Classification of Sound and Stained Wheat Grains Using Visible and near Infrared Hyperspectral Image Analysis

Near infrared hyperspectral image analysis has been used to classify individual wheat grains representing 24 different Australian varieties as sound or as being discoloured by one of the commercially important blackpoint, field fungi or pink stains. The study used a training set of 188 grains and a test set of 665 grains. The spectra were smoothed and then standardised by dividing each spectrum by its mean, so that the analysis was based solely on spectral shape. Penalised discriminant analysis was first used for pixel classification and then a simple rule for grain classification was developed. Overall classification accuracies of 95% were achieved over the 420–2500 nm wavelength range, as well as reduced ranges of 420–1000 nm and 420–700 nm.

[1]  Yung-Chiung Chang,et al.  Development of a Near-Infrared Imaging System for Determination of Rice Moisture , 2006 .

[2]  V. Bellon-Maurel,et al.  Determining Vitreousness of Durum Wheat Kernels Using near Infrared Hyperspectral Imaging , 2006 .

[3]  Brian Osborne,et al.  Application of near Infrared Reflectance Spectroscopy to a Durum Wheat Breeding Programme , 2006 .

[4]  B. A. Weinstock,et al.  Prediction of Oil and Oleic Acid Concentrations in Individual Corn (Zea Mays L.) Kernels Using Near-Infrared Reflectance Hyperspectral Imaging and Multivariate Analysis , 2006, Applied spectroscopy.

[5]  Colin Victor. Greensill,et al.  Sugar “Imaging” of Fruit Using a Low Cost Charge-Coupled Device Camera , 2005 .

[6]  Yankun Peng,et al.  Assessing Peach Firmness by Multi-Spectral Scattering , 2005 .

[7]  Moon S. Kim,et al.  Development of a Simple Algorithm for the Detection of Chilling Injury in Cucumbers from Visible/Near-Infrared Hyperspectral Imaging , 2005, Applied spectroscopy.

[8]  Stephen R. Delwiche,et al.  Detection of Scab-Damaged Hard Red Spring Wheat Kernels by Near-Infrared Reflectance , 2004 .

[9]  Junhong Liu,et al.  Single-Kernel Maize Analysis by Near-Infrared Hyperspectral Imaging , 2004 .

[10]  A. Peirs,et al.  Starch Index Determination of Apple Fruit by Means of a Hyperspectral near Infrared Reflectance Imaging System , 2003 .

[11]  W. R. Windham,et al.  A Hyperspectral Imaging System for Identification of Faecal and Ingesta Contamination on Poultry Carcasses , 2003 .

[12]  S. R. Delwiche,et al.  CLASSIFICATION OF SCAB– AND OTHER MOLD–DAMAGED WHEAT KERNELS BY NEAR–INFRARED REFLECTANCE SPECTROSCOPY , 2003 .

[13]  Moon S. Kim,et al.  Hyperspectral imaging for detection of scab in wheat , 2000, SPIE Optics East.

[14]  John Chambers,et al.  Detection of Grain Weevils inside Single Wheat Kernels by a Very near Infrared Two-Wavelength Model , 1999 .

[15]  John Chambers,et al.  Detection of Insects inside Wheat Kernels by NIR Imaging , 1998 .

[16]  P. M. Williamson.  Black point of wheat : in vitro production of symptoms, enzymes involved, and association with Alternaria alternata , 1997 .

[17]  R. Tibshirani,et al.  Penalized Discriminant Analysis , 1995 .

[18]  D. Bertrand,et al.  Identification of chemical constituents by multivariate near-infrared spectral imaging , 1992 .

[19]  G. Rabatel,et al.  Automatic sorting of fruit: sensors for the future , 1992 .