Title: Detection of Corn Kernels Infected by Fungi Authors
Submitted to: Transactions of the ASAE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: June 1, 2006
Publication Date: September 1, 2006
Repository URL: http://naldc.nal.usda.gov/download/341/PDF
Citation: Pearson, T.C., Wicklow, D.T. 2006. Properties of corn kernels infected by fungi. Transactions of the ASABE. 49(4):1235-1245. Interpretive Summary: Near infrared spectra, x-ray images, color images, near infrared images, and physical properties of single corn kernels were studied to determine if combinations of these measurements could distinguish fungal infected kernels from non-infested kernels. Kernels used in this study were inoculated in the field with eight different fungi: Acremonium zeae, Aspergillus flavus, Aspergillus niger, Diplodia maydis, Fusarium graminearum, Fusarium verticillioides, Penicillium spp. Trichoderma viride. Results indicate that kernels infected with Acremonium zeae and Penicillium were difficult to distinguish from non-infested kernels while all of the other severely infected kernels could be distinguished with greater than 91% accuracy. A neural network was also trained to identify infecting mold species with good accuracy, based on the near infrared spectra. These results indicate that this technology can potentially be used to separate fungal infected corn using high speed sorter; and, automatically and rapidly identify the fungal species of infested corn kernels. This will be of assistance to breeders developing fungal resistant hybrids as well as mycologists studying fungal infected corn.
Technical Abstract: Single kernel reflectance spectra (550 - 1700 nm), visible color reflectance images, x-ray images, multi-spectral transmittance images, and physical properties (mass, length, width, thickness, cross-sectional area) were analyzed to determine if they could be used to detect fungal-infected corn kernels. Kernels were collected from corn ears inoculated with one of several different common fungi several weeks before harvest, then collected at harvest time. It was found that two NIR reflectance spectral bands centered at 715 nm and 965 nm can correctly identify 98.1% of asymptomatic kernels and 96.6% of kernels showing extensive discoloration and infected with Aspergillus flavus, Aspergillus niger, Diplodia maydis, Fusarium graminearum, Fusarium verticillioides, or Trichoderma viride. These two spectral bands are easily implemented on high speed sorting machines for removal of fungal-damaged grain. Histogram features from three transmittance images (blue and red components of color images and another at 960 nm) can distinguish 91.9% of infected kernels with extensive discoloration from 96.2% of asymptomatic kernels. Similar classification accuracies were achieved using x-ray images and physical properties (kernel thickness, weight, length). A neural network was trained to identify infecting fungal species on single kernels using principle components of the reflectance spectra as input features.