Extension of mutual subspace method for low dimensional feature projection

被引:0
|
作者
Velikovic, Dragana [1 ]
Robbins, Kay A. [1 ]
Rubino, Doug [2 ]
Hatsopoulos, Nicholas G. [3 ]
机构
[1] Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
[2] Univ Calif San Diego, Dept Neurosci, La Jolla, CA 92093 USA
[3] Univ Chicago, Dept Organismal Biol & Anat, Chicago, IL 60637 USA
来源
2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7 | 2007年
关键词
feature extraction; distance measurement; multidimensional systems; visualization;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Face recognition algorithms based on mutual subspace methods (MSM) map segmented faces to single points on a feature manifold and then apply manifold learning techniques to classify the results. This paper proposes a generic extension to MSM for analysis of features in high-throughput recordings. We apply this method to analyze short duration overlapping waves in synthetic data and multielectrode brain recordings. We compare different feature space topologies and projection techniques, including MDS, ISOMAP and Laplacian eigenmaps. Overall we find that ISOMAP shows the least sensitivity to noise and provides the best, association between distance in feature space and Euclidean distance in projection space. For non-noisy data, Laplacian eigemnaps show the least sensitivity to feature space topology.
引用
收藏
页码:1013 / +
页数:2
相关论文
共 50 条
  • [22] A hybrid subspace projection method for system identification
    Kim, SP
    Rao, YN
    Erdogmus, D
    Principe, JC
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL VI, PROCEEDINGS: SIGNAL PROCESSING THEORY AND METHODS, 2003, : 321 - 324
  • [23] Low sidelobe pattern synthesis using projection method with mutual coupling compensation
    Kojima, N
    Hariu, KI
    Chiba, I
    IEEE INTERNATIONAL SYMPOSIUM ON PHASED ARRAY SYSTEMS AND TECHNOLOGY 2003, 2003, : 559 - 564
  • [24] Asymmetric Watermarking Method Based on Subspace Projection
    He, Mi
    Cheng, Lizhi
    PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE FOR YOUNG COMPUTER SCIENTISTS, VOLS 1-5, 2008, : 1446 - 1452
  • [25] A Feature Subset Selection Method Based On High-Dimensional Mutual Information
    Zheng, Yun
    Kwoh, Chee Keong
    ENTROPY, 2011, 13 (04) : 860 - 901
  • [26] SMEM: A Subspace Merging Based Evolutionary Method for High-Dimensional Feature Selection
    Li, Kaixuan
    Jiang, Shibo
    Zhang, Rui
    Qiu, Jianfeng
    Zhang, Lei
    Yang, Lixia
    Cheng, Fan
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024,
  • [27] Interactive feature space extension for multidimensional data projection
    Perez, Daniel
    Zhang, Leishi
    Schaefer, Matthias
    Schreck, Tobias
    Keim, Daniel
    Diaz, Ignacio
    NEUROCOMPUTING, 2015, 150 : 611 - 626
  • [28] A novel method for constructing low-dimensional linear discriminative subspace
    Huo, Hongwen
    Feng, Jing
    Feng, Jufu
    MIPPR 2013: PATTERN RECOGNITION AND COMPUTER VISION, 2013, 8919
  • [29] A subspace identification extension to the phase correlation method
    Hoge, WS
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (02) : 277 - 280
  • [30] Speaker recognition using kernel mutual subspace method
    Ichino, M
    Sakano, H
    Komatsu, N
    2004 8TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1-3, 2004, : 397 - 402