Journal of Spectral Imaging,   Volume 7   Article ID a2   (2018)

Peer reviewed paper

Near infrared hyperspectral imaging of blends of conventional and waxy hard wheats

Stephen R. Delwiche,a,* Jianwei Qin,b Robert A. Graybosch,c Steven R. Rauschd and Moon S. Kime
aUSDA- ARS, Beltsville Agricultural Research Center, Food Quality Laboratory, Building 303, BARC-East, Beltsville, Maryland, 20705-2350, USA. E-mail: [email protected]
bUSDA-ARS, Beltsville Agricultural Research Center, Environmental and Microbial Food Safety Laboratory, Building 303, BARC-East, Beltsville, Maryland, 20705-2350, USA
cUSDA-ARS, Department of Agronomy, University of Nebraska, Lincoln, Nebraska, 68583, USA
dUSDA-ARS, Beltsville Agricultural Research Center, Food Quality Laboratory, Building 303, BARC-East, Beltsville, Maryland, 20705-2350, USA
eUSDA-ARS, Beltsville Agricultural Research Center, Environmental and Microbial Food Safety Laboratory, Building 303, BARC-East, Beltsville, Maryland, 20705-2350, USA

Recent development of hard winter waxy (amylose-free) wheat adapted to the North American climate has prompted the quest to find a rapid method that will determine mixture levels of conventional wheat in lots of identity preserved waxy wheat. Previous work documented the use of conventional near infrared (NIR) reflectance spectroscopy to determine the mixture level of conventional wheat in waxy wheat, with an examined range, through binary sample mixture preparation, of 0–100% (weight conventional / weight total). The current study examines the ability of NIR hyperspectral imaging of intact kernels to determine mixture levels. Twenty-nine mixtures (0, 1, 2, 3, 4, 5, 10, 15, …, 95, 96, 97, 98, 99, 100%) were formed from known genotypes of waxy and conventional wheat. Two-class partial least squares discriminant analysis (PLSDA) and statistical pattern recognition classifier models were developed for identifying each kernel in the images as conventional or waxy. Along with these approaches, conventional PLS1 regression modelling was performed on means of kernel spectra within each mixture test sample. Results indicated close agreement between all three approaches, with standard errors of prediction for the better preprocess transformations (PLSDA models) or better classifiers (pattern recognition models) of approximately 9 percentage units. Although such error rates were slightly greater than ones previously published using non-imaging NIR analysis of bulk whole kernel wheat and wheat meal, the HSI technique offers an advantage of its potential use in sorting operations.

Keywords: wheat, hyperspectral imaging, mixture, waxy, amylose

Metrics

Downloads:

176

Full-Text HTML Views:

40

Abstract Views:

158

Altmetrics: