[1]郑德鹏,杜吉祥,翟传敏.基于深度学习MPCANet的年龄估计[J].南京师范大学学报(自然科学版),2017,40(01):20.[doi:10.3969/j.issn.1001-4616.2017.01.004]
 Zheng Depeng,Du Jixiang,Zhai Chuanmin.Age Estimation Based on Deep Learning MPCANet[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(01):20.[doi:10.3969/j.issn.1001-4616.2017.01.004]
点击复制

基于深度学习MPCANet的年龄估计()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第40卷
期数:
2017年01期
页码:
20
栏目:
·数学与计算机科学·
出版日期:
2017-03-31

文章信息/Info

Title:
Age Estimation Based on Deep Learning MPCANet
文章编号:
1001-4616(2017)01-0020-07
作者:
郑德鹏杜吉祥翟传敏
华侨大学计算机科学与技术学院,福建 厦门 361021
Author(s):
Zheng DepengDu JixiangZhai Chuanmin
School of Computer Science and Technology,Huaqiao University,Xiamen 361021,China
关键词:
深度学习年龄估计多层PCA网络(MPCANet)
Keywords:
deep learningage estimationmulti principal component analysis network(MPCANet)
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2017.01.004
文献标志码:
A
摘要:
提出了一种基于多层PCA网络(MPCANet)的深度学习模型来进行年龄估计. 它是基于卷积神经网的结构来设计的,并且用来提取年龄特征. MPCANet是主成分分析网络(PCANet)的一种改进,它是最近提出的一种深度学习算法,MPCANet模型结构组成的成分:(1)卷积滤波层是采用多层级联主成分分析(PCA),(2)非线性层则采用二进制哈希,(3)特征抽取层使用直方图统计方法. 使用核支持向量回归(K-SVR)进行估计年龄值. 实验分别在两个数据库(FG-NET and MORPH)上进行,实验结果表明该方法比目前最新的方法表现得更好.
Abstract:
This paper investigates deep learning techniques for age estimation based on the multi principal component analysis network(MPCANet). A new framework for age feature extraction based on deep learning model with convolutional neural network(CNN)is built. The MPCANet is a variation of principal component analysis network(PCANet),which is recently proposes deep learning algorithms. The MPCANet model architecture components:(1)the use of Multi cascaded principal component analysis(PCA)in the convolution filter layer;(2)the nonlinear process layer by binary hashing; and(3)the use of block histogram in the feature pooling layer. We use K-SVR(Kernel function Support Vector Regression,K-SVR)for age estimation. Experimental results on two datasets(FG-NET and MORPH)show that the proposed approach is significantly better than the state-of-the-art.

参考文献/References:

[1] GENG X,ZHOU Z H,ZHANG Y,et al. Learning from facial aging patterns for automatic age estimation[C]//ACM International Conference on Multimedia. Santa Barbara,USA,2006:307-316.
[2]GUODONG G,YUN F,DYER C R,et al. Image-based human age estimation by manifold learning and locally adjusted robust regression.[J]. IEEE transactions on image processing,2008,17(7):1 178-1 188.
[3]LAWRENCE S,GILES C L,TSOI A C,et al. Face recognition:a convolutional neural-network approach[J]. IEEE transactions on neural networks,1997,8(1):98-113.
[4]KHALIL H M,SUNG L S. A convolutional neural network approach for face verification[C]//2014 International Conference on High Performance Computing and Simulation(HPCS). Bologna,Italy,2014:707-714.
[5]PATTABHI R N,IJJINA E P,MOHAN C K. Illumination invariant face recognition using convolutional neural networks[C]//IEEE International Conference on Signal Processing,Informatics,Communication and Energy Systems. Kozhikode,India:IEEE,2015:1-4.
[6]WANG X,GUO R,KAMBHAMETTU C. Deeply-learned feature for age estimation[C]//Applications of Computer Vision. Waikloloa,HI,USA:IEEE,2015:534-541.
[7]CHAN T H,JIA K,GAO S,et al. PCANet:a simple deep learning baseline for image classification[J]. IEEE transactions on image processing,2014,24(12):5 017-5 032.
[8]FUKAI H,TAKIMOTOY H,MITSUKURA Y. Age and gender estimation by using facial image[C]//Proceeding of the 11th IEEE International Workshop on Advances Motion Control. Nagaoka,Japan:IEEE Computer Society Press,2010:179-184.
[9]FU Y,HUANG T S. Human age estimation with regression on discriminative aging manifold[J]. IEEE transactions on multimedia,2008,10(4):578-584.
[10]ZHAI C M,YU Q,DU J X. Age estimation of facial images based on an improved non-negative matrix factorization algorithms[C]//Advanced Intelligent Computing Theories and Applications with Aspects of Artificial Intelligence,Proceedings of International Conference on Intelligent Computing,Icic 2010. Changsha,China,2010:1 865-1 868.
[11]RICANEK JR K,TESAFAYE T. MORPH:a longitudinal image database of normal adult age-progression[C]//IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. Southamptorm,UK,2006:341-345.
[12]CHANG K Y,CHEN C S,HUNG Y P. Ordinal hyperplanes ranker with cost sensitivities for age estimation[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Colorado Springs,USA:IEEE,2011:585-592.
[13]XIN G,ZHI H Z,KATE S M. Automatic age estimation based on facial aging patterns[J]. IEEE transactions on pattern analysis and machine intelligence,2007,29(12),2 234-2 240.
[14]GUO D G,YUN F,DYER C R,et al:Image-based human age estimation by manifold learning and locally adjusted robust regression[J]. IEEE transactions on image processing,2008,17(7):1 178-1 188.
[15]CHEN K,GONG S,XIANG T,et al. Cumulative attribute space for age and crowd density estimation[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Portland,USA:IEEE,2013:2 467-2 474.
[16]HADCHUM P,WONGTHANAVASU S. Facial age estimation using a hybrid of SVM and Fuzzy Logic[C]//2015 12th International Conference on Electrical Engineering/Electronics,Computer,Telecommunications and Information Technology(ECTI-CON). Hua Hin,Thailand:IEEE,2015:10-21.
[17]ZHENG D P,DU J X,FAN W T,et al. Deep learning with PCANet for human age estimation[M]//International Conference on Intelligent Computing. Lanzhou,China,2016:300-310.

备注/Memo

备注/Memo:
收稿日期:20016-08-20.
基金项目:国家自然科学基金(61673186、61502183)、福建省自然科学基金(2013J06014)、华侨大学中青年教师科研提升资助计划项目(ZQN-YX108)、华侨大学研究生科研创新能力培养项目(1400214009、1400214003).
通讯联系人:杜吉祥,教授,研究方向:模式识别、图像处理. E-mail:jxdu@hqu.edu.cn
更新日期/Last Update: 1900-01-01