计算机科学 ›› 2008, Vol. 35 ›› Issue (6): 196-198.

• • 上一篇    下一篇

基于多特征融合和BoostingRBF神经网络的人脸识别

嵇新浩 丁荣涛   

  1. 浙江商业职业技术学院信息技术系,杭州310053
  • 出版日期:2018-11-16 发布日期:2018-11-16

JI Xin-hao, DING Rong-tao (Information Technology Department,Zhejiang Vocational College of Commerce, Hangzhou 310053,China)   

  • Online:2018-11-16 Published:2018-11-16

摘要: 提出一种多特征信息融合的人脸识剐方法。应用Zemike矩方法和非负矩阵分解法(NMF)分别提取具有旋转不变性的人脸几何特征和人脸子空间投影系数特征,将这两种具有一定互补性的特征串行融合,得到一个分类能力更强的特征。在此基础上,采用RBF神经网络进行人脸识别。为了提高神经网络的分类准确率和泛化能力,采用Boosting方法进行网络集成。实验结果表明,提出的算法利用较少样本数据即可快速地进行人脸识别。

关键词: 人脸识别 Zemike矩 非负矩阵分解法 Boosting方法 RBF神经网络

Abstract: A new face recognition method based on feature fusion was proposed. Firstly, face projection coefficient features were extracted by NMF methods. Then these features were combined with the face rotation invariance Zernike moments features so as to get a ne

Key words: Face recognition, Zernike moments, Non-negative matrix factorization(NMF), Boosting algorithm, RBF neural network

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!