Separation of Touching Grain Kernels in an Image by Ellipse Fitting Algorithm

An algorithm was developed based on morphological features to classify individual kernels of CanadaWestern Red Spring (CWRS) wheat, Canada Western Amber Durum (CWAD) wheat, barley, oats, and rye. Twenty-threemorphological features were used for the discriminant analysis. Grains from 15 growing regions (300 kernels pergrowing region) across Western Canada were used as the training data set and from another five growing regions as thetest data set. The classification accuracies of individual kernels using the 10 most significant features in the morphologymodel were 98.9, 93.7, 96.8, 99.9, and 81.6%, respectively for CWRS wheat, CWAD wheat, barley, oats, and rye whentested on an independent data set (i.e., the test data set where the total number of kernels used was 10 500; for CWRSwheat, 300 kernels each were selected for three grades). When the model was tested on the training data set (total numberof kernels used was 31 500), the classification accuracies of CWRS wheat, CWAD wheat, barley, oats, and rye were 98.9,91.6, 97.9, 100.0, and 91.6%, respectively.

Cereal Grain and Dockage Identification using Machine Vision

Phenolic acid composition of sprouted wheats by ultra-performance liquid chromatography (UPLC) and their antioxidant activities

In the quest for an inexpensive machine-vision system (MVS) to identify and classify cereal grains, a flatbed scanner was used and its performance was evaluated. Images of bulk samples and individual grain kernels of barley, Canada Western Amber Durum (CWAD) wheat, Canada Western Red Spring (CWRS) wheat, oats, and rye were acquired and classification was done using a four layer back-propagation neural network. Classification accuracies in excess of 99% were obtained using a set of 10 color and textural features for bulk samples. For single kernel images, a set of at least 30 features (morphological, color, and textural) was required to achieve similar classification accuracies. Classification accuracies for single kernel samples varied between 96 and 99%.

AAC Craven (BW1127) is a hollow-stemmed, awned, and high yielding Canada Western Red Spring (CWRS) wheat cultivar suited to the growing conditions of western Canada. AAC Craven yielded 4916 kg ha −1 (8% higher than AAC Brandon and 17% higher yielding than Carberry) in the Central Bread Wheat Cooperative registration trials (2021–2023). AAC Craven matured 89 days after seeding and reached a height of 74 cm, similar to AAC Brandon. The lodging score of AAC Craven was 1.9 (1–9 scale), which is better than AAC Brandon (2.3). The test weight of AAC Craven was 80 kg hL −1 and 1000-kernel weight was 33 mg kernel −1 . The grain protein content of AAC Craven was 14.2%, 0.8 units lower than AAC Brandon. AAC Craven expressed moderately resistant reaction to Fusarium head blight (FHB; Fusarium spp.). AAC Craven was resistant to prevalent races of leaf rust ( Puccinia triticina Erikss.), stem rust ( Puccinia graminis Pers. f. sp. tritici Eriks. & E. Henn), and stripe rust ( Puccinia striiformis Westend) in western Canada. AAC Craven had intermediate to moderately susceptible reaction to common bunt ( Tilletia caries (DC) Tul. & C. Tul. and T. laevis J.G. Kühn). AAC Craven was resistant to orange wheat blossom midge ( Sitodiplosis mosellana Géhin). AAC Craven was deemed to fit the CWRS wheat class by the Canadian Grain Commission and registered with Canadian Food Inspection Agency.

Detection of sprout damage in Canada Western Red Spring wheat with multiple wavebands using visible/near-infrared hyperspectral imaging

Granular urea fertilizer applied at planting is prone to nitrogen (N) losses in certain environments. Enhanced efficiency fertilizers (EEFs) are developed to mitigate losses and optimize plant uptake. To determine the benefits of EEFs in grain yield and quality enhancement in Canada Western Red Spring (CWRS) wheat, an experiment was conducted from 2019 to 2022 at eight sites in Alberta and Saskatchewan, Canada. The effects of five N sources [urea; urea + urease inhibitor, N-( n-butyl)thiophosphoric triamide (NBPT); urea + nitrification inhibitor, nitrapyrin; urea + dual-inhibitor, NBPT + dicyandiamide; and polymer-coated urea, ESN® (Environmentally Smart Nitrogen®)] and four N rates (60, 120, 180, and 240 kg N ha−1) on CWRS wheat production were examined. Results indicated that N source affected grain yield in Dark Brown Chernozem soils but not in Black Chernozem or Dark Grey Luvisol soils. In Dark Brown Chernozem soils, a dual inhibitor increased grain yield by 3.1% and 3.9% relative to urea and polymer-coated urea, respectively, while all other EEFs attained similar results. The use of a dual inhibitor EEF led to greater net returns compared to urea and polymer-coated urea in the Dark Brown Chernozem soils. Grain protein concentration increased linearly with increasing N rate from 60 to 240 kg N ha−1. Generally, a rate of 120 kg N ha−1 was optimal for CWRS wheat grown in Canadian prairie conditions when coupled with EEFs, particularly a dual inhibitor, and grain yield and protein were often responsive.

Scientists and the agricultural community require methods of quantifying C sequestration in soils. This is important in assessing the impact of crop management practices on emission of greenhouse gases and for “C trading”. Using simulation models may be a more effective method of quantification as compared with in situ measurements. A 17-yr crop rotation experiment being conducted on a medium-textured Orthic Brown Chernozem at Swift Current, Saskatchewan, in which soil organic C (SOC) was being monitored periodically, was used to assess the effect on C sequestration of cropping frequency, wheat class, legume green manure (LGM), flexible cropping based on available water, and regrassing of crop land. Prior to the study, the experimental site had been cropped to fallow-wheat (F-W) for the previous 60 yr. Crop management in this experiment involved minimum tillage, snow trapping, and N + P fertilization based on soil tests. Three models [Century, the Introductory C Balance model (ICBM), and the Campbell model] were tested for their effectiveness in simulating SOC trends. Because growing season precipitation was average to above average, yields, and thus C inputs from residue, were also above average, and consequently SOC increased in most systems for the first 10 yr before reaching a new steady state. SOC gains (kg ha-1 yr-1) in the 0- to 15-cm depth in 17 yr were directly proportional to cropping frequency (F-W-W = 135, F-W-W-W = 332, and Cont W = 441); LGM-W-W gained SOC at a much higher rate than F-W-W (329 vs. 135 kg ha-1 yr-1 ); Canada Western Red Spring (CWRS) wheat (Triticum aestivum L.), although it yielded 26% less than Canada Prairie Spring (CPS) wheat, gained SOC at a higher rate than CPS wheat (135 vs. 0 kg ha-1 yr-1). Further, 2 yr of conventionally-tilled fallow in 17 yr (flexible system) markedly suppressed SOC gain by 46% compared with Cont W (441 vs. 236 kg ha-1 yr-1). There was a 282 kg ha-1 yr-1 gain in SOC under crested wheatgrass (Agropyron cristatum L.) (CWG) but most of this gain occurred in the last 7 yr. Though having their inherent weaknesses, the ICBM and Campbell models performed equally well in simulating SOC trends (r2 = 0.55**), but Century was less effective (r2 = 0.21*), in part because of its limited ability to simulate yields. Because C input, and thus yield, is one of the main factors influencing SOC gains, and since measured yields are used in the ICBM and Campbell models, while simulated yields are used by Century, the ICBM and Campbell models have an advantage over the Century model in this comparison. Efficiencies of conversion of input C to SOC increased with cropping frequency, and were higher for LGM-W-W than for F-W-W, and for systems with CWRS wheat rather than CPS wheat. Efficiency of conversion was 8% for F-W-W, 15% for LGM-W-W and 21% for Cont W. Key words: ICBM model, Century model, Campbell model, C sequestration, legume green manure, regrassing

The objectives of this work were to investigate the presence of a variety of mycotoxins in Canadian wheat and durum and to characterize the relationship between concentrations of the Fusarium-produced deoxynivalenol (DON) and the presence of visible Fusarium damage. There is a lack of reported mycotoxin surveillance data for Canadian wheat and durum; this work addresses this information gap. Wheat and durum harvest samples from the 2010, 2011 and 2013–2016 growing seasons were analysed for mycotoxins produced by a variety of fungal species, including Fusarium graminearum and Alternaria alternata. The Alternaria-produced tentoxin was observed the most frequently; it was present in 90% of the samples analysed at concentrations up to 0.063 mg kg−1. Fusarium-produced DON and enniatins B and B1 were present in over 70% of samples analysed. The plant transformation product DON-3-glucoside was quantified in up to 30% of samples. There was variability in the presence of the various mycotoxins amongst years. In particular, for DON, the variability reflected the level of visible Fusarium damage noted in grain samples. The geographic source of samples also influenced DON concentrations, which decreased from eastern to western growing regions on the Prairies. Concentrations of DON varied from 0.066 to 0.895 mg kg−1 in south central Manitoba and <0.03 to 0.053 mg kg−1 in central Alberta. DON concentrations were significantly correlated (P < 0.001) with visible Fusarium damage in Canada Western Red Spring wheat for all four years investigated. For Canada Eastern Soft Red Winter wheat and Canada Western Amber Durum, there were significant correlations (P < 0.001) in three of the four years investigated for each grain class. The years with no significant correlation between DON and Fusarium damage occurred when the presence of Fusarium species other than the DON-producing F. graminearum were predominant. This work provides a picture of the presence, and absence, of a number of mycotoxins in Canadian wheat and durum.

Automatic classification of non-touching cereal grains in digital images using limited morphological and color features

Producers in the semiarid Canadian prairies rely on frequent summerfallowing (F) to conserve water, control weed infestations, and maximize soil mineral N reserves, but this practice often results in soil degradation. A crop rotation experiment was initiated in 1987 on a medium-textured, Orthic Brown Chernozem at Swift Current, Saskatchewan, to determine the most ideal cropping frequency for wheat in this region and whether a fixed rotation such as fallow-wheat (Triticum aestivum L.) - wheat (F-W-W) or F-W-W-W would be more effective than flexible rotations in which fallowing is decided each spring based on criteria such as available soil water (if water), or the need to control perennial weed infestations (if weeds). The study also compared the production of traditional Canada Western Red Spring (CWRS) wheat class with the newer higher-yielding (Hy), Canada Prairie Spring (CPS) wheat class. We analyzed results of six rotations over the first 12 yr of the study. The rotations included F-W-W, F-W-W-W, F-Hy-Hy, Continuous wheat (Cont W), Cont W (if weeds), and Cont W (if water). Reduced tillage management was used and stubble was cut tall to enhance snowtrap. Fertilizer N was applied based on soil tests and fertilizer P was applied based on the general recommendations for the region. Over the 1988–1999 period, weather conditions were generally favourable and yields were above average for this region. Canada Prairie Spring wheat outyielded CWRS by 32% when grown on fallow and by 17% when grown on stubble; however, straw yields of the two wheat classes were similar on fallow and CPS was 11% less than CWRS on stubble. Harvest index (HI) averaged 44% for CPS and 37% for CWRS wheat. Water use efficiency for CWRS wheat grown on fallow averaged 7.2 kg ha-1 mm-1 and for CPS 9.4; when grown on stubble the respective values were 6.3 and 7.5 kg ha-1 mm-1. Grain N concentration for CWRS was slightly higher for wheat grown on fallow (25.7 g kg-1) than on stubble (24.5 g kg-1), but was similar for CPS wheat on grown on fallow and stubble (21.9 g kg-1). Straw N concentration averaged 3.8 g kg-1 for CWRS and 4.4 g kg-1 for CPS. Nitrogen yield for grain from CPS was 9% greater than from CWRS when grown on fallow, but there was no effect of wheat class when grown on stubble. Nitrogen yield of CPS straw was 15% greater than for CWRS when grown on fallow, but on stubble N yield was generally not affected by wheat class. Nitrogen harvest index (NHI) averaged about 80% for both wheat classes, whether grown on fallow or stubble. On a rotation basis, grain produced with F-W-W was 1502 kg ha-1 yr-1. The F-W-W-W and Cont W (if weeds) rotations produced 9% more grain than F-W-W, while Cont W (if water) produced 24% more, F-Hy-Hy produced 26% more, and Cont W produced 30% more than F-W-W. Nitrogen production in the grain, straw and aboveground plant material was lowest in F-W-W, highest in Cont W, and intermediate for other rotations. Although the economic and soil quality assessments have yet to be completed, a preliminary conclusion based on crop production characteristics alone suggests that a flexible cropping system in which available soil water in spring is used as the determining criterion is superior to a fixed F-W-W or F-W-W-W rotation. Key words: Yield, N concentration, N yield, water deficit, wheat classes, regressions

For wheat (Triticum aestivum ), sustained crop yield at limited soil water availability has been linked to osmotic adjustment (OA) - a physiological mechanism that aids maintenance of leaf hydration status, turgor (P ) and growth. 'Canada Western Red Spring' (CWRS) wheat cultivars are typically grown in rainfed areas with milder climates, but ongoing climate change is increasesing the frequency and intensity of drought events. The overarching goal of this study was to elucidate if commercially used CWRS cultivars ('Superb', 'Stettler', 'AAC Viewfield') have the ability for leaf OA. Measurements of leaf water relation parameters (water potential, Ψ ; solute potential, Ψ s ; stomatal conductance, g s ; relative water content, RWC) showed that all three cultivars reached zero P (= Ψ - Ψ s ) at a leaf Ψ of -1.1MPa. Prior to that, P maintenance in 'Superb' and 'AAC Viewfield' was associated with a significant reduction in leaf Ψ s and OA contributed 0.53MPa ('Superb') and 0.73MPa ('AAC Viewfield'). Our data analyses provided no support for the existence of OA in 'Stettler'. Under water deficit, leaf g s was significantly higher in 'AAC Viewfield' compared to 'Stettler'; it was intermediate in 'Superb'. Together, drought tolerance in CWRS wheat cultivars is most likely linked to the degree of OA.

The objective of this study was to quantify changes in morphological features of kernels of western Canadian wheat classes caused by moisture increase using a machine vision system. One hundred single wheat kernels for each of eight western Canadian wheat classes were successively conditioned from 12% to 20% (wet basis) moisture contents using potassium hydroxide (KOH) concentrations which regulated relative humidity. A digital camera of 7.4 7.4-m pixel resolution with an inter-line transfer charge-coupled device (CCD) image sensor was used to acquire images of single kernels. A machine vision algorithm developed at the Canadian Wheat Board Centre for Grain Storage Research, University of Manitoba, was implemented to extract seven morphological features (area, perimeter, major axis length, minor axis length, maximum radius, minimum radius, and mean radius) from the wheat kernel images. All the seven features of Canada Western Red Spring, Canada Western Amber Durum, Canada Prairie Spring White, Canada Prairie Spring Red, Canada Western Extra Strong, Canada Western Red Winter, Canada Western Hard White Spring, and Canada Western Soft White Spring wheat kernels were significantly (a = 0.05) different as the moisture content increased from 12% to 20%. All seven features showed a linearly increasing trend with an increase in moisture content.

Canadian Western Red Spring (CWRS) market class is the predominant type of wheat (Triticum aestivum L.) grown in Canada since the turn of the 20th century. Wheat cultivars ranging from cv. Red Fife to cv. Superb were field tested in a series of 24 replicated trials spanning 19 years in central Saskatchewan, Canada. The objective of this study was to measure the rate of cultivar improvement in light of relatively narrow end‐use quality definitions for the CWRS market class. Regression of cultivar trait means on year of cultivar registration was used to assess the rate of change in yield, productivity traits, and end‐use quality parameters. Yield levels were estimated to be increasing at a rate of approximately 15 kg/ha per year in 1970 and 23 kg/ha per year in 1995. Days to spike emergence and plant height decreased over time. Kernel weight, grain protein concentration, SDS sedimentation volume, farinograph absorption, and dough development time increased over time, whereas farinograph mixing tolerance index and yellow pigment concentration decreased. The results show that improvement in key agronomic and end‐use traits has been achieved in CWRS wheat.

Sprout damage (pre-harvest germination) in wheat results in highly deleterious effects on end-product quality. Alpha-amylase, the pre-dominant enzyme in the early stage of sprouting has the most damaging effect. This paper introduces a new method using a SWIR hyperspectral imaging system (1000–2500 nm) to predict the α-amylase activity of individual wheat kernels. Two classes of Canadian wheat, Canada Western Red Spring (CWRS) and Canada Western Amber Durum (CWAD), with samples of differing degrees of sprout damage were investigated. Individual kernels were first imaged with the hyperspectral imaging system and then the α-amylase activity of each kernel was determined analytically. Individual kernel α-amylase activity prediction was significant (R2 0.54 and 0.73) for CWAD and CWRS, respectively using Partial Least Square regression on the hyperspectral data. A classification method is proposed to separate CWRS kernels with high α-amylase activity level from those with low α-amylase activity giving an accuracy of above 80%. This work shows that hyper/multi-spectral imaging techniques can be used for rapidly predicting the α-amylase activity of individual kernels, detecting sprouting at early stage.