基于自适应多重多元回归的人脸年龄估计
|
摘要
针对基于标记分布学习的多重多元回归模型不能生成和人脸老化趋势一致标记分布的问题,提出自适应多重多元回归的人脸年龄估计方法.在为不同年龄生成具有适合标准差的离散高斯分布的基础上,采用偏最小二乘模型并有效地利用邻近年龄的人脸老化信息进行年龄估计.在MORPH人脸数据库上的对比实验结果表明,该文的人脸年龄估计模型具有更好的性能.
In order to address the problem that traditional multivariate multiple regression based label distribution learning methods cannot generate the label distribution according to the tendency of facial aging,a facial age estimation method based on adaptive multivariate multiple regression has been proposed. The proposed method generates the discrete Gaussian distributions with different standard deviations adapted to different ages,and using partial least square model to effectively utilize adjacent facial ageing information to predict facial age. Our experimental results on the MORPH face database show that the facial age estimation model in the paper has better performance than existing correlation models.
In order to address the problem that traditional multivariate multiple regression based label distribution learning methods cannot generate the label distribution according to the tendency of facial aging,a facial age estimation method based on adaptive multivariate multiple regression has been proposed. The proposed method generates the discrete Gaussian distributions with different standard deviations adapted to different ages,and using partial least square model to effectively utilize adjacent facial ageing information to predict facial age. Our experimental results on the MORPH face database show that the facial age estimation model in the paper has better performance than existing correlation models.
引文
[1] Bekhouche S E,Ouafi A,Taleb-Ahmed A,et al. Facial age estimation using BSIF and LBP[EB/OL].[2018-01-06]. https://www. researchgate. net/publication/270276061_Facial_age_estimation_using_BSIF_and_LBP.
[2]Lanitis A,Taylor C J,Cootes T F. Toward automatic simulation of aging effects on face images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):442-455.
[3]Fu Yun,Huang T S. Human age estimation with regression on discriminative aging manifold[J]. IEEE Transactions on Multimedia,2008,10(4):578-584.
[4] Guo Guodong,MuGuowang. Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Colorado Springs,Colorado,USA. IEEE,2011:657-664.
[5]Chao Weilun,Liu Junzuo,Ding Jianjiun. Facial age estimation based on label-sensitive learning and age-oriented regression[J]. Pattern Recognition,2013,46(3):628-641.
[6]Rothe R,Timofte R,Van Gool L. Deep expectation of real and apparent age from a single image without facial landmarks[J]. International Journal of Computer Vision,2018,126(2/4):144-157.
[7] Liu Hao,Lu Jiwen,Feng Jianjiang,et al. Label-sensitive deep metric learning for facial age estimation[J]. IEEE Transactions on Information Forensics and Security,2018,13(2):292-305.
[8] Sahoo T K,Banka H. Multi-feature-based facial age estimation using an incomplete facial aging database[J].Arabian Journal for Science and Engineering,2018:43(12):1-22.
[9]Geng Xin,Yin Chao,Zhou Zhihua. Facial age estimation by learning from label distributions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(10):2401-2412.
[10] Zeng Xueqiang,Run Xiang,Zou Huaxing. Partial least squares regression based facial age estimation[C]∥IEEE International Conference on Computational Science and Engineering(CSE)and Embedded and Ubiquitous Computing(EUC),Guangzhou,China. IEEE,2017,1:416-421.
[11] Singer M,Krivobokova T,Munk A,et al. Partial least squares for dependent data[J]. Biometrika,2016,103(2):351-362.
[12]Stott A E,Kanna S,Mandic D P. Widely linear complex partial least squares for latent subspace regression[J].Signal Processing,2018,152:350-362.
[13]Ramanathan N,Chellappa R. Modeling age progression in young faces[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,New York,USA IEEE,2006:387-394.
[14]Albert A M,Ricanek Jr K,Patterson E. A review of the literature on the aging adult skull and face:implications for forensic science research and applications[J]. Forensic Science International,2007,172(1):1-9.
[15]Panis G,Lanitis A,Tsapatsoulis N,et al. Overview of research on facial ageing using the FG-NET ageing database[J]. Iet Biometrics,2016,5(2):37-46.
[16] Geng Xin,Wang Qin,Xia Yu. Facial age estimation by adaptive label distribution learning[C]∥International Conference on Pattern Recognition(ICPR),Stockholm,Sweden IEEE,2014:4465-4470.
[17]曾雪强,赵丙娟,向润,等.基于偏最小二乘的人脸年龄估计[J].南昌大学学报:工科版,2017,39(4):380-385.
[18]Ricanek K,Tesafaye T. Morph:a longitudinal image database of normal adult age-progression[C]∥International Conference on Automatic Face and Gesture Recognition(FGR),Southampton,UK IEEE,2006:341-345.
[19] Geng Xin,Ji R. Label distribution kearning[J]. IEEE Transactions on Knowledge and Data Engineering,2016,28(7):1734-1748.
[20] Hartung J,Knapp G. Multivariate multiple regression[M]. Wiley StatsRef:Statistics Reference Online,2014.
[21]Waltz R A,Morales J L,Nocedal J,et al. An interior algorithm for nonlinear optimization that combines line search and trust region steps[J]. Mathematical Programming,2006,107(3):391-408.
[22]Guo Guodong,Mu Guowang,Fu Yun,et al. Human age estimation using bio-inspired features[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Miami,Florida,USA IEEE,2009:112-119.
[23] Lan Yuan Dong,Deng Huifang,Chen Tao. Dimensionality reduction based on neighborhood preserving and marginal discriminant embedding[J]. Procedia Engineering,2012,29(4):494-498.
[2]Lanitis A,Taylor C J,Cootes T F. Toward automatic simulation of aging effects on face images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):442-455.
[3]Fu Yun,Huang T S. Human age estimation with regression on discriminative aging manifold[J]. IEEE Transactions on Multimedia,2008,10(4):578-584.
[4] Guo Guodong,MuGuowang. Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Colorado Springs,Colorado,USA. IEEE,2011:657-664.
[5]Chao Weilun,Liu Junzuo,Ding Jianjiun. Facial age estimation based on label-sensitive learning and age-oriented regression[J]. Pattern Recognition,2013,46(3):628-641.
[6]Rothe R,Timofte R,Van Gool L. Deep expectation of real and apparent age from a single image without facial landmarks[J]. International Journal of Computer Vision,2018,126(2/4):144-157.
[7] Liu Hao,Lu Jiwen,Feng Jianjiang,et al. Label-sensitive deep metric learning for facial age estimation[J]. IEEE Transactions on Information Forensics and Security,2018,13(2):292-305.
[8] Sahoo T K,Banka H. Multi-feature-based facial age estimation using an incomplete facial aging database[J].Arabian Journal for Science and Engineering,2018:43(12):1-22.
[9]Geng Xin,Yin Chao,Zhou Zhihua. Facial age estimation by learning from label distributions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(10):2401-2412.
[10] Zeng Xueqiang,Run Xiang,Zou Huaxing. Partial least squares regression based facial age estimation[C]∥IEEE International Conference on Computational Science and Engineering(CSE)and Embedded and Ubiquitous Computing(EUC),Guangzhou,China. IEEE,2017,1:416-421.
[11] Singer M,Krivobokova T,Munk A,et al. Partial least squares for dependent data[J]. Biometrika,2016,103(2):351-362.
[12]Stott A E,Kanna S,Mandic D P. Widely linear complex partial least squares for latent subspace regression[J].Signal Processing,2018,152:350-362.
[13]Ramanathan N,Chellappa R. Modeling age progression in young faces[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,New York,USA IEEE,2006:387-394.
[14]Albert A M,Ricanek Jr K,Patterson E. A review of the literature on the aging adult skull and face:implications for forensic science research and applications[J]. Forensic Science International,2007,172(1):1-9.
[15]Panis G,Lanitis A,Tsapatsoulis N,et al. Overview of research on facial ageing using the FG-NET ageing database[J]. Iet Biometrics,2016,5(2):37-46.
[16] Geng Xin,Wang Qin,Xia Yu. Facial age estimation by adaptive label distribution learning[C]∥International Conference on Pattern Recognition(ICPR),Stockholm,Sweden IEEE,2014:4465-4470.
[17]曾雪强,赵丙娟,向润,等.基于偏最小二乘的人脸年龄估计[J].南昌大学学报:工科版,2017,39(4):380-385.
[18]Ricanek K,Tesafaye T. Morph:a longitudinal image database of normal adult age-progression[C]∥International Conference on Automatic Face and Gesture Recognition(FGR),Southampton,UK IEEE,2006:341-345.
[19] Geng Xin,Ji R. Label distribution kearning[J]. IEEE Transactions on Knowledge and Data Engineering,2016,28(7):1734-1748.
[20] Hartung J,Knapp G. Multivariate multiple regression[M]. Wiley StatsRef:Statistics Reference Online,2014.
[21]Waltz R A,Morales J L,Nocedal J,et al. An interior algorithm for nonlinear optimization that combines line search and trust region steps[J]. Mathematical Programming,2006,107(3):391-408.
[22]Guo Guodong,Mu Guowang,Fu Yun,et al. Human age estimation using bio-inspired features[C]∥IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Miami,Florida,USA IEEE,2009:112-119.
[23] Lan Yuan Dong,Deng Huifang,Chen Tao. Dimensionality reduction based on neighborhood preserving and marginal discriminant embedding[J]. Procedia Engineering,2012,29(4):494-498.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |