scale histograms of principal ori ented gradients[J].Pattern Recognition,2014,47(9):2825-2838.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心