计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 41-49.doi: 10.11896/j.issn.1002-137X.2018.08.008

• 2017 中国多媒体大会 • 上一篇    下一篇

基于区域的年龄估计模型研究

孙劲光, 荣文钊   

  1. 辽宁工程技术大学电子与信息工程学院 辽宁 葫芦岛125105
  • 收稿日期:2017-10-25 出版日期:2018-08-29 发布日期:2018-08-29
  • 作者简介:孙劲光(1962-),女,博士,教授,CCF高级会员,主要研究方向为计算机图像处理、计算机图形学、知识工程; 荣文钊(1990-),男,硕士生,主要研究方向为计算机图像处理,E-mail:mrdlzhao@aliyun.com(通信作者)。
  • 基金资助:
    本文受国家自然科学基金青年基金:地震勘探大数据的高精度处理技术研究(61602226)资助。

Research on Regional Age Estimation Model

SUN Jin-guang, RONG Wen-zhao   

  1. School of Electronic and Information Engineering,Liaoning Technical University,Huludao,Liaoning 125105,China
  • Received:2017-10-25 Online:2018-08-29 Published:2018-08-29

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
[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.
[1] 董晓梅, 王蕊, 邹欣开. 面向推荐应用的差分隐私方案综述[J]. 计算机科学, 2021, 48(9): 21-35.
[2] 周新民, 胡宜桂, 刘文洁, 孙荣俊. 基于多模态多层级数据融合方法的城市功能识别研究[J]. 计算机科学, 2021, 48(9): 50-58.
[3] 钱梦薇, 过弋. 融合偏置深度学习的距离分解Top-N推荐算法[J]. 计算机科学, 2021, 48(9): 103-109.
[4] 徐涛, 田崇阳, 刘才华. 基于深度学习的人群异常行为检测综述[J]. 计算机科学, 2021, 48(9): 125-134.
[5] 张新峰, 宋博. 一种基于改进三元组损失和特征融合的行人重识别方法[J]. 计算机科学, 2021, 48(9): 146-152.
[6] 林椹尠, 张梦凯, 吴成茂, 郑兴宁. 利用生成对抗网络的人脸图像分步补全法[J]. 计算机科学, 2021, 48(9): 174-180.
[7] 黄晓生, 徐静. 基于PCANet的非下采样剪切波域多聚焦图像融合[J]. 计算机科学, 2021, 48(9): 181-186.
[8] 田野, 陈宏巍, 王法胜, 陈兴文. 室内移动机器人的SLAM算法综述[J]. 计算机科学, 2021, 48(9): 223-234.
[9] 谢良旭, 李峰, 谢建平, 许晓军. 基于融合神经网络模型的药物分子性质预测[J]. 计算机科学, 2021, 48(9): 251-256.
[10] 冯霞, 胡志毅, 刘才华. 跨模态检索研究进展综述[J]. 计算机科学, 2021, 48(8): 13-23.
[11] 王立梅, 朱旭光, 汪德嘉, 张勇, 邢春晓. 基于深度学习的民事案件判决结果分类方法研究[J]. 计算机科学, 2021, 48(8): 80-85.
[12] 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨. 基于通道注意递归残差网络的图像超分辨率重建[J]. 计算机科学, 2021, 48(8): 139-144.
[13] 刘帅, 芮挺, 胡育成, 杨成松, 王东. 基于深度学习SuperGlue算法的单目视觉里程计[J]. 计算机科学, 2021, 48(8): 157-161.
[14] 王施云, 杨帆. 基于U-Net特征融合优化策略的遥感影像语义分割方法[J]. 计算机科学, 2021, 48(8): 162-168.
[15] 田嵩旺, 蔺素珍, 杨博. 基于多判别器的多波段图像自监督融合方法[J]. 计算机科学, 2021, 48(8): 185-190.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 编辑部. 新网站开通,欢迎大家订阅![J]. 计算机科学, 2018, 1(1): 1 .
[2] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[3] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[4] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[5] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[6] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[7] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[8] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[9] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[10] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .