计算机科学 ›› 2018, Vol. 45 ›› Issue (1): 152-156.doi: 10.11896/j.issn.1002-137X.2018.01.026

• 第十六届中国机器学习会议 • 上一篇    下一篇

基于集成卷积神经网络的人脸年龄分类算法研究

马文娟,董红斌   

  1. 哈尔滨工程大学计算机科学与技术学院 哈尔滨150001,哈尔滨工程大学计算机科学与技术学院 哈尔滨150001
  • 出版日期:2018-01-15 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金(61472095,61573362),黑龙江省教育厅智能教育与信息工程重点实验室开放基金资助

Face Age Classification Method Based on Ensemble Learning of Convolutional Neural Networks

MA Wen-juan and DONG Hong-bin   

  • Online:2018-01-15 Published:2018-11-13

摘要: 人脸年龄估计由于在人机交互和安全控制等领域有潜在应用,因此得到了广泛关注。文中主要进行人脸年龄分组的研究,针对人脸年龄分类问题提出了一种基于集成卷积神经网络的年龄分类算法。首先,训练两个以人脸图像为输入的卷积神经网络,当用卷积神经网络直接提取人脸图像的特征时,主要对 深度的全局特征 进行提取。为了补充人脸图像的局部特征,尤其是纹理信息,将提取的LBP(Local Binary Pattern)特征作为另一个网络的输入。最后,为了结合人脸的全局特征和局部特征,将这3个网络进行集成。该算法在广泛使用的年龄分类数据集Group上取得了不错的效果。

关键词: 卷积神经网络,年龄分类,集成

Abstract: Face age estimation has attracted much attention due to its potential applications in the areas of human-computer interaction and safety control.This paper focused on face age classification task,and proposed an age classification algorithm based on ensemble convolutional neural network for face age classification.Firstly,two convolutional neural networks which make face images as input are trained,and the deeply global features are extracted mainly by using convolutional neural network.In order to further supply the local features of face images,especially texture information,the extracted LBP feature will be taken as input for another network.Finally,in order to combine the global features and the local features of the face images,three networks are integrated to generate good results in the widely used age estimation dataset.

Key words: Convolutional neural network,Age classification,Ensemble

[1] HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[2] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNetclassification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems.Curran Associates Inc.,2012:1097-1105.
[3] GALLAGHER A C,CHEN T.Understanding images of groups of people[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:256-263.
[4] KWON Y H,VITORIA LOBO N D.Age classification from facial images[J].Computer Vision and Image Understanding,1999,74(1):1-21.
[5] NAKANO M,YASUKATA F,FUKUMI M.Age Classification from Face Images Focusing on Edge Information[M]∥Know-ledge-Based Intelligent Information and Engineering Systems.Springer Berlin Heidelberg,2004:898-904.
[6] LANITIS A,DRAGNOVA C,CHRISTODOULOU C.Compa-ring different classifiers for automatic age estimation[J].IEEE Transactions on Systems Man & Cyberne-tics Part B Cyberne-tics A Publication of the IEEE Systems Man & Cybernetics So-ciety,2004,34(1):621-628.
[7] GENG X,ZHOU Z H,ZHANG Y,et al.Learning from facialaging patterns for automatic age estimation[C]∥ACM International Conference on Multimedia.Santa Barbara,Ca,USA,DBLP,2006:307-316.
[8] GENG X,SMITH-MILESK,ZHOU Z H.Facial age estimation by learning from label distributions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(10):2401-2412.
[9] FU Y,XU Y,HUANG T S.Estimating Human Age by Manifold Analysis of Face Pictures and Regression on Aging Features[C]∥IEEE International Conference on Multimedia and Expo.IEEE,2007:1383-1386.
[10] GUO L L,DING S F.Research Progress on Deep Learning[J].Computer Science,2015,42(5):28-33.(in Chinese) 郭丽丽,丁世飞.深度学习研究进展[J].计算机科学,2015,42(5):28-33.
[11] PAN Q X,DONG H B,HAN Q L,et al.A computing methodfor attribute importance based on BP neural network[J].Journal of University of Science and Technology of China,2017(1):18-25.(in Chinese) 潘庆先,董红斌,韩启龙,等.一种基于BP神经网络的属性重要性计算方法[J].中国科学技术大学学报,2017(1):18-25.
[12] LEVI G,HASSNCER T.Age and gender classification usingconvolutional neural networks[C]∥Computer Vision and Pattern Recognition Workshops.IEEE,2015:34-42.
[13] DONG Y,LIU Y,LIAN S.Automatic age estimation based ondeep learning algorithm[J].Neurocomputing,2016,187:4-10.
[14] ZHUANG F Z,LUO P,HE Q.Survey on Transfer LearningResearch[J].Journal of Software,2015,26(1):26-39.(in Chinese) 庄福振,罗平,何清.迁移学习研究进展[J].软件学报,2015,26(1):26-39.
[15] LI Y D,HAO Z B,LEI H.Survey of convolutional neural network[J].Journal of Computer Applications,2016,36(9):2508-2515.(in Chinese) 李彦冬,郝宗波,雷航.卷积神经网络研究综述[J].计算机应用,2016,36(9):2508-2515.
[16] OJALA T,PIETIKLNEN M,MENP T.Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2000,1842(7):404-420.
[17] AHONEN T,HADID A,PIETIKLNEN M.Face Recogni-tion with Local Binary Patterns[M].IEEE Computer Society,2006.
[18] ZHOU Z H,CHEN S F.Neural Network Ensemble[J].Chinese Journal of Computers,2002,25(1):1-8.(in Chinese) 周志华,陈世福.神经网络集成[J].计算机学报,2002,25(1):1-8.
[19] KROGH A,VEDLEBSBY J.Neural network ensembles,crossvalidation and active learning[C]∥International Conference on Neural Information Processing Systems.MIT Press,1994:231-238.
[20] SHAN C.Learning local features for age estimation on real-life faces[C]∥ACM International Workshop on Multimodal Pervasive Video Analysis.ACM,2010:23-28.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!