Identification of wheat grain in different states based on hyperspectral imaging technology

Abstract

Nondestructive identification of wheat grains in different states plays an important role in improving the quality of wheat products. This study investigated the possibility of using hyperspectral imaging techniques to discriminate healthy wheat grain, germinated wheat grain, mildewed wheat grain, and shriveled wheat grain (wheat grain infected with fusarium head blight). Both sides of individual wheat kernels were subjected to hyperspectral imaging (866.4–1701.0?nm) to acquire hyperspectral cube data. Spectral data were preprocessed by using standardization and multiple scattering correction. In addition, the principal component loading method was used to extract the characteristic wavelengths of both sides of wheat grains. The sample is divided into calibration set, test set, and validation set. The data of the calibration set are used to train the partial least squares discriminant analysis model, K-nearest neighbor model, and the support vector machine model, and the test set data are used to test the model. The results show that spectral data of both sides can achieve good classification results, while the reverse spectral data perform better. By comparing with each other, the support vector machine model is selected as the best classification model. Finally, using two hyperspectral images (reverse side) that are not involved in training and testing to verify the accuracy of the established support vector machine model, and the classification effect maps of the four wheat grains were visualized. The results indicate that nondestructive classification of wheat grains in different states is feasible based on hyperspectral imaging technology.     

Identification of microalgae by hyperspectral microscopic imaging system

Harmful algal blooms can lead to serious environment problems, and thus monitoring and classifying microalgae have received increasing attention. Microcystis aeruginosa, Chlorella pyrenoidosa, and Nannochloris oculata all are small in size and have a similar morphology, which lead to discriminant difficulties using a traditional optical microscope. In this experiment, an independently developed hyperspectral microscopic imaging system was used to obtain the hyperspectral images of microalgae samples, and a hyperspectral dataset was developed through pretreated steps. Then the Fisher algorithm was employed to identify the species of the microalgae, and its sensitivity and specificity were found to be high. The result demonstrated that this method can classify the microalgae in a quick and convenient manner; in addition, the quantity and spatial information of the samples can be acquired.     

A hybrid spatial-spectral denoising method for infrared hyperspectral images using 2DPCA

The traditional noise reduction methods for 3-D infrared hyperspectral images typically operate independently in either the spatial or spectral domain, and such methods overlook the relationship between the two domains. To address this issue, we propose a hybrid spatial-spectral method in this paper to link both domains. First, principal component analysis and bivariate wavelet shrinkage are performed in the 2-D spatial domain. Second, 2-D principal component analysis transformation is conducted in the 1-D spectral domain to separate the basic components from detail ones. The energy distribution of noise is unaffected by orthogonal transformation; therefore, the signal-to-noise ratio of each component is used as a criterion to determine whether a component should be protected from over-denoising or denoised with certain 1-D denoising methods. This study implements the 1-D wavelet shrinking threshold method based on Stein’s unbiased risk estimator, and the quantitative results on publicly available datasets demonstrate that our method can improve denoising performance more effectively than other state-of-the-art methods can.     

Discrimination methods for biological contaminants in fresh-cut lettuce based on VNIR and NIR hyperspectral imaging

The rapid detection of biological contaminants such as worms in fresh-cut vegetables is necessary to improve the efficiency of visual inspections carried out by workers. Multispectral imaging algorithms were developed using visible-near-infrared (VNIR) and near-infrared (NIR) hyperspectral imaging (HSI) techniques to detect worms in fresh-cut lettuce. The optimal wavebands that can detect worms in fresh-cut lettuce were investigated for each type of HSI using one-way ANOVA. Worm-detection imaging algorithms for VNIR and NIR imaging exhibited prediction accuracies of 97.00% (RI_547/945) and 100.0% (RI_1064/1176, SI_1064-1176, RSI-I_{(1064-1173)/1064}, and RSI-II_{(1064-1176)/(1064+1176)})_, respectively. The two HSI techniques revealed that spectral images with a pixel size of 1 × 1 mm or 2 × 2 mm had the best classification accuracy for worms. The results demonstrate that hyperspectral reflectance imaging techniques have the potential to detect worms in fresh-cut lettuce. Future research relating to this work will focus on a real-time sorting system for lettuce that can simultaneously detect various defects such as browning, worms, and slugs.     

Comparison of chemometric methods in the analysis of pharmaceuticals with hyperspectral Raman imaging

Chemical imaging method of vibrational spectroscopy, which provides both spectral and spatial information, creates a three‐dimensional (3D) dataset with a huge amount of data. When the components of the sample are unknown or their reference spectra are not available, the classical least squares (CLS) method cannot be applied to create visualized distribution maps. Raman image datasets can be evaluated even in such cases using multivariate (chemometric) methods for extracting the needed hidden information. The capability of chemometrics‐assisted Raman mapping is evaluated through the analysis of pharmaceutical tablets (considered as unknown) with the aim of estimating the pure component spectra based on the collected Raman image. Six chemometric methods, namely, principal component analysis (PCA), maximum autocorrelation factors (MAF), sample–sample 2D correlation spectroscopy (SS2D), self‐modeling mixture analysis (SMMA), multivariate curve resolution–alternating least squares (MCR‐ALS), and positive matrix factorization (PMF), were compared. SMMA was found to be the best choice to determine the number of components. MCR‐ALS and PMF provided the pure component spectra with the highest quality. MCR‐ALS was found to be superior to PMF in the estimation of Raman scores (which correspond to the concentrations) and yielded almost the same results as CLS (using the real reference spectra). Thus, the combination of Raman mapping and chemometrics could be successfully used to characterize unknown pharmaceuticals, identify their ingredients, and obtain information about their structures. This may be useful in the struggles against illegal and counterfeit products and also in the field of pharmaceutical industry when contaminants are to be identified. Copyright © 2011 John Wiley & Sons, Ltd.     

利用高光谱微分指数进行冬小麦条锈病病情的诊断研究

人工田间会诱发不同等级的小麦条锈病,在不同生育期需测定染病冬小麦冠层光谱以及相应小麦的病情指数。把冠层光谱一阶微分数据与相应的小麦病情指数进行相关分析,采用单变量线性和非线性回归技术,选取部分样本建立小麦的病情指数估测模型,并利用其余的样本对模型进行检验。结果表明,病情指数与一阶微分在432~582nm,637~701nm和715~765nm波长区域内具有极显著的相关性。以蓝边内一阶微分总和(SDb)与红边内一阶微分总和(SDr)的归一化值作为变量的模型是估测病情指数的最佳模型,其RMSE为5.73%。研究表明,可用高光谱信息监测作物的病害情况,且精度较高。利用高光谱遥感监测病害程度及其影响具有实际的应用价值。     

近红外光谱研究水与甲醇混合溶液的氢键作用

对于浓度为0～100wt％(浓度间隔为5wt％)的水-甲醇混合溶液的近红外光谱,通过分析OH组合谱带和倍频谱带随浓度的变化,探索了水-醇溶液中的氢键作用。由于OH谱带在近红外区域重叠比较严重,采用了不同的光谱分析方法——二阶导数、主成分分析和二维相关分析来提高光谱分辨率,进而达到从水-甲醇溶液的近红外光谱获取有用信息的目的。定性地阐述了水-醇混合溶液中的水和醇之间通过氢键的可能结合方式,为探索水-醇混合溶液中的氢键作用提供了一种新的可能性。     

近红外光谱法应用于食用香精中增塑剂的检测研究

借助近红外透射光谱技术得到香精样品的原始光谱,选取波段范围为8 800～8 540和7 500～5 085 cm-1,用主成分分析（PCA）法定性识别其中是否添加DEHP或DINP,正确率100%。同时测定了DEHP和DINP（浓度范围在0～100 mg·kg-1之间）在食用香精中的含量,并以偏最小二乘法（PLS）建立定量分析模型,DEHP和DINP预测结果的相对误差分别在-17.6%～15.8%和-7.6%～9.9%之间,预测均方根误差分别为1.39和0.98。为检测食用香精中增塑剂的含量提供了一种可同时定性与定量的快速、简便、廉价、准确的分析方法。     

Comparison of models and visualization of total volatile basic nitrogen content in mutton using hyperspectral imaging and variable selection methods

Hyperspectral imaging combined with variable selection methods was used to perform the rapid and accurate detection and visualization of total volatile basic nitrogen content in mutton. For each sample, several spectra were extracted from the region of muscle pixels for modeling, and the model performance was improved and better than the model established with average spectrum extracting from each sample. By two steps of variable screening with competitive adaptive reweighted sampling and stepwise regression methods, the efficient dimensionality reduction of spectral data was achieved, and the important characteristic variables were selected. The nonlinear model significantly improved the model predictive capability, and the visualization distribution map based on the model was consistent with the actual change of meat spoilage.     

利用光谱和质谱成像技术实现指纹痕量检测

近年来,依赖于先进光源的化学成像技术迅速发展,极大提高了痕量检测的准确性,在公共安全、环境、食品、医药、考古等领域具有重要的实用价值.在痕量检测中,通过将成像技术与光谱测量技术、质谱技术等相结合,能够同时获取检验对象的物质组成和二维图像信息,不仅可以揭示材料表面的痕量物质成分及其分布,还可以在提高检验灵敏度的情况下,减少甚至避免传统检测手段所需要的特殊显现剂,因此与其他检验方法具有良好的兼容性.本文以指纹检验这一典型的痕量检测问题为例,阐述基于光谱和质谱成像技术的化学成像方法在痕量检测领域中的应用,从定向针对特定组分的化学成像和非定向的直接化学成像两个方面,综述了在指纹显现或显现增强中获得应用的主要成像手段,包括可见-近红外成像、红外成像、拉曼成像、质谱成像等.     

香梨表面低浓度农药残留高光谱检测研究

以喷洒不同浓度杜邦万灵的香梨作为研究对象,探讨了应用高光谱成像技术检测香梨表面农药残留的方法。运用376~1051nm高光谱成像系统采集200个香梨的高光谱图像,其中120个香梨为建模集,80个香梨为预测集。运用多元散射校正(MSC)对光谱数据进行预处理,然后采用连续投影算法(SPA)提取了11个特征波长。基于处理后的光谱数据,分别运用多元线性回归法(MLR)和主成分回归法(PCR)两种算法分别建立农药残留检测的模型,比较两种模型的结果。通过比较,采用MLR建立的农药残留检测模型效果较优,其校正集相关系数(Rc)为0.973,校正均方根误差(RMSEC)为0.260,预测的正确率可以达到91.7%,对较低浓度残留的预测正确率达到80%。研究表明,应用高光谱成像技术可以成功地检测香梨表面农药残留,并且对低浓度检测也有很好的效果。     

High speed measurement of corn seed viability using hyperspectral imaging

Corn is one of the most cultivated crops all over world as food for humans as well as animals. Optimized agronomic practices and improved technological interventions during planting, harvesting and post-harvest handling are critical to improving the quantity and quality of corn production. Seed germination and vigor are the primary determinants of high yield notwithstanding any other factors that may play during the growth period. Seed viability may be lost during storage due to unfavorable conditions e.g. moisture content and temperatures, or physical damage during mechanical processing e.g. shelling, or over heating during drying. It is therefore vital for seed companies and farmers to test and ascertain seed viability to avoid losses of any kind. This study aimed at investigating the possibility of using hyperspectral imaging (HSI) technique to discriminate viable and nonviable corn seeds. A group of corn samples were heat treated by using microwave process while a group of seeds were kept as control group (untreated). The hyperspectral images of corn seeds of both groups were captured between 400 and 2500 nm wave range. Partial least squares discriminant analysis (PLS-DA) was built for the classification of aged (heat treated) and normal (untreated) corn seeds. The model showed highest classification accuracy of 97.6% (calibration) and 95.6% (prediction) in the SWIR region of the HSI. Furthermore, the PLS-DA and binary images were capable to provide the visual information of treated and untreated corn seeds. The overall results suggest that HSI technique is accurate for classification of viable and non-viable seeds with non-destructive manner.     

蔬菜表面农药残留可见-近红外光谱探测与分类识别研究

利用在600～1 100nm波段范围内可见-近红外反射光谱分析技术,对常见的高残留农药在绿色植物活体上的无损检测进行了研究。首先将采集到的漫反射光谱数据进行小波变换提取光谱特征,然后再利用主成分分析方法进一步对光谱特征进行分析,最后把这些光谱的前两个主成分得分作为神经网络的输入信息,建立了多神经元的神经网络感知器。对农药残留检测的结果表明,该方法可有效甄别农药残留和种类,识别得到较好的分类效果。总之,该研究为蔬菜和瓜果表面的农药残留快速无损检测和识别提供了一条新途径。     

太赫兹成像技术对玉米种子的鉴定和识别

利用太赫兹时域光谱(THz_TDS)测试技术及透射式太赫兹逐点扫描成像技术分别对几种玉米种子DNA和胚的样品进行了光谱和成像测量;利用空间图样成份分析(component spatial pattern analysis)方法对得到的THz像进行识别运算。实验结果表明,几种样品在THz波段都有不同的吸收特性,但都没有明显的吸收峰,不能利用“特征指纹谱”进行识别。用基于THz扫描成像的空间图样成份分析方法能很好地实现不同玉米种子DNA样品的鉴定和识别。与现有的THz图像识别方法相比,这个方法只需要THz像的实验数据和样品的吸收谱信息,不需要样品的其它特征。这项研究为进一步利用THz成像技术实现无损检测、安全检查、质量监测等提供了依据,具有实际应用价值。     

近红外光谱结合ELM快速检测固态发酵过程参数pH值

pH值是固态发酵过程关键参数之一,为此提出基于近红外光谱技术的秸秆蛋白饲料固态发酵过程参数pH值检测方法。利用近红外光谱系统获取140个固态发酵过程产物样本在10 000～4 000cm-1范围内的近红外光谱数据,通过酸度计测得近红外光谱预测模型的参考测量值;运用ELM算法建立pH值的预测模型,在模型建立过程中由交互验证法确定最佳主成分因子数和ELM网络隐含层节点数。试验结果显示:最佳ELM网络模型的拓扑结构为10-40-1,模型预测集相关系数(Rp)和预测均方根误差(RMSEP)分别为0.961 8和0.104 4。研究结果可为固态发酵过程参数的在线检测提供技术基础。     

Near-Infrared spectroscopy and hyperspectral imaging for non-destructive quality assessment of cereal grains

Hyperspectral imaging (HSI) combines spectroscopy and imaging, providing information about the chemical properties of a material and their spatial distribution. It represents an advance of traditional Near-Infrared (NIR) spectroscopy. The present work reviews the most recent applications of NIR spectroscopy for cereal grain evaluation, then focuses on the use of HSI in this field. The progress of research from ground material to whole grains and single kernels is detailed. The potential of NIR-based methods to predict protein content, sprout damage and α-amylase activity in wheat and barley is shown, in addition to assessment of quality parameters in other cereals such as rice, maize and oats, and the estimation of fungal infection. This analytical technique also offers the possibility to rapidly classify grains based on properties such as variety, geographical origin, kernel hardness, etc. Further applications of HSI are expected in the near future, for its potential for rapid single-kernel analysis.     

Simultaneous species and sex identification of silkworm pupae using hyperspectral imaging technology

To obtain high-quality raw silk and improve the economic values of sericulture industry, sex needs to be discriminated first before cross-breeding. Much work has been reported about sex identification. However, to realize automatic separation of silkworm pupae, the species also needs to be classified, which no research has ever explored. Hence, this paper studied the feasibility of visible and near-infrared hyperspectral imaging technology to identify the species and sex of silkworm pupae. 288 hyperspectral images of silkworm pupae were collected and the average spectra were extracted from the region of interest, around the tail region of silkworm pupae. Successive projection algorithm was served as a variable selection method to choose the optimal wavelengths from the full spectra. At the same time, principal component analysis was used to choose the characteristic images. Then, the gray-level co-occurrence matrix was implemented on the first three principal component images (accounted for 99.05% of the total variances) to extract 48 textural features. Partial least squares discriminant analysis and support vector machine models were built, respectively, based on the spectral data, textural data and fusion data that included spectral and textural data, in which the support vector machine model based on the fusion data, gave the best species and sex identification result with an accuracy of 95.83%. It demonstrated that the hyperspectral imaging technology could be a new and nondestructive method to replace the manual work.     

Improvement of sensitivity using principal component analysis by dual focused ion beam time-of-flight secondary ion mass spectrometry

It is important to develop and to practically use the method to analyze a micro-nanometer order area. Especially, three-dimensional microanalysis for minute structure that consists of the organic compounds and the polymer is difficult. We developed a novel three-dimensional microanalysis method by means of focused ion beam (FIB) for section processing and ToF-SIMS for mapping method. For the purpose of realization of three-dimensional microanalysis and a chemical and structural analysis of the organic matter, the sensitivity improvement of ToF-SIMS in the three-dimensional analysis device and the method of the spectral analysis are examined. To improve the sensitivity of ToF-SIMS, the sample stage was modified to arrange perpendicularly with the ToF optical axis, and the distortion of electric field was corrected. And, by analyzing the fragment ions by using the principal component analysis (PCA) to raise the efficiency of the spectrum analysis, spatial resolution has improved. As a result, the resolution of the device improved to sub micrometer order, and advanced to the achievement of the three-dimensional microanalysis.     

A review of hyperspectral imaging for nanoscale materials research

As an emerging technology, hyperspectral imaging (HSI), which combines both advanced spectroscopy and imaging techniques, provides sufficient information for spectral and spatial analysis and is thus suitable for distribution and property investigation of nanoscale materials. Considering the applications of HSI have spread from remote sensing to quality control of macro products such as food and milk, this article reviews recent research of HSI in a new field of nanoscale materials. On the basis of fundamental parts of a HSI system, new techniques fitting specifically for nanoscale materials imaging such as dark field and Raman spectroscopy are introduced. Nanoscale materials, including metal nanoparticles, carbon nanotubes and graphene, biological components in cells and tissues, as well as multi-layer nanoscale materials, are the research hotspots utilizing HSI technology. Related research reports of the above materials are reviewed based on the physical distinction of these nanoscale materials. It is believed that HSI technology is a strongly potential technique for property investigation and manipulation of nanomaterial for various applications.     

高光谱最优波长选择及Fisher判别分析法判别玉米颗粒表面黄曲霉毒素

黄曲霉毒素是广泛存在于玉米中且具有剧毒的一种代谢产物,以美国农业部农业研究署(USDA-ARS) Toxicology and Mycotoxin Research Unit提供的2010年先锋玉米为研究对象,验证了高光谱成像技术对玉米中黄曲霉毒素检测的可行性。以甲醇为溶剂制备四种不同浓度的黄曲霉毒素溶液,并将其逐一滴在等量的4组共120粒玉米颗粒表面,以未处理的30粒洁净玉米作为一组对照样本,将大小、形状相似的150个样品随机分为训练集103个,验证集47个;对获取的400～1 000 nm波段范围内的高光谱图像,先进行标准正态变量变换(standard normal variate transformation, SNV)预处理,然后引入基于Fisher判别最小误判率的方法选择最优波长,并以所选波长作为Fisher判别分析法的输入建立判别模型,对玉米颗粒表面不同浓度的黄曲霉毒素进行识别,最后对模型判别正确率进行了验证。结果表明,选取四个最优波长(812.42, 873.00, 900.36和965.00 nm)时Fisher判别分析模型对训练集与验证集的准确率分别为87.4%和80.9%。该方法为含黄曲霉毒素玉米颗粒便携式检测仪器的开发,以及对田间霉变玉米自然代谢产生毒素的检测奠定了技术基础。