Detection of Fusarium in single wheat kernels using spectral Imaging

G. Polder, G.W.A.M. van der Heijden, C. Waalwijk, I.T. Young

    Research output: Contribution to journalArticleAcademicpeer-review

    44 Citations (Scopus)

    Abstract

    Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that nearinfrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q2 of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.
    Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that near-infrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q(2) of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.
    Original languageEnglish
    Pages (from-to)655-668
    JournalSeed Science and Technology
    Volume33
    Publication statusPublished - 2005

    Fingerprint

    Fusarium
    Fusarium head blight
    image analysis
    wheat
    wavelengths
    least squares
    seeds
    disease detection
    spectroscopy
    quantitative polymerase chain reaction
    DNA
    methodology

    Keywords

    • fusarium
    • kernels
    • detection
    • spectral analysis
    • imaging spectroscopy
    • near-infrared reflectance
    • least-squares regression
    • machine vision
    • industrial applications
    • neural-network
    • head blight
    • spectroscopy
    • scab
    • corn
    • identification

    Cite this

    Polder, G. ; van der Heijden, G.W.A.M. ; Waalwijk, C. ; Young, I.T. / Detection of Fusarium in single wheat kernels using spectral Imaging. In: Seed Science and Technology. 2005 ; Vol. 33. pp. 655-668.
    @article{eec2131fc0d84e89938aed5b24052494,
    title = "Detection of Fusarium in single wheat kernels using spectral Imaging",
    abstract = "Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that nearinfrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q2 of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that near-infrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q(2) of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.",
    keywords = "fusarium, korrels (granen), detectie, spectraalanalyse, beeldvormende spectroscopie, fusarium, kernels, detection, spectral analysis, imaging spectroscopy, near-infrared reflectance, least-squares regression, machine vision, industrial applications, neural-network, head blight, spectroscopy, scab, corn, identification",
    author = "G. Polder and {van der Heijden}, G.W.A.M. and C. Waalwijk and I.T. Young",
    year = "2005",
    language = "English",
    volume = "33",
    pages = "655--668",
    journal = "Seed Science and Technology",
    issn = "0251-0952",
    publisher = "International Seed Testing Association",

    }

    Detection of Fusarium in single wheat kernels using spectral Imaging. / Polder, G.; van der Heijden, G.W.A.M.; Waalwijk, C.; Young, I.T.

    In: Seed Science and Technology, Vol. 33, 2005, p. 655-668.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Detection of Fusarium in single wheat kernels using spectral Imaging

    AU - Polder, G.

    AU - van der Heijden, G.W.A.M.

    AU - Waalwijk, C.

    AU - Young, I.T.

    PY - 2005

    Y1 - 2005

    N2 - Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that nearinfrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q2 of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that near-infrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q(2) of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.

    AB - Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that nearinfrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q2 of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.Fusarium head blight (FHB) is a harmful fungal disease that occurs in small grains. Non-destructive detection of this disease is traditionally done using spectroscopy or image processing. In this paper the combination of these two in the form of spectral imaging is evaluated. Transmission spectral images are recorded, both in the visible and near-infrared range from FHB infected wheat kernels. These images are analyzed, using light absorption, the relation between two wavelength bands, unsupervised fuzzy c-means clustering and supervised partial least squares regression. The reference method for training and validation is TaqMan real-time PCR. Results show that near-infrared spectral images perform much better than spectral images in the visible range. Kernels with more than 6000 pg Fusarium DNA could clearly be identified. Above 100 pg it was possible to predict the amount of Fusarium with a Q(2) of 0.8. This was both for Partial Least Squares regression (PLS) and a simple wavelength ratio. Also fuzzy c-means clustering shows a relation between amount of Fusarium and spectra.

    KW - fusarium

    KW - korrels (granen)

    KW - detectie

    KW - spectraalanalyse

    KW - beeldvormende spectroscopie

    KW - fusarium

    KW - kernels

    KW - detection

    KW - spectral analysis

    KW - imaging spectroscopy

    KW - near-infrared reflectance

    KW - least-squares regression

    KW - machine vision

    KW - industrial applications

    KW - neural-network

    KW - head blight

    KW - spectroscopy

    KW - scab

    KW - corn

    KW - identification

    M3 - Article

    VL - 33

    SP - 655

    EP - 668

    JO - Seed Science and Technology

    JF - Seed Science and Technology

    SN - 0251-0952

    ER -