首页 | 官方网站   微博 | 高级检索  
     

基于降维的堆积降噪自动编码机的表情识别方法
引用本文:赵军,赵艳,杨勇,朴仁圭,黄勇.基于降维的堆积降噪自动编码机的表情识别方法[J].重庆邮电大学学报(自然科学版),2016,28(6):844-848.
作者姓名:赵军  赵艳  杨勇  朴仁圭  黄勇
作者单位:1. 重庆邮电大学 计算智能重庆市重点实验室,重庆,400065;2. 重庆邮电大学 计算智能重庆市重点实验室,重庆400065; 韩国仁荷大学 情报通信工学部,仁川402751;3. 韩国仁荷大学 情报通信工学部,仁川,402751
基金项目:重庆市自然科学基金项目(CSTC,2007BB2445);韩国科学与信息科技未来规划部2013年ICT研发项目(10039149)
摘    要:堆积降噪自动编码机是一种典型的深度学习模型,它能够刻画数据丰富的内在信息,具有较强的特征学习能力。基于主成分分析(principal component analysis,PCA)技术和堆积降噪自动编码机(stacked denoising autoen-coders,SDAE)模型,提出一种新的表情识别算法PCA+SDAE。该算法对人脸图片进行裁剪及归一化等预处理,采用主成分分析技术对人脸特征进行线性降维,再利用堆积降噪自动编码机逐层进行特征学习并同时实现对人脸表情数据的非线性降维,可以得到更好的、维度更低的表情特征,并据此进行表情分类。对PCA+SDAE算法的仿真测试实验结果表明,其综合性能比其他的基于深度学习模型的表情识别方法更好,同时与传统的非深度学习表情识别方法相比,它具有更高的表情识别正确率。

关 键 词:表情识别  深度学习  堆积降噪自动编码机  主成分分析
收稿时间:2016/3/15 0:00:00
修稿时间:2016/7/20 0:00:00

Facial expression recognition method based on stacked denoising auto-encoders and feature reduction
ZHAO Jun,ZHAO Yan,YANG Yong,PARK Inkyu and HUANG Yong.Facial expression recognition method based on stacked denoising auto-encoders and feature reduction[J].Journal of Chongqing University of Posts and Telecommunications,2016,28(6):844-848.
Authors:ZHAO Jun  ZHAO Yan  YANG Yong  PARK Inkyu and HUANG Yong
Affiliation:Chongqing Key Laboratory of Computational and Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China;,Chongqing Key Laboratory of Computational and Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China;,Chongqing Key Laboratory of Computational and Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China;Department of Information and Communication Engineering, Inha University, Incheon 402-751, Korea,Department of Information and Communication Engineering, Inha University, Incheon 402751, Korea and Chongqing Key Laboratory of Computational and Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China;
Abstract:A Stacked Denoising Auto-Encoders (SDAE) is a typical deep learning model. Because of its capability of disclosing rich inherent information from data, and it has a strong ability of leaning features. Herein, a new algorithm principal components analysis+stacked denoising auto-encoders (PCA+SDAE) for facial expression recognition is put forward on the bases of principal components analysis (PCA) technology and stacked denoising auto-encoders model. By the new algorithm PCA+SDAE, a facial image is firstly processed by cutting and normalization; then the linear dimensionality of its expression features is reduced by PCA; lastly, a greed layer-wise feature learning is conducted by a SDAE, and the nonlinear dimensionality of its expression features is simultaneously reduced. Consequently, facial expression can be recognized based on the more powerful and lower dimensional facial features can be obtained. The results of simulation test experiments on algorithm PCA+SDAE show that the proposed method has better overall performance than some other expression recognition methods based on deep learning models; and it can also get higher expression recognition accuracy than traditional non-deep learning based expression recognition methods.
Keywords:facial expression recognition  deep learning  stacked denoising autoencoders  principal component analysis  
本文献已被 万方数据 等数据库收录!
点击此处可从《重庆邮电大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《重庆邮电大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号