计算机应用 ›› 2013, Vol. 33 ›› Issue (07): 1930-1934.DOI: 10.11772/j.issn.1001-9081.2013.07.1930

• 人工智能 • 上一篇    下一篇

基于马氏距离的局部边界Fisher分析降维算法

李峰1,王正群1,徐春林2,周中侠1,薛巍1   

  1. 1. 扬州大学 信息工程学院,江苏 扬州 225127
    2. 北方激光科技集团有限公司 激光应用技术部,江苏 扬州 225009
  • 收稿日期:2013-01-06 修回日期:2013-02-26 出版日期:2013-07-01 发布日期:2013-07-06
  • 通讯作者: 李峰
  • 作者简介:李峰(1987-),男,江苏淮安人,硕士研究生,主要研究方向:模式识别、人工智能;王正群(1965-),男,江苏如东人,教授,博士,主要研究方向:模式识别、机器学习;徐春林(1969-),男,江苏兴化人,研究员级高级工程师,主要研究方向:信号处理;周中侠(1988-),男,山东菏泽人,硕士研究生,主要研究方向:机器学习;薛巍(1989-),男,江苏苏州人,硕士研究生,主要研究方向:模式识别。
  • 基金资助:

    国家自然科学基金资助项目(61175111);江苏省高校自然科学基金资助项目(10KJB510027)

Dimensionality reduction algorithm of local marginal Fisher analysis based on Mahalanobis distance

LI Feng1,WANG Zhengqun1,XU Chunlin2,ZHOU Zhongxia1,XUE Wei1   

  1. 1. College of Information Engineering, Yangzhou University, Yangzhou Jiangsu 225127, China
    2. Department of Laser Application Technology, North Laser Technology Group Company Limited, Yangzhou Jiangsu 225009, China
  • Received:2013-01-06 Revised:2013-02-26 Online:2013-07-06 Published:2013-07-01
  • Contact: LI Feng

摘要: 针对人脸识别应用中的高维数据图像以及欧氏距离不能准确体现样本间的相似度的问题,提出了一种基于马氏距离的局部边界Fisher分析(MLMFA)降维算法。该算法从现有的样本中学习得到一个马氏度量,然后在近邻选择以及新样本降维过程中用马氏距离作为相似性度量。同时,通过马氏度量构造出类内“相似”图和类间“代价”图来描述数据集的类内紧凑性和类间分离性。MLMFA很好地保持了数据集的局部结构。用YALE和FERET人脸库进行实验,MLMFA的最大识别率比传统基于欧氏距离算法的最大识别率平均分别提高了1.03%和6%。实验结果表明,算法MLMFA具有很好的分类和识别性能。

关键词: 马氏距离, 局部边界Fisher分析, 降维, 人脸识别

Abstract: Considering high dimensional data image in face recognition application and Euclidean distance cannot accurately reflect the similarity between samples, a Mahalanobis distance based Local Marginal Fisher Analysis (MLMFA) dimensionality reduction algorithm was proposed. A Mahalanobis distance could be ascertained from the existing samples. Then, the Mahalanobis distance was used to choose neighbors and to reduce the dimensionality of new samples. Meanwhile, to describe the intra-class compactness and the inter-class separability, intra-class “similarity” graph and inter-class “penalty” graph were constructed by using Mahalanobis distance, and local structure of data set was preserved well. With the proposed algorithm being conducted on YALE and FERET, MLMFA outperforms the algorithms based on traditional Euclidean distance with maximum average recognition rate by 1.03% and 6% respectively. The results demonstrate that the proposed algorithm has very good classification and recognition performance.

Key words: Mahalanobis Distance, Local Marginal Fisher Analysis, Dimensionality Reduction, Face Recognition

中图分类号: