基于区域的年龄估计模型研究

doi:10.11896/j.issn.1002-137X.2018.08.008

摘要/Abstract

摘要： 随着年龄特征提取和年龄特征分类模式研究的不断深入,为了进一步满足基于年龄信息的人机交互系统在现实生活中的应用需求,构建有效的机器学习算法已成为人脸图像年龄估计技术的研究热点之一。首先,通过分析人脸图像的多个区域特征随年龄变化的规律,将面部分为前额区域、眼部区域、面中部区域及人脸整体区域,并分别构建深度卷积神经网络特征提取模型,实现每个区域年龄的特征提取;其次,以 Morph人脸库为样本集,将其划分为10～19岁、20～29岁、30～39岁、40～49岁、50～59岁、60岁以上6个年龄段,完成多区域年龄特征提取网络模型的训练及测试;最后,依据多区域网络年龄特征分类的准确率,确定基于区域的动态权值年龄估计模型。实验表明:所提模型在Morph人脸库中的年龄估计准确率达到72.6%,也将该人脸库的年龄分类类别由4个提升到6个。

关键词: 年龄估计, 年龄特征, 动态权值, Morph年龄库, 深度学习

Abstract: With the further research on age feature extraction and age feature classification pattern,in order to make further efforts to meet the application demand of human-computer interaction system based on age information in real life,constructing an effective machine learning algorithm has become a research focus in age estimation technology of face image.Firstly,this paper analyzed the rule of multiple regional features changing with age,and divided the face into prefrontal region,eye region,central region and integrated region.Then,it constructed features extraction model of deep convolutional neural network models separately to extract age features of each region.Thirdly,taking Morph face database as the sample set,this paper divided it into 6 stages aged 10～19,20～29,30～39,40～49,50～59,and 60 years or older to train and test age feature extraction network model in multiple regions.Finally,according to the accuracy of age feature classification model,this paper defined the region-based dynamic weight age estimation model.The experiment shows that the accuracy of age estimation on Morph face database is 72.6%,and the age classification category has been raised from 4 to 6.

Key words: Age estimation, Age characteristics, Dynamic weights, Morph age database, Deep learning

中图分类号:

TP391

孙劲光, 荣文钊. 基于区域的年龄估计模型研究[J]. 计算机科学, 2018, 45(8): 41-49.

SUN Jin-guang, RONG Wen-zhao. Research on Regional Age Estimation Model[J]. Computer Science, 2018, 45(8): 41-49.

参考文献

[1]KWON Y H.Age classification from facial images[C]∥1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1994(CVPR’94).IEEE,1994:762-767.
[2]HORNG W B.Classification of age groups based on facial features[J].淡江理工学刊,2001,4(3):183-192.
[3]DEHSHIBI M M,BASTANFARD A.A new algorithm for age recognition from facial images[J].Signal Processing,2010,90(8):2431-2444.
[4]HAYASHI J,YASUMOTO M,ITO H,et al.Age and gender estimation based on wrinkle texture and color of facial images[C]∥16th International Conference on Pattern Recognition,2002.IEEE,2002:405-408.
[5]NAKANO M,YASUKATA F,FUKUMI M.Age classification from face images focusing on edge information[C]∥Knowledge-based Intelligent Information and Engineering Systems.Springer Berlin/Heidelberg,2004:898-904.
[6]TXIA J D,HUANG C L.Age estimation using AAM and local facial features[C]∥Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing,2009(IIH-MSP’09).IEEE,2009:885-888.
[7]GUO G,MU G,FU Y,et al.Human age estimation using bio-inspired features[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:112-119.
[8]ZHANG Y,ZHOU Z H.A new age estimation method based on ensemble learning[J].Acta Automatica Sinica,2008,34(8):997-1000.(in Chinese)张宇,周志华.基于集成的年龄估计方法[J].自动化学报,2008,34(8):997-1000.
[9]YU Q,DU J X.Age estimation of facial images based on an improved non-negative matrix factorization algorithms[J].Journal of Imageand Graphics,2008,13(10):1865-1868.(in Chinese)余庆,杜吉祥.基于一种改进NMF算法的人脸年龄估计方法[J].中国图象图形学报,2008,13(10):1865-1868.
[10]DU J X,YU Q,ZHAI C M.Age estimation of facial images based on non-negative matrix factorization with sparseness constraints[J].Journal of Shandong University (Natural Science),2010,45(7):65-69.(in Chinese)杜吉祥,余庆,翟传敏.基于稀疏性约束非负矩阵分解的人脸年龄估计方法[J].山东大学学报(理学版),2010,45(7):65-69.
[11]GENG X,ZHOU Z H,SMITH-MILES K.Automatic age estimation based on facial aging patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(12):2234-2240.
[12]LEVI G,HASSNER T.Age and gender classification using convolutional neural networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2015:34-42.
[13]YI D,LEI Z,LI S Z.Age estimation by multi-scale convolutional network[C]∥Asian Conference on Computer Vision.Springer International Publishing,2014:144-158.
[14]ROTHE R,TIMOFTE R,VAN GOOL L.Dex:Deep expecta-tion of apparent age from a single image[C]∥Procee-dings of the IEEE International Conference on Computer Vision Workshops.2015:10-15.
[15]LIU X,LI S,KAN M,et al.Agenet:Deeply learned regressor and classifier for robust apparent age estimation[C]∥Procee-dings of the IEEE International Conference on Computer Vision Workshops.2015:16-24.
[16]ANTIPOV G,BACCOUCHE M,BERRANI S A,et al.Appa-rent age estimation from face images combining general and children-specialized deep learning models[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2016:96-104.
[17]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems.2012:1097-1105.
[18]LEMPERLE G,HOLMES R E,LEMPERLE S S M.A Classification of Facial Wri[J].Plastic and Reconstructive Surgery,2001,108(6):1735-1750.
[19]LI Y L,ZHENG L B,YU K L,et al.Variation of head and facial morphological characteristics with increased age of Han in Southern China[J].Chinese Science Bulletin,2013,58(4／5):517-524.(in Chinese)李咏兰,郑连斌,宇克莉,等.南方汉族人头面部形态特征的年龄变化[J].科学通报,2013,58(4):336-343.
[20]SONG X,ZHANG X H,YU K L,et al.Age variations of morphological traits of head and face in Qiangnationality in Sichuan [J].Journal of Tianjin Normal University (Natural Science Edition),2016,36(2):69-74.(in Chinese)宋雪,张兴华,宇克莉,等.四川羌族头面部特征的年龄变化[J].天津师范大学学报 (自然科学版),2016,36(2):69-74.
[21]LI Y L,LU S H,ZHENG L B,et al.Age variation of head and facial morphology in Han nationality in Jiangxi province [J].Acta an Thropologica Sinica,2012,31(2):193-201.(in Chinese)李咏兰,陆舜华,郑连斌,等.江西汉族人头面部形态特征的年龄变化[J].人类学学报,2012,31(2):193-201.
[22]李咏兰,郑连斌,宇克莉,等.中国北方汉族人头面部形态特征的年龄变化[C]∥中国解剖学会2015年年会论文文摘汇编.2015.
[23]ZHENG L B,ZHANG X H,HU Y,et al.Variation of Morphological Traits in Head-facial Values of Han in Qionglai of Sichuan Province[J].Journal of Sun Yat-sen University (Medical Sciences),2011,32(6):729-734.(in Chinese)郑连斌,张兴华,胡莹,等.四川邛崃汉族头面部形态特征的年龄变化[J].中山大学学报(医学科学版),2011,32(6):729-734.
[24]RICANEK K,TESAFAYE T.Morph:A longitudinal image database of normal adult age-progression[C]∥7th International Conference on Automatic Face and Gesture Recognition,2006(FGR 2006).IEEE,2006:341-345.
[25]WANG X M,LIANG L Y,WANG Z L,et al.Age estimation by facial image:a survey[J].Journal of Image and Graphics,2012,17(6):603-618.(in Chinese)王先梅,梁玲燕,王志良,等.人脸图像的年龄估计技术研究[J].中国图象图形学报,2012,17(6):603-618.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed