Fusion-based age-group classification method using multiple two-dimensional feature extraction algorithms

Kazuya Ueki, Tetsunori Kobayashi

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    An age-group classification method based on a fusion of different classifiers with different two-dimensional feature extraction algorithms is proposed. Theoretically, an integration of multiple classifiers can provide better performance compared to a single classifier. In this paper, we extract effective features from one sample image using different dimensional reduction methods, construct multiple classifiers in each subspace, and combine them to reduce age-group classification errors. As for the dimensional reduction methods, two-dimensional PCA (2DPCA) and twodimensional LDA (2DLDA) are used. These algorithms are antisymmetric in the treatment of the rows and the columns of the images. We prepared the row-based and column-based algorithms to make two different classifiers with different error tendencies. By combining these classifiers with different errors, the performance can be improved. Experimental results show that our fusion-based age-group classification method achieves better performance than existing two-dimensional algorithms alone.

    Original languageEnglish
    Pages (from-to)923-934
    Number of pages12
    JournalIEICE Transactions on Information and Systems
    VolumeE90-D
    Issue number6
    DOIs
    Publication statusPublished - 2007 Jun

    Fingerprint

    Feature extraction
    Classifiers
    Fusion reactions

    Keywords

    • 2DLDA
    • 2DPCA
    • Age-group classification
    • Classification combination
    • Face recognition pattern recognition
    • Max rule
    • Min rule
    • Min-max normalization
    • Produc rule
    • Sum rule
    • Z-score

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Software
    • Artificial Intelligence
    • Hardware and Architecture
    • Computer Vision and Pattern Recognition

    Cite this

    @article{69217e0a0fb54eeaa8e40e2ef546e5ff,
    title = "Fusion-based age-group classification method using multiple two-dimensional feature extraction algorithms",
    abstract = "An age-group classification method based on a fusion of different classifiers with different two-dimensional feature extraction algorithms is proposed. Theoretically, an integration of multiple classifiers can provide better performance compared to a single classifier. In this paper, we extract effective features from one sample image using different dimensional reduction methods, construct multiple classifiers in each subspace, and combine them to reduce age-group classification errors. As for the dimensional reduction methods, two-dimensional PCA (2DPCA) and twodimensional LDA (2DLDA) are used. These algorithms are antisymmetric in the treatment of the rows and the columns of the images. We prepared the row-based and column-based algorithms to make two different classifiers with different error tendencies. By combining these classifiers with different errors, the performance can be improved. Experimental results show that our fusion-based age-group classification method achieves better performance than existing two-dimensional algorithms alone.",
    keywords = "2DLDA, 2DPCA, Age-group classification, Classification combination, Face recognition pattern recognition, Max rule, Min rule, Min-max normalization, Produc rule, Sum rule, Z-score",
    author = "Kazuya Ueki and Tetsunori Kobayashi",
    year = "2007",
    month = "6",
    doi = "10.1093/ietisy/e90-d.6.923",
    language = "English",
    volume = "E90-D",
    pages = "923--934",
    journal = "IEICE Transactions on Information and Systems",
    issn = "0916-8532",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "6",

    }

    TY - JOUR

    T1 - Fusion-based age-group classification method using multiple two-dimensional feature extraction algorithms

    AU - Ueki, Kazuya

    AU - Kobayashi, Tetsunori

    PY - 2007/6

    Y1 - 2007/6

    N2 - An age-group classification method based on a fusion of different classifiers with different two-dimensional feature extraction algorithms is proposed. Theoretically, an integration of multiple classifiers can provide better performance compared to a single classifier. In this paper, we extract effective features from one sample image using different dimensional reduction methods, construct multiple classifiers in each subspace, and combine them to reduce age-group classification errors. As for the dimensional reduction methods, two-dimensional PCA (2DPCA) and twodimensional LDA (2DLDA) are used. These algorithms are antisymmetric in the treatment of the rows and the columns of the images. We prepared the row-based and column-based algorithms to make two different classifiers with different error tendencies. By combining these classifiers with different errors, the performance can be improved. Experimental results show that our fusion-based age-group classification method achieves better performance than existing two-dimensional algorithms alone.

    AB - An age-group classification method based on a fusion of different classifiers with different two-dimensional feature extraction algorithms is proposed. Theoretically, an integration of multiple classifiers can provide better performance compared to a single classifier. In this paper, we extract effective features from one sample image using different dimensional reduction methods, construct multiple classifiers in each subspace, and combine them to reduce age-group classification errors. As for the dimensional reduction methods, two-dimensional PCA (2DPCA) and twodimensional LDA (2DLDA) are used. These algorithms are antisymmetric in the treatment of the rows and the columns of the images. We prepared the row-based and column-based algorithms to make two different classifiers with different error tendencies. By combining these classifiers with different errors, the performance can be improved. Experimental results show that our fusion-based age-group classification method achieves better performance than existing two-dimensional algorithms alone.

    KW - 2DLDA

    KW - 2DPCA

    KW - Age-group classification

    KW - Classification combination

    KW - Face recognition pattern recognition

    KW - Max rule

    KW - Min rule

    KW - Min-max normalization

    KW - Produc rule

    KW - Sum rule

    KW - Z-score

    UR - http://www.scopus.com/inward/record.url?scp=50249152185&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=50249152185&partnerID=8YFLogxK

    U2 - 10.1093/ietisy/e90-d.6.923

    DO - 10.1093/ietisy/e90-d.6.923

    M3 - Article

    VL - E90-D

    SP - 923

    EP - 934

    JO - IEICE Transactions on Information and Systems

    JF - IEICE Transactions on Information and Systems

    SN - 0916-8532

    IS - 6

    ER -