Skip to main content
ARS Home » Research » Publications at this Location » Publication #152182
Title: CLASSIFICATION OF FUNGAL-DAMAGED SOYBEAN SEEDS USING NEAR-INFRARED SPECTROSCOPY

Author
item WANG, DONGHAI - KS STATE UNIVERSITY
item Dowell, Floyd
item Ram, M
item SCHAPAUGH, W - KS STATE UNIVERSITY

Submitted to: International Journal of Food Properties
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/13/2003
Publication Date: 6/1/2003
Citation: WANG, D., DOWELL, F.E., RAM, M.S., SCHAPAUGH, W.T. CLASSIFICATION OF FUNGAL-DAMAGED SOYBEAN SEEDS USING NEAR-INFRARED SPECTROSCOPY. INTERNATIONAL JOURNAL OF FOOD PROPERTIES. 2003. v. 6(0). p. 1-8.

Interpretive Summary: Soybean quality is reduced if they are infected with fungi. Thus it is important to accurately determine quality before soybeans are marketed or used in food or feed products. The objective of this research was to classify healthy and fungal-damaged soybean seeds, and discriminate among various types of fungal damage using near-infrared spectroscopy. Spectra were obtained from single soybean seeds and models were developed to differentiate healthy and fungal-damaged soybean seeds. Classification accuracies ranged from 84-100% when detecting 5 different types of fungi.

Technical Abstract: Fungal damage caused by pathogens such as Phomopsis, Personospora manshurca Syd (downy mildew), soybean mosaic virus (SMV) and Cercospora kikuchii (C. kikuchii) has a devastating impact on soybean quality and end-use. The objective of this research was to classify healthy and fungal-damaged soybean seeds, and discriminate among various types of fungal damage using NIR spectroscopy. A diode-array NIR spectrometer, which measured reflectance (log (1/R)) from 400-1700 nm, was used to obtain spectra from single soybean seeds. Partial least square (PLS) and neural network models were developed to differentiate healthy and fungal-damaged soybean seeds. The highest classification accuracy was more than 99% when the wavelength region of 490-1690 nm was used under a two-class PLS model. Neural network models yielded higher classification accuracy than the PLS models for five-class classification. The average of correct classifications was 93.5% for the calibration sample set and 94.6% for the validation sample set. The classification accuracies of the validation sample set were 100, 99, 84, 94, and 96% corresponding to healthy seeds, Phomopsis, C.kikuchii, SMV, and downy mildew damaged seeds, respectively.