Spectral Imaging Research
Secure Food Solutions spectral imaging technology is backed by patent, and the following research conducted over the past decade by scientists at Mississippi State University and USDA Agricultural Research Services:
1. ‘Hyperspectral Bright Greenish-Yellow Fluorescence (BGYF) Imaging of Aflatoxin Contaminated Corn Kernels.’ - The objective of the study was to analyze hyperspectral BGYF response of corn kernels under UVA excitation. The BGYF positive kernels were manually picked out and imaged under a visible near-infrared hyperspectral imaging system under UV radiation with excitation wavelength centered at 365 nm. Initial results exhibited strong emission spectra with peaks centered from 500 nm to 515 nm wavelength range for BGYF positive kernels (Yao, Hruska, Brown & Cleveland, 2006).
2. ‘Differentiation of toxigenic fungi using hyperspectral imagery.’ - The report focused on the feasibility of using spectral image data for fungal species classification. A tabletop hyperspectral imaging system, VNIR-100E, was used for spectral and spatial data acquisition. A total of five fungal species were selected for a two-part experiment: Penicillium chrysogenum, Fusarium moniliforme, Aspergillus parasiticus, Trichoderma viride,and Aspergillus flavus. The objective of the study was to use visible near-infrared hyperspectral imagery to differentiate fungal species. Results indicate that all five fungi are highly separable with classification accuracy of 97.7%. In addition, all five fungi could be classified by using only three narrow bands (bandwidth=2.43nm) centered at 743nm, 458nm, and 541nm (Yao, Hruska, Kincaid, Brown & Cleveland, 2008).
3. ‘Automatic detection of aflatoxin contaminated corn kernels using dual-band imagery.’ – Analyzes a technique that automatically detects aflatoxin contaminated corn kernels by using dual-band imagery. The method exploits the fluorescence emission spectra from corn kernels captured under 365 nm ultra-violet light excitation. This approach could lead to a non-destructive and non-invasive way of quantifying the levels of aflatoxin contamination. The preliminary results demonstrate the potential of this technique for aflatoxin detection (Onyonye, Yao, Hruska, Kincaid, Brown & Cleveland, 2009).
4. ‘Spectral Angle Mapper classification of fluorescence hyperspectral image for aflatoxin contaminated corn’ - The study applied the Spectral Angle Mapper classification technique to classify single corn kernels into contaminated and healthy groups. Fluorescence hyperspectral images were used in the classification. An obvious fluorescence peak shift was observed to be associated with the aflatoxin contaminated corn (Yao, Hruska, Kincaid, Onyonye, Brown & Cleveland, 2010).
5. ‘Correlation and classification of single kernel fluorescence hyperspectral data with aflatoxin concentration in corn kernels inoculated with Aspergillus flavus spores.’ - The objective of this study is to examine the relationship between fluorescence emissions of corn kernels inoculated with Aspergillus flavus and aflatoxin contamination levels within the kernels. A fluorescence peak shift phenomenon was noted among different groups of kernels with different aflatoxin contamination levels. The fluorescence peak shift was found to move more toward the longer wavelength in the blue region for the highly contaminated kernels and toward the shorter wavelengths for the clean kernels. Highly contaminated kernels were also found to have a lower fluorescence peak magnitude compared with the less contaminated kernels (Yao, Hruska, Kincaid, Brown, Cleveland & Bhatnagar, 2010).
6. ‘Single Aflatoxin Contaminated Corn Kernel Analysis with Fluorescence Hyperspectral Image.’ - The focus of this paper is to classify aflatoxin contaminated single corn kernels using fluorescence hyperspectral imagery. Two classification algorithms, Maximum Likelihood and Binary Encoding, were used to classify each corn kernel into "control" or "contaminated" through pixel classification. The Binary Encoding approach had a slightly better performance with accuracy equals to 87% or 88% when 20 ppb or 100 ppb was used as classification threshold, respectively (Yao, Hruska, Kincaid, Onyonye, Brown & Cleveland, 2010).
7. ‘Selective principal component regression analysis of fluorescence hyperspectral image to assess aflatoxin contamination in corn.’ - Selective principal component regression analysis (SPCR) uses a subset of the original image bands for principal component transformation and regression. For optimal band selection before the transformation, this paper used genetic algorithms (GA). This algorithm was used for analyzing fluorescence hyperspectral images of aflatoxin contaminated corn kernels. The results demonstrated that SPCR could be used as a combined dimension reduction and data analysis tool for high dimensionality data processing (Yao, Hruska, Kincaid, Onyonye, Brown & Cleveland, 2010).
8. ‘SVM-based feature extraction and classification of aflatoxin contaminated corn using fluorescence hyperspectral data.’ - Support Vector Machine (SVM) was used in the Genetic Algorithms (GA) process to select and classify a subset of hyperspectral image bands. The method was applied to fluorescence hyperspectral data for the detection of aflatoxin contamination in Aspergillus flavus infected single corn kernels. In the band selection process, the training sample classification accuracy was used as fitness function. Two aflatoxin thresholds, 20 ppb and 100 ppb, were used to divide the single corn kernels into clean and contaminated samples. The validation accuracy was 87.7% for the 20 ppb threshold and 90.5% for the 100 ppb threshold (Yao, Hruska, Kincaid, Brown, Bhatnagar & Cleveland, 2012).
9. ‘Utilizing Fluorescence Hyperspectral Imaging to Differentiate Corn Inoculated with Toxigenic and Atoxigenic Fungal Strains.’ (Yao, Haibo, et al. 2012) - The objective of the current study was to assess, with the use of a hyperspectral sensor, the difference in fluorescence emission between corn kernels inoculated with toxigenic and atoxigenic inoculums of A. flavus. Both sides of the kernel, germplasm and endosperm, were imaged separately using a fluorescence hyperspectral imaging system. The best result was achieved with the germplasm side of the corn kernels (Yao, Hruska, Kincaid, Brown, Bhatnagar & Cleveland, 2012).
10. ‘Detecting maize inoculated with toxigenic and atoxigenic fungal strains with fluorescence hyperspectral imagery.’ - Used fluorescence hyperspectral imagery to study Aspergillus flavus inoculated maize. Toxigenic and atoxigenic strains of fungi were compared in the study. Two side of corn – germ and endosperm – were evaluated. The actual aflatoxin of each maize kernel was chemically measured. The best results for separation were achieved with the germ side of the maize kernels. The study showed potential of imaging for aflatoxin contamination detection in maize (Yao, Hruska, Kincaid, Brown, Bhatnagar & Cleveland, 2013).