Abstract
Background Mildew damage is a quality defect that has an adverse effect on the quality of flour. Aims The objective of this study was to develop a rapid and consistent imaging method to quantify the extent of mildew damage in wheat samples. Materials and methods A hyperspectral imaging system with a wavelength range of 400–1000 nm was used to detect and quantify mildew in 65 Canada Eastern Soft Red Winter (CESRW) wheat samples. Partial least square (PLS) regression calibrations were developed to predict mildew levels based on the spectral characteristics of the bulk samples. Results and discussion Predictions from a model with 4 PLS factors based on image standard deviation spectra matched well with the visual assessment of the samples with an R2 approaching 0.87 and an RMSE of 0.76 on the validation set. Accuracy of the PLS classification for 9 mildew levels was 90.6% (±1 level) and 84.4% for 3 inspector grades. Conclusion This study confirms that potential use of hyperspectral imaging for mildew detection in commercial operations is possible. Shahin MA, Hatcher, DW, Symons JS (2010). Assessment of mildew levels in wheat samples based on spectral characteristics of bulk grains. Quality Assurance and Safety of Crops & Foods, 2, 133–140.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
