一种面向人脸识别的加权代价敏感局部保持投影
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(60873176, 61272222, 61003116); 江苏省自然科学基金(BK2011782, BK2011005); 江苏省创新基金(CXZZ12_0386)


Weighted Cost Sensitive Locality Preserving Projection for Face Recognition
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    传统的局部保持降维方法追求最低的识别错误率,即假设每一类的错分代价都是相同的.这个假设在真实的人脸识别应用中往往是不成立的.人脸识别是一个多类的代价敏感和类不平衡问题.例如,在人脸识别的门禁系统中,将入侵者错分成合法者的损失往往高于将合法者错分成入侵者的损失.因此,每一类的错分代价是不同的.另外,如果任一类合法者的样本数少于入侵者的样本数,该类合法者和入侵者就是类别不平衡的.为此,将错分代价融入到局部保持的降维模型中,提出了一种错分代价最小化的局部保持降维方法.同时,采用加权策略平衡了各类样本对投影方向的贡献.在人脸数据集AR,PIE,Extended Yale B 上的实验结果表明了该算法的有效性.

    Abstract:

    Conventional locality preserving projection aims to minimize recognition error rate, implicitly assuming the losses of different misclassifications are the same. However, this may not hold in many real world face recognition applications. Face recognition is a multiclass cost sensitive and class imbalance task. For example, it will be troublesome if a gallery person is misclassified as an impostor, but it will be much more costly if an impostor is misclassified as a gallery person. Consequently, different kinds of mistakes will lead to different losses. Moreover, the examples of gallery person from any class are fewer than examples of the impostor, which is referred to as class imbalance. For that, this paper integrates the misclassification costs into an objective function of the locality preserving projection and proposes a cost sensitive locality preserving projection that minimizes the misclassification costs. Simultaneously, a weight strategy is used to balance the contribution of each class to the projection. Experimental results on AR, PIE, Extended Yale B datasets demonstrate the superiority of the proposed method.

    参考文献
    相似文献
    引证文献
引用本文

万建武,杨明,吉根林,陈银娟.一种面向人脸识别的加权代价敏感局部保持投影.软件学报,2013,24(5):1155-1164

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2011-12-18
  • 最后修改日期:2012-05-18
  • 录用日期:
  • 在线发布日期: 2013-05-07
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号