Classification of Scab– and Other Mold–damaged Wheat Kernels by Near–infrared Reflectance Spectroscopy

Abstract

ABSTRACT. Scab (Fusarium head blight) is a disease that causes wheat kernels to be shriveled, underweight, and difficult to mill. Scab is also a health concern because of the possible concomitant production of the mycotoxin deoxynivalenol. Current official inspection procedures entail manual human inspection. A study was undertaken to explore the possibility of detecting scab-damaged wheat kernels by a near-infrared (NIR) diode array spectrometer. Wheat kernels from three categories (sound, scab-damaged, and mold-damaged)

Hyperspectral and Chlorophyll Fluorescence Imaging for Early Detection of Plant Diseases, with Special Reference to Fusarium spec. Infections on Wheat

“…[61] found a significant correlation between the colour components hue, saturation and intensity (HSI) of RGB images and the thousand-seed-weight, which decreased with infection. From NIR spectra (940 to 1700 nm) and applying a classification, which regards grain mass and the differences in logarithmic reciprocal spectral values at 1182 and 1242 nm, Fusarium damaged wheat grains could be detected by hyperspectral imaging with an accuracy of up to 95% under practical conditions [2]. [59,62] used absorption spectra in the NIR range to determine the Deoxynivalenol (DON) content in Fusarium infected kernels.…”

“…Highly contaminated lots of grain are evidentially harmful and dangerous to humans and livestock. Fusarium generates mycotoxins such as deoxinivalenol (DON), zearalenone and fumonisins to different degrees [2][3][4], which can cause vomiting, mass loss, kidney failure, miscarriage, false pregnancy and cancer [5][6][7][8][9].…”

Optical characterization of free-falling mold-damaged wheat kernels

“…For the purpose of comparing the classification accuracy of the free-falling apparatus with expectations (from previous studies) of accuracies that could be achieved under controlled laboratory, kernel-at-rest conditions, the kernels of each sample were also scanned by a 512-element silicon photodiode array, whereupon readings were interpolated to a uniform increment of 1 nm at whole wavelengths between 380 and 879 nm, as described in Delwiche 13 . A 250-ms integration time, with 10 successive scans per spectrum, was used for each kernel.…”

“…In the second category, kernel morphology and color characteristics were the primary features used to distinguish damaged from healthy kernels 10,11 , with the Fusarium damage characterized by kernels having a white or pinkish color and being shriveled 12 . In the author's own studies [13][14][15] , which involved visible and NIR spectroscopy on individual kernels, identification of Fusarium-damaged kernels of hard red winter wheat could be achieved at an accuracy of 95 to 97 percent with as few as two wavelengths. However, these studies were conducted under controlled laboratory conditions, in which each kernel was scanned at rest while placed in a machined trough on a black plate.…”

Detection of Fecal/Ingesta Contaminants on Poultry Processing Equipment Surfaces by Visible and Near-Infrared Reflectance Spectroscopy

“…One key factor in successful applications is the use of a few essential spectral bands, which should not only reflect the chemical / physical information in the samples, but also maintain successive discrimination and T classification efficiency. These essential bands can be determined through a variety of analytical strategies, such as analyzing spectral difference (Liu et al, 2003;Liu et al, 2005), performing principal component analysis (Windham et al, 2003b), and stepwise linear regression (Williams and Norris, 2001;Delwiche 2003).…”