Performance indicators for the statistical evaluation of digital image classifications

G. D'Urso, M. Menenti

    Research output: Contribution to journalArticleAcademicpeer-review

    12 Citations (Scopus)

    Abstract

    A statistical procedure is proposed to evaluate the algorithms for the numerical classification of images. The approach is based on the derivation of performance indicators from measurements of signature separability and thresholding analysis. Although these measurements are not new in image processing techniques, they are used in this study in an original way for the comparison of outputs resulting from different classification criteria. The theoretical description of the method suggested is followed by its practical application to a case-study for mapping crop coefficients in an irrigation district.
    Original languageEnglish
    Pages (from-to)78-90
    JournalISPRS Journal of Photogrammetry and Remote Sensing
    Volume51
    Issue number2
    DOIs
    Publication statusPublished - 1996

    Fingerprint

    image classification
    Image classification
    digital image
    irrigation
    evaluation
    crops
    Irrigation
    image processing
    Crops
    Image processing
    derivation
    signatures
    crop
    output
    coefficients
    indicator
    comparison
    analysis
    method

    Keywords

    • equipment
    • imagery
    • photointerpretation
    • remote sensing

    Cite this

    @article{648156daf653427eb6848f234bd7fd81,
    title = "Performance indicators for the statistical evaluation of digital image classifications",
    abstract = "A statistical procedure is proposed to evaluate the algorithms for the numerical classification of images. The approach is based on the derivation of performance indicators from measurements of signature separability and thresholding analysis. Although these measurements are not new in image processing techniques, they are used in this study in an original way for the comparison of outputs resulting from different classification criteria. The theoretical description of the method suggested is followed by its practical application to a case-study for mapping crop coefficients in an irrigation district.",
    keywords = "uitrusting, afbeelden, fotointerpretatie, remote sensing, equipment, imagery, photointerpretation, remote sensing",
    author = "G. D'Urso and M. Menenti",
    year = "1996",
    doi = "10.1016/0924-2716(95)00004-6",
    language = "English",
    volume = "51",
    pages = "78--90",
    journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
    issn = "0924-2716",
    publisher = "Elsevier",
    number = "2",

    }

    Performance indicators for the statistical evaluation of digital image classifications. / D'Urso, G.; Menenti, M.

    In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 51, No. 2, 1996, p. 78-90.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Performance indicators for the statistical evaluation of digital image classifications

    AU - D'Urso, G.

    AU - Menenti, M.

    PY - 1996

    Y1 - 1996

    N2 - A statistical procedure is proposed to evaluate the algorithms for the numerical classification of images. The approach is based on the derivation of performance indicators from measurements of signature separability and thresholding analysis. Although these measurements are not new in image processing techniques, they are used in this study in an original way for the comparison of outputs resulting from different classification criteria. The theoretical description of the method suggested is followed by its practical application to a case-study for mapping crop coefficients in an irrigation district.

    AB - A statistical procedure is proposed to evaluate the algorithms for the numerical classification of images. The approach is based on the derivation of performance indicators from measurements of signature separability and thresholding analysis. Although these measurements are not new in image processing techniques, they are used in this study in an original way for the comparison of outputs resulting from different classification criteria. The theoretical description of the method suggested is followed by its practical application to a case-study for mapping crop coefficients in an irrigation district.

    KW - uitrusting

    KW - afbeelden

    KW - fotointerpretatie

    KW - remote sensing

    KW - equipment

    KW - imagery

    KW - photointerpretation

    KW - remote sensing

    U2 - 10.1016/0924-2716(95)00004-6

    DO - 10.1016/0924-2716(95)00004-6

    M3 - Article

    VL - 51

    SP - 78

    EP - 90

    JO - ISPRS Journal of Photogrammetry and Remote Sensing

    JF - ISPRS Journal of Photogrammetry and Remote Sensing

    SN - 0924-2716

    IS - 2

    ER -