Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (4): 239-241.

• 工程与应用 • Previous Articles     Next Articles

Person-independent expression recognition based on images adjusted by Hopfield network

LI Zheng-chun1,YING Zi-lu1,2   

  1. 1.School of Information,Wuyi University,Jiangmen,Guangdong 529020,China
    2.School of Electronics and Information Engineering,Beihang University,Beijing 100083,China
  • Received:2007-06-04 Revised:2007-08-03 Online:2008-02-01 Published:2008-02-01
  • Contact: LI Zheng-chun

一种经过Hopfield网调整后的非特定人表情识别

李正淳1,应自炉1,2   

  1. 1.五邑大学 信息学院,广东 江门 529020
    2.北京航空航天大学 电子信息工程学院,北京 100083
  • 通讯作者: 李正淳

Abstract: In this paper,a new method adjusted by Hopfield network is proposed for expression recognition.First,a standard expression images should be selected for training of Hopfield network.Then,when Hopfield network had been trained,all expression images would be adjusted to close with similar standard images.This would increase distances between seven expression images.It would benefit for expression recognition.Experiment result shows this method can highly improve recognition rates.

Key words: Hopfield, PCA, LDC, Fisherc, expression recognition

摘要: 采用了一种经过Hopfield网调整后再进行人脸表情识别的方法。先选取一套做得较好表情作为标准样本,用Hopfield网对这个标准样本进行训练。再把样本库中的全部样本用这个训练好的Hopfield网进行调整,由于Hopfield网吸引稳定作用,会使样本库中样本向标准样本中相似的样本靠拢,这样相当于利用它们的相似拉开了各类表情样本的距离,有利于以后进行的分类。实验结果表明,采用Hopfield网调整后的识别率得到了较大的提高。

关键词: Hopfield, PCA, LDC, Fisherc, 人脸表情识别