增量式正交局部判别投影法
DOI:
CSTR:
作者:
作者单位:

作者简介:

郑建炜(1982-),男,博士,讲师,主要研究方向为 模式识别、计算机视觉等.

通讯作者:

中图分类号:

TP391.41

基金项目:

国家自然科学基金(61070043)和浙江省自然科学基金(LQ12F03011)资助项目 (浙江工业大学 计算机科学与技术学院,浙江 杭州 310023)


Orthogonal locally discriminant projection algorithm for incremental data
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:

    针对现有投影分析算法随着输入数据量的增 加计算复杂度急剧增长这一问题,通过子块优化策略构建了目标投影模型,称之为增量 的局部判别投影(ILDP)算法。算法兼顾样本的类间离散度和类内紧凑性,求得的投影 矩阵 还具有正交性;通过子块叠加和奇异值升级算法对模型的求解进行了增量式扩展,计 算过程中并无出现矩阵逆操作,即规避了小样本问题。在COIL图像库、USPS手写字体库 和ExYaleB人脸库中的实验表明,对比经典的ILDA、LSDA、MMP等降维算法,ILDP具有更高的 识别率,尤其在USPS数据库中,ILDP的识别率接近于90%,而其它的 算法识别率都低于85%。 与此同时,ILDP的计算量也明显少于对比算法,在USPS数据库中仅需要少于0.5s的时间即可完成最优投影矩阵计算。

    Abstract:

    The standard implementation of traditional projection algorithms takes all the t raining samples as the input data,which scales badly with the dataset size and m akes computations for large samples application infeasible.We introduce a block optimization and batch alignment strategy to propose a novel locally discriminan t projection (LDP) algorithm for solving this problem.The advantages of the prop osed algorithm are:Firstly,it preserves the intra class structure of the manifol d and maximizes margins between the data of different classes;Secondly,the final projection matrix of the proposed algorithm has the orthogonality property;Thir dly,there is no small sample size problem in this algorithm;Finally,LDP can be e asily extended to the incremental LDP (ILDP) for learning the locally discrimina nt subspace with the newly inserted data by employing the singular value decompo sition updating algorithm.The experimental data by employing the singular value decomposition updating algoirthm.The experimental results on COIL image database ,USPS hand written digit database on ExYaleB face database demonstrate that ILDP has higher recognition rate compared with the classical ILDA,LSDA and MMP algor ithms.Especially in the USPS database,ILDP reaches recognition rate of 90% while the others are all below 85%.Meanwhile,ILDP bears less computational cost,which needs only less than 0.5s for training USPS database.

    参考文献
    相似文献
    引证文献
引用本文

郑建炜,王万良,蒋一波.增量式正交局部判别投影法[J].光电子激光,2013,(1):161~169

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:2012-06-15
  • 最后修改日期:2012-08-31
  • 录用日期:
  • 在线发布日期:
  • 出版日期:
文章二维码