Hyperspectral Image Classification and Development of Fluorescence Index for Single Corn Kernels Infected with Aspergillus flavus

Abstract

<abstract><title><italic>Abstract. </italic></title> Aflatoxins are toxic secondary metabolites predominantly produced by the fungi Aspergillus flavus and Aspergillus parasiticus. Aflatoxin-contaminated corn is toxic to domestic animals when ingested in feed and is a known carcinogen associated with liver and lung cancer in humans. Consequently, aflatoxin levels in food and feed are regulated by the U.S. Food and Drug Administration (FDA), which allows 20 ppb (parts per billion) limits in food and 100 ppb in feed for interstate commerce. Currently, aflatoxin detection and quantification methods are based on analytical tests, including thin-layer chromatography (TCL) and high-performance liquid chromatography (HPLC). These analytical tests require the destruction of samples and are costly and time consuming. Thus, the ability to detect aflatoxin in a rapid, non-destructive way is crucial to the grain industry, particularly the corn industry. Hyperspectral imaging technology offers a non-invasive approach to screening for food safety inspection and quality control based on spectral signatures. The focus of this study was to classify aflatoxin-contaminated single corn kernels using fluorescence hyperspectral imagery. Field-inoculated corn kernels were used in the study. Contaminated and control kernels under long-wavelength ultraviolet excitation were imaged using a visible near-infrared (VNIR) hyperspectral camera. The imaged kernels were chemically analyzed to provide reference information for image analysis. This article describes a procedure for processing corn kernels located in different images for statistical training and classification. Two classification algorithms (maximum likelihood and binary encoding) were used to classify each corn kernel as “control” or “contaminated” through pixel classification. The binary encoding approach had a slightly better performance, with accuracy equal to 87% or 88% when 20 ppb or 100 ppb, respectively, was used as the classification threshold. In addition, three narrow-band fluorescence indices were developed and tested in this study. It was found that the highest correlation was -0.81 with the normalized difference fluorescence index (NDFI). The two bands used for the NDFI were 437 and 537 nm. The use of key wavelengths for contamination detection would be helpful for developing rapid and non-invasive inspection systems. This study demonstrated the potential of using fluorescence hyperspectral imagery for aflatoxin contamination detection in corn kernels infected with A. flavus.