期刊文献+

基于小波变换和独立分量分析的面部表情识别 被引量:1

Facial expression recognition based on 2D-DWT and ICA
下载PDF
导出
摘要 提出了一种联合二维离散小波变换(2D-DWT)和独立分量分析(ICA)相结合的表情特征提取法。首先通过2D-DWT将当前图像分解成4个子图像,其中一子图像对应原图像的主体部分(低通部分),其余三个子图像对应图像的细节部分(高通部分)。采用ICA分别对每一子图像进行特征提取,得到的表情矢量与中性矢量的差值矢量作为特征矢量,在此基础上使用性能比较稳定的支持向量机来分析各个子带图像的识别情况。此外,还提出了一种简单有效的方法对各个子图像所提取的特征进行融合,将融合的结果作为特征矢量来识别。同其它基于静态图像识别的方法相比,所提的方法识别效果好,且具有一定泛化性和鲁棒性。 An efficient facial expression recognition method by combining the two-dimensional Discrete Wavelet Transform (2D- DWT) method with the Independent Component Analysias(ICA) method are proposed.First,each image is decomposed into four sub-images by using the 2D-DWT approach,and then ICA approach is used to extract features form each sub-image respectively.Then,the differences of extracted features are obtained by subtracting features of neutral expression from the features of other expressions.All the differences of features are further combined and used for facial expression classification.Moreover, considering that the discriminative features extracted from each sub-image may not share the same metric scale measure,the authors also propose an effective features combination method in this paper.These experiment results indicate that the recognition ratios of facial expression are heightened by this method.
出处 《计算机工程与应用》 CSCD 北大核心 2008年第10期188-191,共4页 Computer Engineering and Applications
基金 江苏大学高级专业人才科研启动基金资助项目(No.05JDG020)
关键词 表情识别 二维离散小波变换 独立分量分析 支持向量机 facial expression recognition 2D Discrete Wavelet Transform Independent Component Analysis Support Vector Machine
  • 相关文献

参考文献10

  • 1王志良,刘芳,王莉.基于计算机视觉的表情识别技术综述[J].计算机工程,2006,32(11):231-233. 被引量:12
  • 2Lanitis A,Taylor C,Cootes T F.Automatic interpretation and coding of face images using flexible models[J].IEEE Trans on Pattern Analysis and Machine Intelligence, 1997,19:743-756.
  • 3Calder A J,Burton A M,MillerP,et al.A principal component analysis off facial expression,vision reseach[R].2001.1179-1208.
  • 4Tian Ying-li,Kanade T,Cohn J F.Evaluation of gab or wavelet based facial action unit recognition in image sequences of increase complexity[C]//IEEE on Automatic Face and Gesture Recognition, 2002. 229-234.
  • 5Comon P.Indepent component analysis:a new concept [J].Signal Processing, 1994,36(3 ) : 287-314.
  • 6Jutten C,Herault J.Blind separation of sources.PartI:Anadaptive algorithm based on neuromimetic architecture[J].Signal Processing, 1991,24( 1 ) : 1-10.
  • 7Bueiu C I,Pitas K I.ICA and Gabor representation for expression expressions[C]//Int Conf on Image Processing,2003.
  • 8徐正光,闫恒川,张立欣.独立成分分析在表情识别中的应用[J].微计算机信息,2006(06Z):287-289. 被引量:8
  • 9Hyvarinen A.Fast and robust fixed-point algorithms for indepent component analysis[J],IEEE Trans on Neural Networks, 1999,10(3).
  • 10Cortes C,Vapnik V.Support vector networks[J].Machine Learning, 1995,20: 273-297.

二级参考文献11

  • 1王聃,贾云伟,林福严.人脸识别系统中的特征提取[J].微计算机信息,2005,21(07X):53-55. 被引量:18
  • 2刘芳.应用图像处理技术的人脸表情识别研究[D].北京:北京科技大学,2003—06—20.
  • 3Michel E Kaliouby R E. Real Time Facial Expression Recognition in Video Using Support Vector Machines[C]. ICMT03, 2003-11-5.
  • 4Buciu C I, Pitas K I. ICA and Gabor Representation for Facial Expression Recognition[C]. Int. Conf. on Image Processing, 2003:855-858.
  • 5Essa I A. Coding, Analysis, Interpretation, and Recognition of Facial Expressions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (7).
  • 6Alldrin N, Smith A, Turnbull D. Classifying Facial Expression with Radial Basis Function Networks, Using Gradient Descent and K-means[C]. CSE253, 2003.
  • 7Bouchra Abboud, Franck Davoine, Mo Dang. Expressive face recognition and synthesis for visual interaction[J/OL]. IEEE CVPR Workshop on Computer Vision and Pattern Recognition for Human Computer Interaction, Madison, USA, June 2003.
  • 8Aapo Hyvrinen, Erkki Oja. Independent Component Analysis:Algorithms and Applieations[J/OL]. Neural Networks, 2000. 13(4-5): p.411-430.
  • 9Aapo Hyv?rinen. Fast and Robust Fixed-Point Algorithms for Independent Component Analysis[J/OL]. IEEE Trans. on Neural Networks, 10(3):626-634, 1999.
  • 10杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报,2002,28(5):762-772. 被引量:148

共引文献17

同被引文献15

引证文献1

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部