Detection of different stages of fungal infection in stored canola using near-infrared hyperspectral imaging

Near-infrared (NIR) hyperspectral imaging system was used to detect different stages of fungal infections in stored canola. Artificially infected canola seeds (Fungi: Aspergillus glaucus and Penicillium spp) were subjected to hyperspectral imaging in the range between 1000 and 1600 nm at 61 evenly distributed wavelengths. Four wavelengths 1100, 1130, 1250 and 1300 nm were identified as significant wavelengths and were used in statistical discriminant analysis. Pair-wise, two-class and six-class classification models were developed to classify the healthy and different stages of fungal infected samples. Linear, quadratic and Mahalanobis discriminant classifiers were used to classify healthy, five stages of A. glaucus and five stages of Penicillium spp infected canola seeds. All the three classifiers classified healthy and fungal infected canola seeds with a classification accuracy of more than 95% for healthy canola seeds and more than 90% for the initial stages of A. glaucus and Penicillium spp infected canola seeds. The classification accuracy increased to 100% with increase in fungal infection level (length of time since inoculation). All the samples subjected to imaging were tested for seed germination and free fatty acid value (FAV). The germination decreased with increase in amount of fungal infection, whereas FAV increased with increase in amount of fungal infection.     

Detection of insect-damaged wheat kernels using near-infrared hyperspectral imaging

Insect damage in wheat adversely affects its quality and is considered one of the most important degrading factors in Canada. The potential of near-infrared (NIR) hyperspectral imaging for the detection of insect-damaged wheat kernels was investigated. Healthy wheat kernels and wheat kernels visibly damaged by Sitophilus oryzae, Rhyzopertha dominica, Cryptolestes ferrugineus, and Tribolium castaneum were scanned in the 1000–1600 nm wavelength range using an NIR hyperspectral imaging system. Dimensionality of the acquired hyperspectral data was reduced using multivariate image analysis. Six statistical image features (maximum, minimum, mean, median, standard deviation, and variance) and 10 histogram features were extracted from images at 1101.69 and 1305.05 nm and given as input to statistical discriminant classifiers (linear, quadratic, and Mahalanobis) for classification. Linear discriminant analysis and quadratic discriminant analysis classifiers correctly classified 85–100% healthy and insect-damaged wheat kernels.     

Detection of fungal infection in five different pulses using near-infrared hyperspectral imaging

The five major pulse crops grown in Canada are: chick peas, green peas, lentils, pinto beans and kidney beans. Potential causes of fungal infection in these pulses are Aspergillus flavus and Penicillium commune. Early stages of fungal infections in pulses are not detectable with human eyes and traditional microbial methods require significant time to detect fungal infection. Near-infrared (NIR) hyperspectral imaging system is an advanced technique widely being assessed for detection of insect infestation and fungal infection in cereal grains and oilseeds. The primary objective of this study was to assess the feasibility of the NIR hyperspectral imaging system to identify fungal infections in pulses. Hyperspectral images of healthy and fungal infected chick peas, green peas, lentils, pinto beans and kidney beans were acquired and features (six statistical and 10 histogram) were used to develop classification models to identify fungal infection caused by A. flavus and P. commune. Images of healthy and fungal-infected kernels were acquired at 2 week intervals (0, 2, 4, 6, 8 and 10 weeks from artificial inoculation). Six-way (healthy vs the five different stages of infection) and two-way (healthy vs every stage of infection) models were developed and classifications were done using linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) classifiers. The LDA classifier identified both types of fungal infections with 90–94% accuracy while using the six-way model, and with 98–100% accuracy when using the two-way models for all five types of pulses. The QDA classifier also showed promising results as it gave 85–90% accuracy for the six-way model and 96–100% accuracy for the two-way models. The two fungal species could not be differentiated by the hyperspectral imaging.     

Fusarium damage assessment in wheat kernels by Vis/NIR hyperspectral imaging

Fusarium head blight is a fungal disease that affects the world’s small grains, such as wheat and barley. Attacking the spikelets during development, the fungus causes a reduction of yield and grain of poorer processing quality. Secondary metabolites that often accompany the fungus, such as deoxynivalenol (DON), are health concerns to humans and livestock. Conventional grain inspection procedures for Fusarium damage are heavily reliant on human visual analysis. As an inspection alternative, a near-infrared (NIR) hyperspectral image system (1000–1700 nm) was fabricated and applied to Fusarium-damaged kernel recognition. An existing extended visible (400–1000 nm) system was similarly used. Exhaustive searches were performed on the 144 and 125 wavelength pair images that, respectively, comprised the NIR and visible systems to determine accuracy of classification using a linear discriminant analysis (LDA) classifier. On a limited set of wheat samples the best wavelength pairs, either with visible or NIR wavelengths, were able to discriminate Fusarium-damaged kernels from sound kernels, both based on visual assessment, at an average accuracy of approximately 95%. Accuracy dropped off substantially when the visual contrast between the two kernel conditions became imperceptible. The NIR region was slightly better than the visible region in its broader array of acceptable wavelength pairs. Further, the region of interest (ROI) defined as the whole kernel was slightly better than ROIs limited to either a portion of the endosperm or the germ tip. For the NIR region, the spectral absorption near 1200 nm, attributed to ergosterol (a primary constituent in fungi cell membranes), was shown to be useful in spectral recognition of Fusarium damage.     

Feasibility of Detecting Aflatoxin B1 on Inoculated Maize Kernels Surface using Vis/NIR Hyperspectral Imaging

The feasibility of using a visible/near‐infrared hyperspectral imaging system with a wavelength range between 400 and 1000 nm to detect and differentiate different levels of aflatoxin B₁ (AFB₁) artificially titrated on maize kernel surface was examined. To reduce the color effects of maize kernels, image analysis was limited to a subset of original spectra (600 to 1000 nm). Residual staining from the AFB₁ on the kernels surface was selected as regions of interest for analysis. Principal components analysis (PCA) was applied to reduce the dimensionality of hyperspectral image data, and then a stepwise factorial discriminant analysis (FDA) was performed on latent PCA variables. The results indicated that discriminant factors F₂ can be used to separate control samples from all of the other groups of kernels with AFB₁ inoculated, whereas the discriminant factors F₁ can be used to identify maize kernels with levels of AFB₁ as low as 10 ppb. An overall classification accuracy of 98% was achieved. Finally, the peaks of β coefficients of the discrimination factors F₁ and F₂ were analyzed and several key wavelengths identified for differentiating maize kernels with and without AFB₁, as well as those with differing levels of AFB₁ inoculation. Results indicated that Vis/NIR hyperspectral imaging technology combined with the PCA–FDA was a practical method to detect and differentiate different levels of AFB₁ artificially inoculated on the maize kernels surface. However, indicated the potential to detect and differentiate naturally occurring toxins in maize kernel.     

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

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.     

Detection of fusarium damage in Canadian wheat using visible/near-infrared hyperspectral imaging

Fusarium damage in wheat may reduce the quality and safety of food and feed products. In this study, the use of hyperspectral imaging was investigated to detect fusarium damaged kernels (FDK) in Canadian wheat samples. More than 5,200 kernels, representing seven major Canadian wheat classes, with varying degree of infection symptoms ranging from sound through mild to severe were imaged in the visible-NIR (400–1,000 nm) wavelength range. Partial least squares discriminant analysis (PLS-DA) was used to segregate kernels into sound and damaged categories based on kernel mean spectra. A universal PLS-DA model based on four wavelengths was able to detect FDK in all seven classes with an overall accuracy of 90 % and false positives of 9 %.     

Near-infrared hyperspectral imaging for grading and classification of pork

In this study, a hyperspectral imaging technique was developed to achieve fast, accurate, and objective determination of pork quality grades. Hyperspectral images were acquired in the near-infrared (NIR) range from 900 to 1700 nm for 75 pork cuts of longissimus dorsi muscle from three quality grades (PSE, RFN and DFD). Spectral information was extracted from each sample and six significant wavelengths that explain most of the variation among pork classes were identified from 2nd derivative spectra. There were obvious reflectance differences among the three quality grades mainly at wavelengths 960, 1074, 1124, 1147, 1207 and 1341 nm. Principal component analysis (PCA) was carried out using these particular wavelengths and the results indicated that pork classes could be precisely discriminated with overall accuracy of 96%. Algorithm was developed to produce classification maps of the tested samples based on score images resulting from PCA and the results were compared with the ordinary classification method. Investigation of the misclassified samples was performed and showed that hyperspectral based classification can aid in class determination by showing spatial location of classes within the samples.     

Application of NIR hyperspectral imaging for discrimination of lamb muscles

The potential of near-infrared (NIR) hyperspectral imaging system coupled with multivariate analysis was evaluated for discriminating three types of lamb muscles. Samples from semitendinosus (ST), Longissimus dorsi (LD) and Psoas Major (PM) of Charollais breed were imaged by a pushbroom hyperspectral imaging system with a spectral range of 900-1700 nm. Principal component analysis (PCA) was used for dimensionality reduction, wavelength selection and visualizing hyperspectral data. Six optimal wavelengths (934, 974, 1074, 1141, 1211 and 1308 nm) were selected from the eigenvector plot of PCA and then used for discrimination purpose. The results showed that it was possible to discriminate lamb muscles with overall accuracy of 100% using NIR hyperspectral reflectance spectra. An image processing algorithm was also developed for visualizing classification results in a pixel-wise scale with a high overall accuracy.     

Identification of <Emphasis Type="Italic">Staphylococcus</Emphasis> species with hyperspectral microscope imaging and classification algorithms

Hyperspectral microscope imaging method was presented as a rapid and efficient tool to classify gram-positive bacteria species. The datacube (1024 × 1024 × 89) were obtained by hyperspectral microscope imaging system, which provided cell images between 450 and 800 nm wavelengths with 4-nm resolution, resulting in 89 contiguous spectral images that were acquired with an acousto-optic tunable filters (AOTF) hyperspectral imaging platform. Spectral information of bacteria were extracted from region-of-interest (ROI) in the cell, which were approximately between 140 and 380 pixels depending on the size of the cells. Using a Mahalanobis distance algorithm, the outliers beyond 99 % confidence of data were eliminated and classified five species with classification methods including partial least square discriminant analysis (PLS-DA) and support vector machine (SVM) for linear and non-linear classification algorithms to differentiate Staphylococcus species. PLS-DA classified five species with 89.8 % accuracy and 0.87 kappa coefficient; whereas, SVM had much higher classification accuracy of 97.8 % with 0.97 kappa coefficient. To reduce the number of wavelengths for fast data processing, thirty-one spectral bands out of 89 contiguous bands were selected using the correlation of each band. When SVM classification method with selected bands were used, the classification accuracy and kappa coefficient were 93.9 % and 0.92, respectively.     

利用可见/近红外光谱技术对小米产地进行溯源研究

目的利用可见/近红外光谱技术对产自不同地区的晋谷21号小米进行溯源研究。方法使用近红外光谱仪获取产自洪洞、浮山、沁县3个不同地区的晋谷21号小米400~1004nm波段范围内的漫反射光谱;对光谱分别进行多元散射校正法(multiple scattering correction,MSC)、一阶导数法(first derivative,1St-D)预处理;对预处理光谱进行主成分分析,全交叉验证确定最佳主成分数量,获取主成分;同时选择预处理光谱特征波长。使用马氏距离法、线性判别法建立判别模型,最后用未知样品的验证准确率来表示模型的判别效果。结果原始光谱和MSC处理光谱提取特征波长分别建立的产地判别模型对3个不同产地的小米判别完全准确;1St-D处理光谱基于7个主成分结合马氏距离法和基于9个主成分结合线性判别法建立的2种判别模型对3个不同产地的小米亦实现完全准确判别。结论可见/近红外反射光谱技术用于小米产地的判别具有可行性,本研究可为小米产地的快速判别应用中提供技术基础。     

Quality classification of cooked, sliced turkey hams using NIR hyperspectral imaging system

This study was carried out to develop a hyperspectral imaging system in the near infrared (NIR) region (900-1700 nm) to assess the quality of cooked turkey hams of different ingredients and processing parameters. Hyperspectral images were acquired for ham slices originated from each quality grade and then their spectral data were extracted. Spectral data were analyzed using principal component analysis (PCA) to reduce the high dimensionality of the data and for selecting some important wavelengths. Out of 241 wavelengths, only eight wavelengths (980, 1061, 1141, 1174, 1215, 1325, 1436 and 1641 nm) were selected as the optimum wavelengths for the classification and characterization of turkey hams. The data analysis showed that it is possible to separate different quality turkey hams with few numbers of wavelengths on the basis of their chemical composition. The results revealed the potentiality of NIR hyperspectral imaging as an objective and non-destructive method for the authentication and classification of cooked turkey ham slices.     

Differentiation of toxigenic fungi using hyperspectral imagery

Some pathogenic fungi, Aspergillus flavus for example, produce mycotoxins that can contaminate grain products including wheat and corn. The contaminated grain poses a threat to the health of both humans and animals. Therefore, from the perspective of food safety and protection, it is important to detect and identify the different toxin-producing fungi encountered in food production. Earlier studies examined various spectral-based, non-destructive methods for the detection of fungi and toxins. The present report focused on the feasibility of using spectral image data for fungal species classification. A tabletop hyperspectral imaging system, VNIR-100E, was used for spectral and spatial data acquisition. A total of five fungal species were selected for a two-part experiment: Penicillium chrysogenum, Fusarium moniliforme (verticillioides), Aspergillus parasiticus, Trichoderma viride, and Aspergillus flavus. All fungal isolates were cultured on media under laboratory conditions and were imaged on day 5 of growth. The objective of the study was to use visible near-infrared hyperspectral imagery to differentiate fungal species. Results indicate that all five fungi are highly separable with classification accuracy of 97.7%. In addition, all five fungi could be classified by using only three narrow bands (bandwidth = 2.43 nm) centered at 743 nm, 458 nm, and 541 nm.     

Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling

The objective of this study was to develop a non-destructive method for classifying cooked-beef tenderness using hyperspectral imaging of optical scattering on fresh beef muscle tissue. A hyperspectral imaging system (λ = 922–1739 nm) was used to collect hyperspectral scattering images of the longissimus dorsi muscle (n = 472). A modified Lorentzian function was used to fit optical scattering profiles at each wavelength. After removing highly correlated parameters extracted from the Lorentzian function, principal component analysis was performed. Four principal component scores were used in a linear discriminant model to classify beef tenderness. In a validation data set (n = 118 samples), the model was able to successfully classify tough and tender samples with 83.3% and 75.0% accuracies, respectively. Presence of fat flecks did not have a significant effect on beef tenderness classification accuracy. The results demonstrate that hyperspectral imaging of optical scattering is a viable technology for beef tenderness classification.     

Using a Short Wavelength Infrared (SWIR) hyperspectral imaging system to predict alpha amylase activity in individual Canadian western wheat kernels

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 (R ² 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.     

Determining optimal wavebands using genetic algorithm for detection of internal insect infestation in tart cherry

This paper reports the results of waveband selection for detecting internal insect infestation in tart cherries as a precursor to development of a dedicated multispectral vision system. A genetic algorithm (GA) approach was applied on hyperspectral transmittance images (580–980 nm) and reflectance spectral data (590–1,550 nm) acquired from both intact and infested tart cherries. The GA analysis indicates that the ability of using transmittance imaging approach for detecting internal insect infestation in tart cherries would be limited. According to the GA analysis on the reflectance spectra, visible wavelengths were of less importance than NIR wavelengths for the purpose of distinguishing intact cherries from infested ones. The PLSDA results indicate that models built with three or four GA selected wavelength regions gave similar classification accuracy to the model built with full wavelength region, which demonstrates the efficiency of the GA variable selection procedure. However, due to the stochastic nature of the GA, the efficiency of using these wavebands in a multispectral vision system needs to be verified in future work.     

Rapid and real-time prediction of lactic acid bacteria (LAB) in farmed salmon flesh using near-infrared (NIR) hyperspectral imaging combined with chemometric analysis

In this study, hyperspectral imaging working in near-infrared (NIR) region (900–1700 nm) was applied to evaluate surface lactic acid bacteria (LAB) spoilage of farmed salmon flesh during cold storage. Hyperspectral images of salmon samples were acquired at different storage times. Spectral information within regions of interest (ROIs) of images were extracted to relate to reference LAB values measured by standard pour plate method. Least-squares support vector machine (LS-SVM) algorithm was used to calibrate the full NIR range spectral data, resulting in regression coefficients of prediction (R_P) of 0.929 with root mean square error of prediction (RMSEP) of 0.515. Competitive adaptive reweighted sampling (CARS) algorithm was employed to reduce the spectral redundancy and identify the most informative wavelengths (MIWs) most related with LAB prediction across the whole wavelength range. Eight individual MIWs at 1155 nm, 1255 nm, 1373 nm, 1376 nm, 1436 nm, 1641 nm, 1665 nm and 1689 nm were finally selected from the full 239 wavelengths. Based on the selected MIWs, a new optimised model named CARS-LS-SVM was established, leading to R_P of 0.925 with RMSEP of 0.531. At last, the CARS-LS-SVM model was transferred to each pixel of hyperspectral images of samples and colour maps were generated for visualising the LAB spoilage process in salmon flesh. The overall results indicated that NIR hyperspectral imaging is very potential and could be used as a rapid, non-destructive and efficient technique for LAB evaluation in salmon flesh.     

基于高光谱信息特征选择的玉米霉变程度Fisher鉴别方法

为了提高高光谱鉴别玉米霉变程度的正确率,分别对全波长和特征波长下霉变玉米进行鉴别分析。利用高光谱图像采集系统获得250个霉变玉米样本的高光谱数据,并用标准正态变量变换(standard normal variate,SNV)和多元散射校正(Multiplicative scatter correction,MSC)2种方法对原始数据进行预处理,再对未预处理和预处理后的原始数据进行判别,优选出多元散射校正的预处理方法;运用偏最小二乘回归系数选择了9个特征波长;运用Fisher判别分析(Fisher discriminant analysis,FDA)分别对全波长和特征波长下的训练集进行判别分析,并用对应的测试集进行检验。FDA结果表明,全波长下判别模型的训练集和测试集的准确率分别为97.71%,97.33%,9个特征波长下训练集和测试集的准确率分别为100.00%,98.67%。研究结果表明,利用特征光谱能够较好地表征玉米的霉变程度,有利于提高玉米霉变程度的鉴别正确率。     

Application of Visible and Near-Infrared Hyperspectral Imaging for Detection of Defective Features in Loquat

The intent of present work was to develop a valid method for detection of defective features in loquat fruits based on hyperspectral imaging. A laboratorial hyperspectral imaging device covering the visible and near-infrared region of 380–1,030 nm was utilized to acquire the loquat hyperspectral images. The corresponding spectral data were extracted from the region of interests of loquat hyperspectral images. The dummy grades were assigned to the defective and normal group of loquats, separately. Competitive adaptive reweighted sampling (CARS) was conducted to elect optimal sensitive wavelengths (SWs) which carried the most important spectral information on identifying defective and normal samples. As a result, 12 SWs at 433, 469, 519, 555, 575, 619, 899, 912, 938, 945, 970, and 998 nm were selected, respectively. Then, the partial least squares discriminant analysis (PLS-DA) model was established using the selected SWs. The results demonstrated that the CARS-PLS-DA model with the discrimination accuracy of 98.51 % had a capability of classifying two groups of loquats. Based on the characteristics of image information, minimum noise fraction (MNF) rotation was implemented on the hyperspectral images at SWs. Finally, an effective approach for detecting the defective features was exploited based on the images of MNF bands with “region growing” algorithm. For all investigated loquat samples, the developed program led to an overall detection accuracy of 92.3 %. The research revealed that the hyperspectral imaging technique is a promising tool for detecting defective features in loquat, which could provide a theoretical reference and basis for designing classification system of fruits in further work.     

基于软X射线与低场核磁检测小麦隐蔽性害虫玉米象

针对小麦内部隐蔽性害虫玉米象(Sitophilus zeamais)难以检出的问题,本文将高清软X射线与低场核磁两种检测技术相结合,通过高清软X射线拍摄的图片,观察玉米象在小麦内部的整个生长周期,提取图片纹理特征,用线性判别分析(linear discriminant analysis,LDA)与二次判别分析(quadratic discriminant analysis,QDA)算法进行分类判别,并对被不同虫态玉米象感染的小麦进行低场核磁检测。研究结果表明:在12%水分含量小麦中,玉米象的生长周期大约为36 d,LDA与QDA模型对未感染小麦与不同感染阶段小麦进行单独分类判别时,准确率都达到了95%以上,对卵期以及幼虫具有较高的分类准确率。根据小麦被玉米象感染后特征峰值比例P2b与P22的变化,可以用来作为小麦是否受玉米象感染定性判断的依据。