Identification of wheat classes at different moisture levels using near-infrared hyperspectral images of bulk samples

Abstract

Wheat classes at different moisture levels need to be identified to accurately segregate, properly dry, and safely store before processing. This paper introduces a new method using a near infrared (NIR) hyperspectral imaging system (960-1,700 nm) to identify five western Canadian wheat classes (Canada Western Red Spring (CWRS), Canada Western Extra Strong (CWES), Canada Western Red Winter (CWRW), Canada Western Soft White Spring (CWSWS), and Canada Western Hard White Spring (CWHWS)) and moisture levels, independent of each other. The objectives of this research also included identification of each wheat class at specific moisture levels of 12, 14, 16, 18, and 20%. Bulk samples of wheat were scanned in the 960-1,700 nm wavelength region at 10 nm intervals using an Indium Gallium Arsenide (InGaAs) NIR camera. Spectral feature data sets were developed by calculating relative reflectance intensities of the scanned images. Principal components analysis was used to generate scores images and loadings plots. The NIR wavelengths in the region of 1,260-1,360 nm were important based on the loadings plot of first principal component. In statistical classification, the linear and quadratic discriminant analyses were used to classify wheat classes giving accuracies of 61-97 and 82-99%, respectively, independent of moisture contents. It was also found that the linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) could classify moisture contents with classification accuracies of 89-91 and 91-99%, respectively, independent of wheat classes. Once wheat classes were identified, classification accuracies of 90-100 and 72-99% were observed using LDA and QDA, respectively, when identifying specific moisture levels. Spectral features at key wavelengths of 1,060, 1,090, 1,340, and 1,450 nm were ranked at top in classifying wheat classes with different moisture contents. This work shows that hyperspectral imaging techniques can be used for rapidly identifying the wheat classes even at varying moisture levels.

On the value of the Kullback–Leibler divergence for cost-effective spectral imaging of plants by optimal selection of wavebands

“…2, the difference between durum and common wheat is difficult to perceive from the contrast in an RGB image. This classification task has, therefore, also been addressed in the literature with imaging systems including hyperspectral imaging and thermal imaging [30][31][32].…”

Chemometrics in Food Technology

“…While Mahesh et al (2011) used near-infrared hyperspectral images (wavelength range: 960-1700 nm), applied to a bulk samples, to classify the moisture levels (12, 14, 16, 18, and 20%) on the wheat. Principal components analysis (PCA) was used to identify the region (1260-1360 nm) with more information.…”

Principal Component Analysis in the Development of Optical and Imaging Spectroscopic Inspections for Agricultural / Food Safety and Quality

“…A NIR hyperspectral imaging system (960-1700 nm) has been explored to identify five western Canadian wheat classes at varying moisture levels (Mahesh et al, 2011). Besides the generation of scores images and loadings plots from PCA, the linear and quadratic discriminant analyses were used to classify wheat classes giving accuracies of 61-97 and 82-99%, respectively, independent of moisture contents.…”