中国邮电高校学报(英文) ›› 2011, Vol. 18 ›› Issue (1): 91-97.doi: 10.1016/S1005-8885(10)60033-7

• Artificial Intelligence • 上一篇    下一篇

Orthogonal isometric projection for face recognition

卢官明,左加阔   

  1. 南京邮电大学
  • 收稿日期:2010-06-21 修回日期:2010-11-06 出版日期:2011-02-28 发布日期:2011-02-28
  • 通讯作者: 卢官明 E-mail:lugm@njupt.edu.cn
  • 基金资助:

    江苏省基础研究计划(自然科学基金);江苏省高校自然科学研究项目

Orthogonal isometric projection for face recognition

Jia-Kuo ZUO2   

  • Received:2010-06-21 Revised:2010-11-06 Online:2011-02-28 Published:2011-02-28
  • Contact: LU Guan-ming E-mail:lugm@njupt.edu.cn
  • Supported by:

    Natural Science Foundation of Jiangsu Province;Natural Science Research Project for Colleges and Universities in Jiangsu Province

摘要:

Isometric projection (IsoProjection) is a linear dimensionality reduction method, which explicitly takes into account the manifold structure embedded in the data. However, IsoProjection is non-orthogonal, which makes it extremely sensitive to the dimensions of reduced space and difficult to estimate the intrinsic dimensionality. The non-orthogonality also distorts the metric structure embedded in the data. This paper proposes a new method called orthogonal isometric projection (O-IsoProjection), which shares the same linear character as IsoProjection and overcomes the metric distortion problem of IsoProjection. Similar to IsoProjection, O-IsoProjection firstly constructs an adjacency graph which can reflect the manifold structure embedded in the data and the class relationship between the sample points of face space, and then obtains the projections by preserving such a graph structure. Different from IsoProjection, O-IsoProjection requires the basis vectors to be orthogonal, and the orthogonal basis vectors can be calculated by iterative way. Experimental results on ORL and Yale databases show that O-IsoProjection has better recognition rate for face recognition than Eigenface, Fisherface and IsoProjection.

关键词:

IsoProjection, O-IsoProjection, face recognition, dimensionality reduction

Abstract:

Isometric projection (IsoProjection) is a linear dimensionality reduction method, which explicitly takes into account the manifold structure embedded in the data. However, IsoProjection is non-orthogonal, which makes it extremely sensitive to the dimensions of reduced space and difficult to estimate the intrinsic dimensionality. The non-orthogonality also distorts the metric structure embedded in the data. This paper proposes a new method called orthogonal isometric projection (O-IsoProjection), which shares the same linear character as IsoProjection and overcomes the metric distortion problem of IsoProjection. Similar to IsoProjection, O-IsoProjection firstly constructs an adjacency graph which can reflect the manifold structure embedded in the data and the class relationship between the sample points of face space, and then obtains the projections by preserving such a graph structure. Different from IsoProjection, O-IsoProjection requires the basis vectors to be orthogonal, and the orthogonal basis vectors can be calculated by iterative way. Experimental results on ORL and Yale databases show that O-IsoProjection has better recognition rate for face recognition than Eigenface, Fisherface and IsoProjection.

Key words:

IsoProjection, O-IsoProjection, face recognition, dimensionality reduction

中图分类号: