Classification of Fungal-Damaged Soybean Seeds Using Near-Infrared Spectroscopy

Abstract Fungal damage has a devastating impact on soybean quality and end-use. The current visual method for identifying damaged soybean seeds is based on discoloration and is subjective. 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 (NIR) spectroscopy. A diode-array NIR spectrometer, which measured reflectance [log(1/R)] from 400 to 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 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. Classification accuracies of the validation sample set were 100, 99, 84, 94, and 96% corresponding to healthy seeds, Phomopsis, Cercospora kikuchii, soybean mosaic virus (SMV), and downy mildew damaged seeds, respectively. #Contribution No. 03-163-J from the Kansas Agricultural Experiment Station. Mention of a trademark or proprietary product does not constitute a guarantee or warranty of the product by the U.S. Department of Agriculture and does not imply its approval to the exclusion of other products that also may be suitable.

[1]  Franklin E. Barton,et al.  Preliminary study on the analysis of forages with a filter-type near-infrared reflectance spectrometer , 1979 .

[2]  David R. Erickson,et al.  Handbook of Soy Oil Processing and Utilization , 1980 .

[3]  J. B. Sinclair,et al.  Physical Properties of Soybean Seeds Damaged by Fungi and a Virus , 1989 .

[4]  J. Sinclair,et al.  Effects of Cercospora kikuchii on soybean seed germination and quality , 1989 .

[5]  J. B. Sinclair,et al.  Compendium Of Soybean Diseases , 1989 .

[6]  Marvin R Paulsen,et al.  Using machine vision to inspect oilseeds. , 1990 .

[7]  L. Bochereau,et al.  A method for prediction by combining data analysis and neural networks: Application to prediction of apple quality using near infra-red spectraag , 1992 .

[8]  J. Sinclair.  Discoloration of Soybean Seeds- An Indicator of Quality , 1992 .

[9]  T. Hymowitz,et al.  Selective degradation of proteins by Cercospora kikuchii and Phomopsis longicolla in soybean seed coats and cotyledons , 1992 .

[10]  W. W. Casady,et al.  A Trainable Algorithm for Inspection of Soybean Seed Quality , 1992 .

[11]  J. Shenk,et al.  Application of NIR Spectroscopy to Agricultural Products , 1992 .

[12]  J. Sinclair.  Phomopsis seed decay of soybeans : a prototype for studying seed disease , 1993 .

[13]  B. Doupnik.  SOYBEAN PRODUCTION AND DISEASE LOSS ESTIMATES FOR NORTH CENTRAL UNITED STATES FROM 1989 TO 1991 , 1993 .

[14]  Floyd E. Dowell.  Neural network parameter effects on object classification and wavelength selection , 1994 .

[15]  Richard F. Wilson,et al.  Dealing with the problems of fungal damage in soybean and other oilseeds , 1995 .

[16]  G. Fenner,et al.  Effect of fungal damage on seed composition and quality of soybeans , 1995 .

[17]  J. B. Sinclair,et al.  Reevaluation of grading standards and discounts for fungus-damaged soybean seeds , 1995 .

[18]  J. F. Reid,et al.  Color Classifier for Symptomatic Soybean Seeds Using Image Processing. , 1999, Plant disease.

[19]  Floyd E. Dowell,et al.  SINGLEWHEAT KERNEL COLOR CLASSIFICATION USING NEURAL NETWORKS , 1999 .

[20]  Floyd E. Dowell,et al.  CLASSIFICATION OF DAMAGED SOYBEAN SEEDS USING NEAR–INFRARED SPECTROSCOPY , 2002 .