新疆维吾尔族男性三维人脸图像的年龄估计与年龄面貌重构
|
摘要
目的基于新疆维吾尔族男性三维脸部图像寻找与年龄相关的脸部特征,构建年龄估计模型,重塑个体衰老及年轻时的脸部图像。方法使用Artec Studio软件对采集的105例17~57岁新疆维吾尔族男性人脸三维图像预处理。用Face Analysis软件将人脸图像转为高密度三维点阵数据,使每张图像可用32 251个点所表示。利用广义普鲁克分析法对人脸图像进行中心化校正并统一至同一坐标系。采用偏最小二乘回归法建立年龄估计模型。将年龄相关脸部形态特征的变化展现在平均脸的热图上,并基于该模型进行不同年龄的脸部图像重构。结果随着年龄的增长,平均脸会发生鼻唇沟加深、脸颊凹陷、颧骨突出、眼角下垂等变化。估计年龄和真实年龄之间的Pearson相关系数为0.71,估计年龄的平均绝对偏差(mean absolute deviation,MAD)为6.37岁,>30~40岁组的年龄估计结果最准确(MAD值为4.27岁),40岁以后偏差随年龄上升。合成的脸部图像随年龄增长脸部形态变化和衰老效果明显。结论本研究在维吾尔族人群中揭示了年龄相关的脸部特征和衰老标记,建立了可靠的年龄估计模型。
Objective To search age-correlated facial features and construct an age estimation model based on the three-dimensional(3 D) facial images of Xinjiang Uygur males, and to structure individual face images of old age and young age. Methods Pretreatment was performed to collect 105 3 D facial images of Xingjiang Uygur males aged between 17-57 years by Artec Studio software. The facial images were transferred to high-density 3 D dot matrix data by Face Analysis software, and each image could be represented with 32 251 vertexes. Central correction of the facial images was done and all the data were aligned to a standard coordinate frame by generalized Procrustes analysis(GPA). The age estimation model was established by partial least square regression(PLSR). Furthermore, the changes of age-correlated facial features were presented on the heat map of average face, and the reconstruction of facial images at different ages was performed based on this model. Results With age, the average faces showed a series of changes including the nasolabial sulcus deepening, cheek sinking, cheekbone protruding and eye corner drooping. The Pearson correlation coefficient(r) between estimated age and chronological age was 0.71.The mean absolute deviation(MAD) of age estimation was 6.37 years. The results of age estimation in>30-40 years group showed a best accuracy(MAD=4.27 years), and the deviations increased with age after 40 years. The composite facial images represented a significant result with age on facial morphological features and aging. Conclusion The results of this study reveal the age-correlated facial features and aging markers in Uygur population, which help to construct a reliable age estimation model.
Objective To search age-correlated facial features and construct an age estimation model based on the three-dimensional(3 D) facial images of Xinjiang Uygur males, and to structure individual face images of old age and young age. Methods Pretreatment was performed to collect 105 3 D facial images of Xingjiang Uygur males aged between 17-57 years by Artec Studio software. The facial images were transferred to high-density 3 D dot matrix data by Face Analysis software, and each image could be represented with 32 251 vertexes. Central correction of the facial images was done and all the data were aligned to a standard coordinate frame by generalized Procrustes analysis(GPA). The age estimation model was established by partial least square regression(PLSR). Furthermore, the changes of age-correlated facial features were presented on the heat map of average face, and the reconstruction of facial images at different ages was performed based on this model. Results With age, the average faces showed a series of changes including the nasolabial sulcus deepening, cheek sinking, cheekbone protruding and eye corner drooping. The Pearson correlation coefficient(r) between estimated age and chronological age was 0.71.The mean absolute deviation(MAD) of age estimation was 6.37 years. The results of age estimation in>30-40 years group showed a best accuracy(MAD=4.27 years), and the deviations increased with age after 40 years. The composite facial images represented a significant result with age on facial morphological features and aging. Conclusion The results of this study reveal the age-correlated facial features and aging markers in Uygur population, which help to construct a reliable age estimation model.
引文
[1]LU J,TAN Y P.Gait-based human age estimation[C].Dallas:2010 IEEE International Conference on Acoustics,Speech and Signal Processing,2010.
[2]Minematsu N,Sekiguchi M,Hirose K.Automatic estimation of one’s age with his/her speech based upon acoustic modeling techniques of speakers[C].Orlando:2002 IEEE International Conference on Acoustics,Speech,and Signal Processing,2002.
[3]ZHOU S K,GEORGESCU B,ZHOU X S,et al.Image based regression using boosting method[C].Beijin:Tenth IEEE International Conference on Computer,2005.
[4]GUO G,MU G.Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression[C].Providence:2017 IEEE Conference on Computer Vision and Pattern Recognition,2011.
[5]ALLEY T R.Social and applied aspects of perceiving faces[M].London:Psychology Press,1988.
[6]ZHAO W,CHELLAPPA R,PHILLIPS P J,et al.Face recognition:a literature survey[J].Acm Comput Surv,2000,4(35):399-458.
[7]GENG X,ZHOU Z H,SMITH-MILES K.Automatic age estimation based on facial aging patterns[J].IEEE Trans Pattern Anal Mach Intell,2007,29(12):2234-2240.
[8]CHOI S E,LEE Y J,LEE S J,et al.Age estimation using a hierarchical classifier based on global and local facial features[J].Pattern Recogn,2011,44(6):1262-1281.
[9]GUO G,FU Y,HUANG T S,et al.Locally adjusted robust regression for human age estimation[C].Copper Mountain:2008 IEEE Workshop on Applications of Computer,2008.
[10]FU Y,GUO G,HUANG T S.Age synthesis and estimation via faces:a survey[J].IEEE Trans Pattern Anal Mach Intell,2010,32(11):1955-1976.
[11]胡春龙.基于人脸图像的头部姿态估计与年龄估计方法研究[D].武汉:华中科技大学,2014.
[12]黄兵.基于Gabor小波与LBP直方图的人脸图像年龄估计[D].天津:天津大学,2011.
[13]李玲芝,梁毅雄,艾玮,等.基于稀疏表示的自动年龄估计[J].中南大学学报(自然科学版),2015,46(3):878-885.
[14]CHEN W,QIAN W,WU G,et al.Three-dimensional human facial morphologies as robust aging markers[J].Cell Res,2015,25(5):574-587.
[15]林时苗.基于人脸图像的年龄估计关键技术研究[D].南京:南京大学,2014.
[16]胡斓,夏利民.基于人工免疫识别系统的年龄估计[J].计算机工程与应用,2006(26):186-188.
[17]罗晓羽.基于多标签的自动人脸年龄估计研究[D].武汉:华中科技大学,2012.
[18]王芹.基于自适应标记分布学习的人脸年龄估计[D].南京:东南大学,2015.
[19]GUO G,MU G,FU Y,et al.Human age estimation using bio-inspired features[C].Miami:2009 IEEE Conference on Computer Vision and Pattern Recognition,2009.
[20]VAPNIK V N.Statistical learning theory[M].New York:Wiley-Interscience,1998.
[21]GUO G,MU G.Joint estimation of age,gender and ethnicity:CCA vs.PLS[C].Shanghai:2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition,2013
[22]许磊,黎智辉,王俊娟,等.高精度三维人脸图像数据库[J].刑事技术,2015(2):94-97.
[23]WIRTHLIN J,KAU C H,ENGLISH J D,et al.Comparison of facial morphologies between adult Chinese and Houstonian Caucasian populations using three-dimensional imaging[J].Int J Oral Maxillofac Surg,2013,42(9):1100-1107.
[24]KASPERAVICIUTE D,CATARINO C B,CHINTHAPALLI K,et al.Uncovering genomic causes of co-morbidity in epilepsy:gene-driven phenotypic characterization of rare microdeletions[J].PLo S One,2011,6(8):e23182.
[25]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999.
[26]GUO J,MEI X,TANG K.Automatic landmark annotation and dense correspondence registration for 3D human facial images[J].Bmc Bioinformatics,2013,14:232.
[27]GOWER J C.Generalized procrustes analysis[J].Psychometrika,1975,40(1):33-51.
[28]MEVIK B,WEHRENS R.The pls package:principal component and partial least squares regression in R[J].J Stat Software,2007,18(2):1-23.
[29]ADLER D,MURDOCH D,NENADIC O,et al.rgl:3D visualization using Open GL[Z/OL].[2017-05-10].https://CRAN.R-project.org/package=rgl.
[30]ZBIEC-PIEKARSKA R,SPOLNICKA M,KUPIEC T,et al.Development of a forensically useful age prediction method based on DNA methylation analysis[J].Forensic Sci Int Genet,2015,17:173-179.
[31]FREIRE-ARADAS A,PHILLIPS C,MOSQUERAMIGUEL A,et al.Development of a methylation marker set for forensic age estimation using analysis of public methylation data and the Agena Bioscience Epi TYPER system[J].Forensic Sci Int Genet,2016,24:65-74.
[32]闫陈静.人脸年龄估计算法的设计与实现[D].北京:北京交通大学,2016.
[33]潘思宇,赵雯婷,唐鲲,等.人脸年龄估计和年龄面貌合成技术研究进展[J].刑事技术,2017(4):270-276.
[2]Minematsu N,Sekiguchi M,Hirose K.Automatic estimation of one’s age with his/her speech based upon acoustic modeling techniques of speakers[C].Orlando:2002 IEEE International Conference on Acoustics,Speech,and Signal Processing,2002.
[3]ZHOU S K,GEORGESCU B,ZHOU X S,et al.Image based regression using boosting method[C].Beijin:Tenth IEEE International Conference on Computer,2005.
[4]GUO G,MU G.Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression[C].Providence:2017 IEEE Conference on Computer Vision and Pattern Recognition,2011.
[5]ALLEY T R.Social and applied aspects of perceiving faces[M].London:Psychology Press,1988.
[6]ZHAO W,CHELLAPPA R,PHILLIPS P J,et al.Face recognition:a literature survey[J].Acm Comput Surv,2000,4(35):399-458.
[7]GENG X,ZHOU Z H,SMITH-MILES K.Automatic age estimation based on facial aging patterns[J].IEEE Trans Pattern Anal Mach Intell,2007,29(12):2234-2240.
[8]CHOI S E,LEE Y J,LEE S J,et al.Age estimation using a hierarchical classifier based on global and local facial features[J].Pattern Recogn,2011,44(6):1262-1281.
[9]GUO G,FU Y,HUANG T S,et al.Locally adjusted robust regression for human age estimation[C].Copper Mountain:2008 IEEE Workshop on Applications of Computer,2008.
[10]FU Y,GUO G,HUANG T S.Age synthesis and estimation via faces:a survey[J].IEEE Trans Pattern Anal Mach Intell,2010,32(11):1955-1976.
[11]胡春龙.基于人脸图像的头部姿态估计与年龄估计方法研究[D].武汉:华中科技大学,2014.
[12]黄兵.基于Gabor小波与LBP直方图的人脸图像年龄估计[D].天津:天津大学,2011.
[13]李玲芝,梁毅雄,艾玮,等.基于稀疏表示的自动年龄估计[J].中南大学学报(自然科学版),2015,46(3):878-885.
[14]CHEN W,QIAN W,WU G,et al.Three-dimensional human facial morphologies as robust aging markers[J].Cell Res,2015,25(5):574-587.
[15]林时苗.基于人脸图像的年龄估计关键技术研究[D].南京:南京大学,2014.
[16]胡斓,夏利民.基于人工免疫识别系统的年龄估计[J].计算机工程与应用,2006(26):186-188.
[17]罗晓羽.基于多标签的自动人脸年龄估计研究[D].武汉:华中科技大学,2012.
[18]王芹.基于自适应标记分布学习的人脸年龄估计[D].南京:东南大学,2015.
[19]GUO G,MU G,FU Y,et al.Human age estimation using bio-inspired features[C].Miami:2009 IEEE Conference on Computer Vision and Pattern Recognition,2009.
[20]VAPNIK V N.Statistical learning theory[M].New York:Wiley-Interscience,1998.
[21]GUO G,MU G.Joint estimation of age,gender and ethnicity:CCA vs.PLS[C].Shanghai:2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition,2013
[22]许磊,黎智辉,王俊娟,等.高精度三维人脸图像数据库[J].刑事技术,2015(2):94-97.
[23]WIRTHLIN J,KAU C H,ENGLISH J D,et al.Comparison of facial morphologies between adult Chinese and Houstonian Caucasian populations using three-dimensional imaging[J].Int J Oral Maxillofac Surg,2013,42(9):1100-1107.
[24]KASPERAVICIUTE D,CATARINO C B,CHINTHAPALLI K,et al.Uncovering genomic causes of co-morbidity in epilepsy:gene-driven phenotypic characterization of rare microdeletions[J].PLo S One,2011,6(8):e23182.
[25]王惠文.偏最小二乘回归方法及其应用[M].北京:国防工业出版社,1999.
[26]GUO J,MEI X,TANG K.Automatic landmark annotation and dense correspondence registration for 3D human facial images[J].Bmc Bioinformatics,2013,14:232.
[27]GOWER J C.Generalized procrustes analysis[J].Psychometrika,1975,40(1):33-51.
[28]MEVIK B,WEHRENS R.The pls package:principal component and partial least squares regression in R[J].J Stat Software,2007,18(2):1-23.
[29]ADLER D,MURDOCH D,NENADIC O,et al.rgl:3D visualization using Open GL[Z/OL].[2017-05-10].https://CRAN.R-project.org/package=rgl.
[30]ZBIEC-PIEKARSKA R,SPOLNICKA M,KUPIEC T,et al.Development of a forensically useful age prediction method based on DNA methylation analysis[J].Forensic Sci Int Genet,2015,17:173-179.
[31]FREIRE-ARADAS A,PHILLIPS C,MOSQUERAMIGUEL A,et al.Development of a methylation marker set for forensic age estimation using analysis of public methylation data and the Agena Bioscience Epi TYPER system[J].Forensic Sci Int Genet,2016,24:65-74.
[32]闫陈静.人脸年龄估计算法的设计与实现[D].北京:北京交通大学,2016.
[33]潘思宇,赵雯婷,唐鲲,等.人脸年龄估计和年龄面貌合成技术研究进展[J].刑事技术,2017(4):270-276.