计算机科学 ›› 2015, Vol. 42 ›› Issue (6): 32-36.doi: 10.11896/j.issn.1002-137X.2015.06.007

• 第十届和谐人机环境联合学术会议 • 上一篇    下一篇

基于人脸图像的年龄估计

林时苗,毛晓蛟,杨育彬   

  1. 南京大学计算机软件新技术国家重点实验室 南京210093,南京大学计算机软件新技术国家重点实验室 南京210093,南京大学计算机软件新技术国家重点实验室 南京210093
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受教育部新世纪优秀人才计划(NCET-11-0213),国家自然科学基金(61273257,1,61035003),江苏省六大人才高峰项目(2013-XXRJ-018)资助

Age Estimation Based on Facial Image

LIN Shi-miao, MAO Xiao-jiao and YANG Yu-bin   

  • Online:2018-11-14 Published:2018-11-14

摘要: 年龄是人固有的生物特征,随着年龄的变化,人脸特征也不断变化。近年来基于人脸图像的年龄估计方法的研究不断深入。基于人脸图像的年龄估计主要有两个阶段:特征提取和估计方法。针对以上两个阶段,分别提出相应的方法。在特征提取方面,为了更好地描述年龄变化,特别是针对未成年人,引入了方向梯度直方图(Histogram of Oriented Gradient,HOG)特征,并将其与局部二元模式(Local Binary Pattern,LBP)特征进行融合;在估计方法方面,提出了软双层估计模型, 其采用由粗到细的策略。首先,在第一层将人脸分成“未成年人”与“成年人”两类;然后,在第二层通过在两类的边界设置重叠区域,分别对其建立年龄估计模型,以对第一层的错误分类进行补救。通过实验发现,融合的特征具有更强的年龄判别性,同时,软双层模型也进一步提高了年龄估计的准确度。

关键词: 年龄估计,特征融合,软双层模型

Abstract: Age is an inherent biometric for human.As we grow older,our faces will change a lot.Age estimation based on facial image has been widely studied in recent years.Age estimation mainly consists of two phases:feature extraction and estimation method.A new age estimation method was proposed in this paper.In the feature extraction phase,we suggested combining histogram of oriented gradient (HOG) with local binary patter (LBP) to better describe the age progression of facial images,especially for the teenagers.In the estimation phase,a soft two-level estimation method based on coarse-to-fine strategy was proposed.Specifically,facial images are categorized as either adults or teenagers in the first level.In the second level,then age estimation models for each of the categories are trained,and an overlap area at the category boundary is adopted to fix the classification errors caused by the first level.Experimental results show that the features of fusion achieve better discriminative power of aging.Moreover,the soft two-level model further improves the age estimation accuracy.

Key words: Age estimation,Feature fusion,Soft two-level model

[1] 王先梅,梁玲燕,王志良,等.人脸图像的年龄估计技研究[J].中国图象图形学报,2012,17(6):603-618 Wang Xian-mei,Liang Ling-yan,Wang Zhi-liang,et al.Age estimation by facial image:a survey[J].Journal of Image and Graphics,2012,7(6):603-618
[2] Kwon Y H,da V L N.Age Classification from Facial Images.Computer Vision and Image Understanding,1999,74(1):1-21
[3] Lanitis A,Taylor C J,Coots T F.Toward automatic simulation of age effects on face images[J].PAMI,2002,24(4):442-455
[4] Geng X,Zhou Z H,Zhang Y,et al.Learning from facial aging patterns for automatic age estimation[C]∥ACM International Conf.on Multimedia.2006:307-316
[5] Yan S,Wang H,Tang X,et al.Learning auto-structured regressor from uncertain nonnegative labels[C]∥ICCV2007.2007:1-8
[6] Günay A,Nabiyev V V.Automatic Age Classification with LBP[C]∥International Symposium on Computer and Information Sciences(ISCIS).2008
[7] Farkas L G.Anthropometry of the Head and Face in Medicine[M].New York:Elsevier North Holland,1981
[8] Albert M,Ricanek K,Patterson E.A review of the literature on the aging adult skull and face:Implications for forensic science research and applications[J].Journal of Forensic Science International,2007,172(1):1-9
[9] Luu K,Bui T D,Ricanek J,et al.Age Estimation using Active Appearance Models and Support Vector Machine Regression[C]∥IEEE International Conference on Biometric:Theory,Application,and Systems(BTAS).Washington,DC,U.S.,2009
[10] Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).2005,1:886-893
[11] Ling Hai-bin,Soatto S,Ramanathan N,et al.A Study of Face Recognition as People Age[C]∥International Conference on Computer Vision(ICCV).2007:1-8
[12] Mao Xiao-jiao,Yang Yu-bin,Li Ning,et al.Age-Invariant Face Verification Based on Local Classifier Ensemble[C]∥21st International Conference on Pattern Recognition (ICPR 2012).Tsukuba,Japan,November 2012:11-15
[13] Ojala T,Pietikainen M,Harwood D.Performance evaluation of texture measures with classification based on Kullback discrimination of distributions[C]∥Proceedings of the 12th IAPR International Conference on Pattern Recognition (ICPR).1994:582-585
[14] Vapnik V.Statistical learning theory[M].New York:Wiley-Interscience,1998
[15] Guo Guo-dong,Mu Guo-wang,Fu Yun,et al.A Study on Automatic Age Estimation using a Large Database[C]∥International Conference on Computer Vision(ICCV).2009:1986-1991
[16] Lanitis A,Taylor C,Cootes T.Modeling the process of ageing in face images[C]∥ICCV 1999.1999:131-136
[17] Ricanek K,Tesafaye T.MORPH:A longitudinal Image Database of Normal Adult Age-Progression[C]∥FG 2006.2006
[18] Viola P A,Jones M J.Rapid object detection using a boosted cascade of simple features[C]∥Computer Vision and Pattern Recognition(CVPR).2001,1:511-518
[19] Wang Jian-gang,Yau Wei-yun, Wang Hee Lin.Age Categorization via ECOC with Fused Gabor and LBP Features[C]∥Workshop on Applications of Computer Vision(WACV).2009:1-6
[20] Fan R E,Chang K W,Hsieh C J,et al.Liblinear:A library for large linear classification[J].The Journal of Machine Learning Research,2008,9:1871-1874
[21] Chang K Y,Chen C S,Hung Y P.A ranking approach for human ages International estimation based on face images[C]∥2010 20th International Conference on Pattern Recognition (ICPR).IEEE,2010:3396-3399
[22] Mu G,Guo G,Fu Y,Huang T S.Human age estimation using bio-inspired features[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:112-119

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!