Detecting and Segregating Black Tip‐Damaged Wheat Kernels Using Visible and Near‐Infrared Spectroscopy

Detection of individual wheat kernels with black tip symptom (BTS) and black tip damage (BTD) was demonstrated with near‐infrared reflectance spectroscopy (NIRS) and silicon light‐emitting‐diode (LED) based instruments. The two instruments tested, a single‐kernel NIRS instrument (SKNIRS) and a silicon LED‐based single‐kernel high‐speed sorter (SiLED‐SKS) were both developed by the Stored Product Insect and Engineering Research Unit, Center for Grain and Animal Health Research, USDA Agricultural Research Service. BTD was classified into four levels for the study ranging from sound, symptomatic (BTS) at two levels, and damaged (BTD). Discriminant analysis models for the SKNIRS instrument could distinguish sound undamaged kernels well, correctly classifying kernels 80% of the time. Damaged kernels were classified with 67% accuracy and symptomatic kernels at about 44%. Higher classification accuracy (81–87%) was obtained by creating only two groupings: 1) combined sound and lightly symptomatic kernels and 2) combined heavily symptomatic and damaged kernels. A linear regression model was developed from the SiLED‐SKS sorted fractions to predict the percentage of combined BTS and BTD kernels in a sample. The model had an R² of 0.64 and a standard error of prediction of 7.4%, showing it had some measurement ability for BTS and BTD. The SiLED‐SKS correctly classified and sorted out 90% of BTD and 66% of BTS for all 28 samples after three passes through the sorter. These instruments can serve as important tools for plant breeders and grading facilities of the wheat industry that require timely and objective determination and sorting of different levels of black tip present in wheat samples.     

Determining Weight and Moisture Properties of Sound and Fusarium‐Damaged Single Wheat Kernels by Near‐Infrared Spectroscopy

Single kernel moisture content (MC) is important in the measurement of other quality traits in single kernels because many traits are expressed on a dry weight basis. MC also affects viability, storage quality, and price. Also, if near‐infrared (NIR) spectroscopy is used to measure grain traits, the influence of water must be accounted for because water is a strong absorber throughout the NIR region. The feasibility of measurement of MC, fresh weight, dry weight, and water mass of single wheat kernels with or without Fusarium damage was investigated using two wheat cultivars with three visually selected classes of kernels with Fusarium damage and a range of MC. Calibration models were developed either from all kernel classes or from only undamaged kernels of one cultivar that were then validated using all spectra of the other cultivar. A calibration model developed for MC when using all kernels from the wheat cultivar Jagalene had a coefficient of determination (R²) of 0.77 and standard error of cross validation (SECV) of 1.03%. This model predicted the MC of the wheat cultivar 2137 with R² of 0.81 and a standard error of prediction (SEP) of 1.02% and RPD of 2.2. Calibration models developed using all kernels from both cultivars predicted MC, fresh weight, dry weight, or water mass in kernels better than models that used only undamaged kernels from both cultivars. Single kernel water mass was more accurately estimated using the actual fresh weight of kernels and MC predicted by calibrations that used all kernels or undamaged kernels. The necessity for evaluating and expressing constituent levels in single kernels on a mass/kernel basis rather than a percentage basis was elaborated. The need to overcome the effects of kernel size and water mass on single kernel spectra before using in calibration model development was also highlighted.     

Variation in Kernel Hardness and Associated Traits in U.S. Barley Breeding Lines

Kernel hardness is an important trait influencing postharvest handling, processing, and food product quality in cereal grains. Though well‐characterized in wheat, the basis of kernel hardness is still not completely understood in barley. Kernels of 959 barley breeding lines were evaluated for hardness using the Single Kernel Characterization System (SKCS). Barley lines exhibited a broad range of hardness index (HI) values at 30.1–91.9. Distribution of kernel diameter and weight were 1.7–2.9 mm and 24.9–53.7 mg, respectively. The proportion of hull was 10.2–20.7%. From the 959 breeding lines, 10 hulled spring barley lines differing in HI values (30.1–91.2) were selected to study the associations of HI with proportion of hull, kernel weight, diameter, vitreousness, protein, β‐glucan, and amylose content. Vitreousness, evaluated visually using a light box, showed a clear distinction between hard and soft kernels. Hard kernels appeared translucent, while soft kernels appeared opaque when illuminated from below on the light box. Kernel brightness (L*), determined as an indicator of kernel vitreousness, showed a significant negative correlation (r = –0.83, P < 0.01) with HI. Protein, β‐glucan, amylose content, proportion of hull, kernel weight, and diameter did not show any significant association with HI.     

Removal and Isolation of Germ‐Rich Fractions from Hull‐less Barley Using a Fitzpatrick Comminuting Mill and Sieves

A process was developed to produce a germ‐enriched fraction from hull‐less barley using a Fitzpatrick comminuting mill (FitzMilling) followed by sieving. Hulled and hull‐less barleys contain 1.5–2.5% oil and, like wheat kernels, which contain wheat germ oil, much of the oil in barley kernels is in the germ fraction. A process that combined FitzMilling and sieving produced a germ‐enriched fraction with an oil content of ≈15% and a yield of ≈1.1%. For comparison, this is higher than the levels of oil in most samples of commercial wheat germ. Experimental conditions were also described to produce a germ‐enriched fraction with a higher yield (2.16%), but it would have lower oil content (10.24%). Germination and compositional analysis studies suggested that FitzMilling hull‐less barley for 2 min or longer reduced germination rates to 1% or less, which was interpreted to mean that almost the entire viable germ was removed. In contrast, FitzMilling conventional hulled barley for 4 min had no effect on germination, and milling for 6 and 8 min resulted in germination rates of 36 and 12%, respectively. The oil extracted from germ‐enriched fractions was rich in free phytosterols (≈1%), phytosterol esters (3–7%), and free fatty acids (2–10%). These germ‐enriched fractions and the extracted oil they contain may have value as nutraceuticals or premium edible oils.     

Determining Vitreous Subclasses of Hard Red Spring Wheat Using Visible/Near‐Infrared Spectroscopy

The percentage of dark hard vitreous (DHV) kernels in hard red spring wheat is an important grading factor that is associated with protein content, kernel hardness, milling properties, and baking quality. The current visual method of determining DHV and non‐DHV (NDHV) wheat kernels is time‐consuming, tedious, and subject to large errors. The objective of this research was to classify DHV and NDHV wheat kernels, including kernels that were checked, cracked, sprouted, or bleached using visible/near‐infrared (Vis/NIR) spectroscopy. Spectra from single DHV and NDHV kernels were collected using a diode‐array NIR spectrometer. The dorsal and crease sides of the kernels were viewed. Three wavelength regions, 500–750 nm, 750–1,700 nm, and 500–1700 nm were compared. Spectra were analyzed by using partial least squares (PLS) regression. Results suggest that the major contributors to classifying DHV and NDHV kernels are light scattering, protein content, kernel hardness, starch content, and kernel color effects on the absorption spectrum. Bleached kernels were the most difficult to classify because of high lightness values. The sample set with bleached kernels yielded lower classification accuracies of 91.1–97.1% compared with 97.5–100% for the sample set without bleached kernels. More than 75% of misclassified kernels were bleached. For sample sets without bleached kernels, the classification models that included the dorsal side gave the highest classification accuracies (99.6–100%) for the testing sample set. Wavelengths in both the Vis/NIR regions or the NIR region alone yielded better classification accuracies than those in the visible region only.     

Association of Barley Kernel Hardness with Physical Grain Traits and Food Processing Parameters

Kernel hardness is not a well‐characterized food quality trait in barley. Unlike wheat, not much is known about the effect of barley kernel hardness on food processing. Ten barley genotypes differing in single kernel characterization system hardness index (SKCS‐HI) (30.1–91.2) of dehulled kernels were used to determine the association of barley HI with other physical grain traits and food processing parameters. Thousand kernel weight (TKW) values of 10 genotypes were 29.7–38.1 g. Values for bulk density of grains were 721.1–758.9 kg/m³. Crease width and depth values were 0.9–1.3 mm and 0.4–0.7 mm, respectively. Barley HI showed no significant association with TKW, bulk density, or kernel crease dimensions. Kernel loss due to pearling after 325 sec of abrasion was 28.8–38.4% and showed significant negative correlation with HI (r = –0.87, P < 0.01). Proportion of barley flour particles >106 μm had values of 34.5–42.0%, and starch damage values were 1.8–4.5% among those 10 barley genotypes. HI showed significant positive correlations with both proportion of barley flour particles >106 μm (r = 0.93, P < 0.01) and starch damage (r = 0.93, P < 0.01). Water imbibition of barley kernels and cooked kernel hardness did not show significant correlation with HI.     

Influence of Barley and Malt Storage on Lipoxygenase Reaction

The dioxygenation of linoleic acid (LA) by aqueous flour suspensions of barley and malting samples was studied. The rate of this lipoxygenase (LOX) reaction varied as the malting process proceeded, giving a characteristic LOX reaction profile for a malting. The differences in the profiles from one malting to another were dramatic. It also appeared that during storage of dry, intact kernel samples from a single malting, a reduction in the rate of LOX reaction always occurred, and the rates of reduction with time were dependent on the stage of malting at the time of sampling. The kinetics of this aging could roughly be divided into four categories representing different stages of malting. Consequently, greatly varying LOX reaction profiles can be obtained from a single malting depending on the time of storage of kernels before assays. The results indicate that steeping, germination and the subsequent drying render the state of kernels unstable with respect to the LOX reaction for at least two to three weeks. Homogeneity of malt quality is important in the further applications of malt, especially in the brewing industry. Therefore, the rate of LOX reaction should be considered as a quality factor of malt.     

Automated Color Classification of Single Wheat Kernels Using Visible and Near-Infrared Reflectance

Modification of an existing single kernel wheat characterization system allowed collection of visible and near-infrared (NIR) reflectance spectra (450–1,688 nm) at a rate of 1 kernel/4 sec. The spectral information was used to classify red and white wheats in an attempt to remove subjectivity from class determinations. Calibration, validation, and prediction results showed that calibrations using partial least squares regression and derived from the full wavelength profile correctly classed more kernels than either the visible region (450–700 nm) or the NIR region (700–1,688 nm). Most results showed >99% correct classification for single kernels when using the visible and NIR regions. Averaging of single kernel classifications resulted in 100% correct classification of bulk samples.     

Surface Abrasion of Hulled and Hulless Barley: Physical Characterization of the Milled Fractions

Abrasion techniques were used to remove the hull and pericarp layers of barley kernels to obtain a smaller kernel enriched in endosperm. The objective of this study was to evaluate the fractions produced by two alternative abrading systems on four barley cultivars for potential use in fuel ethanol processes that feature an upstream (of the fermentation) dry fractionation system. Four barley cultivars, two hulled (Thoroughbred and Nomini) and two hulless (Doyce and Merlin), were scarified and whitened at 22 scarification times and three milling degrees (settings 2, 4, and 6), respectively. Three different abrasive surfaces (36, 40, and 50 grit) were used in the scarifier to determine the material removal ratio for each barley cultivar. Material balances and color analyses were conducted for all of the fractions produced. Three fractions were produced with the whitener at each milling degree: broken kernels, fine fractions >323 μm, and fine fractions <323 μm. Setting #2 seems to be the milling level that releases most of the hull in the hulled barley with the whitener. After 50 sec of scarification, rougher surfaces produced more fine material (<1,410 μm diameter) and consequently less coarse material (>1,410 μm diameter). A lower grit (36 grit) abrasive surface induced faster hull removal in hulled barley. Color parameters L* and b* were good indicators of the fine and coarse fractions produced by abrasive methods because they indicate the kernel layer removed and were modeled as a function of the fraction of the material produced. The information obtained in this study has application in designing processes capable of removing and recovering hull and pericarp layers of barley kernels and thereby producing smaller kernels or kernel pieces containing mainly endosperm tissue.     

Composition,Microstructure, Water Imbibition,and Thermal Properties of Abraded Barley

Barley, nonwaxy hull (cvs. Crystal and Meltan) and waxy hull-less (cvs. Merlin and Waxbar), was abraded at 10, 20, and 40% of kernel weight on a laboratory scale and commercially abraded at two levels: fine and coarse. In 40% abraded kernels of Crystal, protein, ash, and free lipids contents decreased by 1.6, 1.4, and 1.4%, respectively, and starch and β-glucans contents increased by 16 and 1.2%, respectively, compared to nonabraded kernels. Merlin showed smaller changes in the levels of these components, except for proteins. Changes in starch and protein in laboratory abraded barley were used to estimate the level of barley abrasion on a commercial scale. Scanning electron microscope pictures revealed that in nonwaxy barley at 10% abrasion the hull and part of the seed coat were absent, whereas waxy barley lost all of the seed coat and most of the aleurone layer. Maximum water imbibition of 40% abraded waxy barley was reached after 5 hr of soaking, whereas nonwaxy barley needed 8 hr to level off. Nonwaxy barley kernels at 20% abrasion and cooked for 10 min required 52 N to compress to 50% thickness, whereas waxy barley needed only 28 N. Changes in chemical composition and microstructure due to abrasion had a strong effect on the thermal properties of kernels during cooking. The extent to which barley starch was gelatinized during cooking was evaluated by differential scanning calorimetry. Crystal and Merlin showed significant decreases in enthalpy value for 40% compared to 10% abraded barley. These results indicate that when a large portion of the outer layer of barley is removed, water and heat penetrate more quickly into kernels during cooking, causing more starch to be gelatinized. The results obtained in this study indicate that changes in composition and microstructure due to abrasion affect the rate of water imbibition, hardness of cooked kernels, and enthalpy value of starch. Composition and properties of laboratory abraded barley could be used to predict the level of abrasion and properties of barley abraded on a commercial scale within the same cultivar.     

Effect of NaOH on Visible Wavelength Spectra of Single Wheat Kernels and Color Classification Efficiency

A diode-array system, which measures spectral reflectance from 400 to 700 nm, was used to quantify single wheat kernel color before and after soaking in NaOH as a means of determining color class. Wheat color classification is currently a subjective determination and important in determining the end-use of the wheat. Soaking kernels in NaOH and classifying the soaked kernels with the diode-array system resulted in more difficult-to-classify kernels correctly classified (98.1%) than the visual method of classifying kernels (74.8%). Kernel orientation had a slight effect on correct classification, with the side view correctly classifying more kernels than the dorsal or crease view. The diode-array system provided a means of quantifying kernel color and eliminated inspector subjectivity when determining color class.     

Near‐Infrared Hyperspectral Imaging of Fusarium‐Damaged Oats (Avena sativa L.)

The feasibility of hyperspectral imaging (HSI) to detect deoxynivalenol (DON) content and Fusarium damage in single oat kernels was investigated. Hyperspectral images of oat kernels from a Fusarium‐inoculated nursery were used after visual classification as asymptomatic, mildly damaged, and severely damaged. Uninoculated kernels were included as controls. The average spectrum from each kernel was paired with the reference DON value for the same kernel, and a calibration model was fitted by partial least squares regression (PLSR). To correct for the skewed distribution of DON values and avoid nonlinearities in the model, the DON values were transformed as DON* = [log(DON)]³. The model was optimized by cross‐validation, and its prediction performance was validated by predicting DON* values for a separate set of validation kernels. The PLSR model and linear discriminant analysis classification were further used on single‐pixel spectra to investigate the spatial distribution of infection in the kernels. There were clear differences between the kernel classes. The first component separated the uninoculated and asymptomatic from the severely damaged kernels. Infected kernels showed higher intensities at 1,925, 2,070, and 2,140 nm, whereas noninfected kernels were dominated by signals at 1,400, 1,626, and 1,850 nm. The DON* values of the validation kernels were estimated by using their average spectra, and the correlation (R) between predicted and measured DON* was 0.8. Our results show that HSI has great potential in detecting Fusarium damage and predicting DON in oats, but it needs more work to develop a model for routine application.     

Relationship Between Single Wheat Kernel Particle-Size Distribution and Perten SKCS 4100 Hardness Index

The Perten Single Kernel Characterization system is the current reference method for determination of single wheat kernel texture. However, the SKCS 4100 calibration method is based on bulk samples. The objective of this research was to develop a single-kernel hardness reference based on single-kernel particle-size distributions (PSD). A total of 473 kernels, drawn from eight different classes, was studied. Material from single kernels that had been crushed on the SKCS 4100 system was collected, milled, then the PSD of each ground single kernel was measured. Wheat kernels from soft and hard classes with similar SKCS hardness indices (HI 40–60) typically had a PSD that was expected from their genetic class. That is, soft kernels tended to have more particles at <21 μm than hard kernels after milling. As such, a combination of HI and PSD gives better discrimination between genetically hard and soft classes than either parameter measured independently. Additionally, the use of SKCS-predicted PSD, combined with other low level SKCS parameters, appears to reduce classification errors into genetic hardness classes by ≈50% over what is currently accomplished with HI alone.     

Development and Evaluation of a Near‐Infrared Instrument for Single‐Seed Compositional Measurement of Wheat Kernels

A single‐kernel, near‐infrared reflectance instrument was designed, built, and tested for its ability to measure composition and traits in wheat kernels. The major objective of the work was targeted at improving an existing design concept of an instrument used for larger seeds such as soybeans and corn but in this case designed for small seeds. Increases in throughput were sought by using a vacuum to convey seeds without compromising measurement accuracy. Instrument performance was evaluated by examining measurement accuracy of wheat kernel moisture, protein content, and kernel mass. Spectral measurements were obtained on individual wheat kernels as they were conveyed by air through an illuminated tube. Partial least squares (PLS) prediction models for these constituents were then developed and evaluated. PLS single‐kernel moisture predictions had a root mean square error of prediction (RMSEP) around 0.5% MC wet basis; protein prediction models had an RMSEP near 0.70%. Prediction of mass was not as good but still provided a reasonable estimate of single‐kernel mass, with RMSEP values of 2.8–4 mg. Data showed that kernel mass and protein content were not correlated, in contrast to some previous research. Overall, results showed the instrument performed comparably to other single‐seed instruments or methods based on accuracy but with an increased throughput at a rate of at least 4 seeds/s.     

利用近红外光谱与PCA-SVM识别热损伤番茄种子

为了研究近红外光谱技术用于热损伤种子快速无损识别的可行性,该文以120粒番茄种子为研究对象,其中60粒番茄种子通过高温加热处理的方式成为热损伤种子组,其他60粒番茄种子为正常种子组,利用实验室自主搭建的近红外光谱检测系统获取单粒番茄种子在980~1 700 nm范围内的光谱,分别采用偏最小二乘判别法(partial least squares discriminant analysis,PLS-DA)和支持向量机(support vector machines,SVM)建立了番茄种子热损伤的定性分析模型。试验结果表明:2种判别模型的验证集总正确率均大于96%,均可用于热损伤种子的判别。其中,基于主成分分析(principal component analysis,PCA)预处理的光谱数据构建的支持向量机模型的判别效果最好,其校正集和验证集的判别正确率均为100%,更适用于种子热损伤识别。因此,应用近红外光谱技术可快速无损识别热损伤番茄种子,为种子检验提供了一种新的方法。     

Development of Nondestructive Screening Methods for Single Kernel Characterization of Wheat

The development of nondestructive screening methods for single seed protein, vitreousness, density, and hardness index has been studied for single kernels of European wheat. A single kernel procedure was applied involving, image analysis, near‐infrared transmittance (NIT) spectroscopy, laboratory density determination, single kernel characterization system (SKCS), and finally Kjeldahl protein determination on the crushed single kernels. Single kernel NIT spectroscopy showed excellent ability to determine protein content, and some ability for determination of single kernel vitreousness. Nondestructive determination of single kernel density, either based on NIT spectroscopy or based on image analysis and kernel weight, needs to be further improved for practical use. The use of SKCS hardness index as a true single kernel hardness reference in a NIT prediction model resulted in a poor predictability. However, by applying an averaging approach, in which single seed replicate measurements are mathematically simulated, a very good NIT prediction model was achieved. This suggests that the single seed NIT spectra contain hardness information, but that a single seed hardness method with higher accuracy is needed to achieve a good NIT prediction model for single kernel hardness.     

基于核磁共振的玉米不同籽粒类型单粒质量和含油率分析

针对现有玉米单倍体核磁共振分选系统基于一个含油率阈值,无法对胚败育籽粒和单倍体籽粒正确分选的问题,分别对玉米生物诱导产生的二倍体、单倍体和胚败育3种不同籽粒类型的单粒质量和含油率进行分析,提出了利用籽粒含油率双阈值提高单倍体正确识别率的分选方法。该研究以2个普通玉米杂交种和3个自交系为母本,以高油型诱导系为父本,进行生物诱导产生的3种不同类型籽粒为研究对象,利用核磁共振分选系统分别对不同类型籽粒的单粒质量和含油率进行测定,结果表明：单粒质量整体表现为单倍体>二倍体>胚败育,除二倍体籽粒与胚败育籽粒间存在极显著差异外,其他籽粒类型间差异不显著;不同类型籽粒的单粒质量平均变异系数为16.62%,并且每个材料的3种籽粒类型间出现较大的重叠区域。而不同类型籽粒含油率整体表现为二倍体>单倍体>胚败育,变异性以二倍体最小,平均变异系数仅为12.52%,其次是单倍体,而胚败育籽粒最高（34.14%）,但其含油率最低且均≤2%;每个材料各自的3种类型籽粒间含油率呈现梯度分布,存在较明显的界限。由此可见,利用籽粒含油率能够区分玉米生物诱导的3种不同籽粒类型,而单粒质量则不能;通过设置二倍体籽粒的最小含油率为上限,胚败育籽粒的最大含油率为下限,利用含油率的双阈值可提高单倍体的正确识别率,为玉米生物诱导单倍体高效自动化分选提供依据。     

Hardness Measurement of Bulk Wheat by Single‐Kernel Visible and Near‐Infrared Reflectance Spectroscopy

Reflectance spectra (400 to 1700 nm) of single wheat kernels collected using the Single Kernel Characterization System (SKCS) 4170 were analyzed for wheat grain hardness using partial least squares (PLS) regression. The wavelengths (650 to 700, 1100, 1200, 1380, 1450, and 1670 nm) that contributed most to the ability of the model to predict hardness were related to protein, starch, and color differences. Slightly better prediction results were observed when the 550–1690 nm region was used compared with 950–1690 nm region across all sample sizes. For the 30‐kernel mass‐averaged model, the hardness prediction for 550–1690 nm spectra resulted in a coefficient of determination (R²) = 0.91, standard error of cross validation (SECV) = 7.70, and relative predictive determinant (RPD) = 3.3, while the 950–1690 nm had R² = 0.88, SECV = 8.67, and RPD = 2.9. Average hardness of hard and soft wheat validation samples based on mass‐averaged spectra of 30 kernels was predicted and compared with the SKCS 4100 reference method (R² = 0.88). Compared with the reference SKCS hardness classification, the 30‐kernel (550–1690 nm) prediction model correctly differentiated (97%) between hard and soft wheat. Monte Carlo simulation technique coupled with the SKCS 4100 hardness classification logic was used for classifying mixed wheat samples. Compared with the reference, the prediction model correctly classified mixed samples with 72–100% accuracy. Results confirmed the potential of using visible and near‐infrared reflectance spectroscopy of whole single kernels of wheat as a rapid and nondestructive measurement of bulk wheat grain hardness.     

Selecting and Sorting Waxy Wheat Kernels Using Near‐Infrared Spectroscopy

An automated single kernel near‐infrared (NIR) sorting system was used to separate single wheat (Triticum aestivum L.) kernels with amylose‐free (waxy) starch from reduced‐amylose (partial waxy) or wild‐type wheat kernels. Waxy kernels of hexaploid wheat are null for the granule‐bound starch synthase alleles at all three Wx gene loci; partial waxy kernels have at least one null and one functional allele. Wild‐type kernels have three functional alleles. Our results demonstrate that automated single kernel NIR technology can be used to select waxy kernels from segregating breeding lines or to purify advanced breeding lines for the low‐amylose kernel trait. Calibrations based on either amylose content or the waxy trait performed similarly. Also, a calibration developed using the amylose content of waxy, partial waxy, and wild‐type durum (T. turgidum L. var durum) wheat enabled adequate sorting for hard red winter and hard red spring wheat with no modifications. Regression coefficients indicated that absorption by starch in the NIR region contributed to the classification models. Single kernel NIR technology offers significant benefits to breeding programs that are developing wheat with amylose‐free starches.     

基于胚部区域特征的麦粒姿态自动识别

麦粒姿态的自动判别,是近红外高光谱成像系统自动检测多姿态麦粒内部虫害的前提。依据麦粒目标在最优波长图像中的坐标、重心等信息,从高光谱数据立方体中自动分割出单个完整麦粒的子图像。利用麦粒胚部端粗糙度较大的原理,依据纹理、不变矩、均值等13个可能胚部区域特征的判别正确率,确定不变矩4为判别麦粒胚部区域的有效特征。针对麦粒胚部区域,提取梯度图像和二值图像的26个特征,利用人工鱼群算法选择出延伸率、胚部区域对称度、延伸率等13个特征。选取1 200个样本进行训练,600个样本进行检验,利用最大离差法自动确定13个特征的模糊权重,麦粒3个姿态可拓分类的正确识别率为94.5%,证实了基于局部区域特征的麦粒姿态自动识别的可行性。