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 fungal infection and Ochratoxin A contamination in stored wheat using near-infrared hyperspectral imaging

A study was done to detect Aspergillus glaucus, and Penicillium spp., infection and Ochratoxin A contamination in stored wheat using a Near-Infrared (NIR) Hyperspectral Imaging system. Fungal-infected samples were imaged every two weeks, and the three dimensional hypercubes obtained from image data were transformed into two dimensional data. Principal component analysis was applied to the two dimensional data and based on the highest factor loadings, 1280, 1300, and 1350 nm were identified as significant wavelengths. Six statistical features and ten histogram features corresponding to the significant wavelengths were extracted and subjected to linear, quadratic and Mahalanobis discriminant classifiers. All the three classifiers differentiated healthy kernels from fungal-infected kernels with a classification accuracy of more than 90%. The quadratic discriminant classifier provided classification accuracy higher than the linear and Mahalanobis classifiers for pair-wise, two-way and six-way classification models. The Ochratoxin A contaminated samples had a unique significant wavelength at 1480 nm in addition to the two significant wavelengths corresponding to fungal infection. The peak at 1480 nm was identified only in the Ochratoxin A contaminated samples. The Ochratoxin A contaminated samples can be detected with 100% classification accuracy using NIR hyperspectral imaging system. The NIR hyperspectral system can differentiate between different fungal infection stages and different levels of Ochratoxin A contamination in stored wheat.     

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.     

Thermal imaging for detecting fungal infection in stored wheat

The feasibility of using an infrared thermal imaging system to identify the fungal infection in stored wheat was studied. Thermal images of bulk wheat grains infected by Aspergillus glaucus group, Aspergillus niger van Tieghem and Penicillium spp. were obtained using an un-cooled focal planar array type infrared thermal camera after heating grain for 180 s with a plate heater placed 10 mm above the grain and maintained at 90 °C, and then cooling in ambient air for 30 s. In total, twelve temperature features were derived from heated and cooled wheat and four-way and pair-wise classification models were developed by linear and quadratic discriminant analyses (LDA and QDA). Leave-one-out and bootstrapping methods were used to validate the developed classification models. Pair-wise LDA and QDA classification models gave a maximum accuracy of 100% for healthy samples and more than 97% and 96% for infected samples, respectively. Four-way LDA and QDA classification models yielded relatively low classification accuracies for fungus-infected samples due to the non-significant changes in the temperature features between grain samples infected with different species of fungi.     

Prediction of firmness and soluble solids content of blueberries using hyperspectral reflectance imaging

Currently, blueberries are inspected and sorted by color, size and/or firmness (or softness) in packing houses, using different inspection techniques like machine vision and mechanical vibration or impact. A new inspection technique is needed for effectively assessing both external features and internal quality attributes of individual blueberries. This paper reports on the use of hyperspectral imaging technique for predicting the firmness and soluble solids content (SSC) of blueberries. A pushbroom hyperspectral imaging system was used to acquire hyperspectral reflectance images from 302 blueberries in two fruit orientations (i.e., stem and calyx ends) for the spectral region of 500–1000 nm. Mean spectra were extracted from the regions of interest for the hyperspectral images of each blueberry. Prediction models were developed based on partial least squares method using cross validation and were externally tested with 25% of the samples. Better firmness predictions (R = 0.87) were obtained, compared to SSC predictions (R = 0.79). Fruit orientation had no or insignificant effect on the firmness and SSC predictions. Further analysis showed that blueberries could be sorted into two classes of firmness. This research has demonstrated the feasibility of implementing hyperspectral imaging technique for sorting blueberries for firmness and possibly SSC to enhance the product quality and marketability.     

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 %.     

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.     

加工番茄虫眼及霉变的可见近红外高光谱成像检测

为了探求一种快速有效识别虫眼和霉变加工番茄的无损检测方法,利用高光谱成像技术,从光谱和图像2个角度对其进行检测。先借助可见近红外高光谱成像系统获取408~1 013nm的加工番茄高光谱图像数据,提取并分析感兴趣区域的平均光谱曲线进行主成分分析,根据各波段权重系数优选了550,750,900nm 3个特征波长;然后通过特征波长下图像的主成分分析,选择缺陷部位与正常区域强度对照最明显的第一主成分图像,通过掩模、阈值处理和形态学开运算等图像处理方法对缺陷番茄进行检测判别。虫眼、霉变和正常三类番茄的识别率分别为93.3%,90%,100%。同时利用上述3个特征波长进行波段比图像运算,并选择波段比550nm/750nm图像进行缺陷识别,虫眼、霉变和正常三类加工番茄的识别率分别为93.3%,96.7%,100%。研究结果表明,二次主成分分析和波段比检测算法均可以有效地识别缺陷加工番茄。另外研究中仅选用了3个特征波段,数据量大大减少,为搭建开发适于加工番茄缺陷的多光谱在线检测系统提供了可能。     

高光谱成像技术在谷物品质检测中的应用进展

高光谱成像(Hyperspectral imaging,HSI)技术作为一种无损和快速的光学成像分析技术在谷物品质的无损检测应用广泛。本文简述了高光谱成像的基本原理、光谱信息数据处理方法,综述了HSI技术在小麦、玉米、稻谷3种大宗谷物中化学成分检测、品种鉴别、种子活力检测以及不完善籽粒检测等近五年的应用研究进展,提出HSI技术在谷物品质检测实际应用中需破解的难题。     

基于高光谱成像技术的灵武长枣常见缺陷检测

以灵武长枣为研究对象,利用高光谱成像技术结合主成分分析法(principal component analysis,PCA)和最小噪声分离法(minimum noise fraction,MNF)对长枣缺陷进行快速检测与识别,主要探讨样本背景对缺陷识别的影响。首先,采集虫眼、裂痕、正常枣的高光谱图像,利用PCA法和MNF法分别对其降维去噪,选择虫眼与正常枣的PC1和M1图像、裂痕枣的PC2和M2图像进行缺陷识别,经PCA分析后的缺陷识别率均为100%,MNF处理后的识别率分别为69.2%,56.8%,100%;随后对其高光谱图像进行掩模去背景,再对其降维去噪后检测识别,PCA后的识别率均为100%,MNF后的识别率分别为73.1%,65.9%,100%。结果表明:利用高光谱成像技术结合两种降维去噪法对长枣常见缺陷的识别是可行的,背景干扰对于PCA法的缺陷识别不影响,其识别效果优于MNF法,且去背景后的MNF法缺陷识别率较未去背景的有所提高,为后续长枣缺陷的在线检测提供理论依据。     

Prediction of optimal cooking time for boiled potatoes by hyperspectral imaging

Cooking of potatoes causes changes in the microstructure and composition of starch. These changes affect the interaction of light with the starch granules at different regions inside the potato. In this research, the potential of hyperspectral imaging in the wavelength range 400-1000 nm in combination with chemometric tools and image processing for contactless detection of the cooking front in potatoes has been investigated. Partial least squares discriminant analysis (PLSDA) was employed to discriminate between the pixel spectra for the cooked regions and those for the remaining raw regions. In a next step image processing techniques were applied to detect the cooking front in the images obtained by the PLSDA pixel classification. From each of the resulting images with detected cooking fronts, the ratio of the remaining raw part area over the total potato area was then calculated. Finally, the effect of the cooking time on this ratio was modeled to be able to predict the optimal cooking time. The results illustrate the potential of hyperspectral imaging as a process monitoring tool for the potato processing industry.     

Detection of melamine in milk powder using MCT-based short-wave infrared hyperspectral imaging system

Extensive research has been conducted on non-destructive and rapid detection of melamine in powdered foods in the last decade. While Raman and near-infrared hyperspectral imaging techniques have been successful in terms of non-destructive and rapid measurement, they have limitations with respect to measurement time and detection capability, respectively. Therefore, the objective of this study was to develop a mercury cadmium telluride (MCT)-based short-wave infrared (SWIR) hyperspectral imaging system and algorithm to detect melamine quantitatively in milk powder. The SWIR hyperspectral imaging system consisted of a custom-designed illumination system, a SWIR hyperspectral camera, a data acquisition module and a sample transfer table. SWIR hyperspectral images were obtained for melamine-milk samples with different melamine concentrations, pure melamine and pure milk powder. Analysis of variance and the partial least squares regression method over the 1000–2500 nm wavelength region were used to develop an optimal model for detection. The results showed that a melamine concentration as low as 50 ppm in melamine-milk powder samples could be detected. Thus, the MCT-based SWIR hyperspectral imaging system has the potential for quantitative and qualitative detection of adulterants in powder samples.     

基于图像处理和BP网络的烟包印刷质量检测

为解决烟包印刷质量在线检测问题,本文提出了一种基于图像处理和BP神经网络的印刷质量检测和诊断方法.利用待测印刷图像和标准模版图像间差异的特征参数,BP神经网络可将印刷品分成优秀、合格以及不合格三类.实验结果表明,现有系统能够满足烟包印刷质量检测的需求,并且能够运用于烟包印刷质量的在线检测中.     

基于高光谱成像技术的金银花霉变检测模型

利用高光谱成像技术,研究一种快速、准确、无损检测金银花霉变程度的方法。通过比较Savitzky-Golay(SG)卷积平滑、多元散射校正(MSC)和SG-MSC 3种预处理方法对偏最小二乘算法(PLS)建模效果的影响,得到SG-MSC为建模最优预处理方法。使用连续投影算法(SPA)和竞争性自适应重加权算法(CARS)选择经预处理后光谱的特征波长,并分别建立偏最小二乘判别(PLS-DA)和最小二乘支持向量机(LS-SVM)的判别分析模型。结果表明,光谱经SG-MSC预处理后,应用CARS提取特征波长并建立LS-SVM判别分析模型为金银花不同霉变程度最优判别模型,其训练集与验证集的正确率均达到100%。利用高光谱成像技术能够快速无损、有效地鉴别金银花霉变程度,并且在特征波长下能实现金银花霉变程度的快速判别分析。     

NIR高光谱成像技术检测冷鲜羊肉嫩度

利用900¹700 nm近红外高光谱成像系统对冷鲜羊肉嫩度进行快速无损检测研究。采集冷鲜羊肉（1⁸ d）表面的高光谱散射图像,提取样本感兴趣区域反射光谱曲线并用剪切力值表征冷鲜羊肉的标准嫩度。以原始光谱、特征区域光谱和Savitzky-Golay卷积平滑预处理光谱建立冷鲜羊肉嫩度的偏最小二乘回归（PLSR）模型,预处理的特征区域光谱建立的模型效果更优。结果表明:特征区域光谱可有效替代全波段光谱,经过S-G卷积平滑预处理后,模型预测效果最佳,预测相关系数（Rp）和均方根误差（RMSEP）分别为0.773和1.060。研究表明:利用近红外高光谱成像技术结合偏最小二乘回归法对冷鲜羊肉嫩度的快速无损检测是可行的。      

基于高光谱技术检测苹果外观缺陷

目的 利用高光谱技术检测苹果外观缺陷, 分析主成分分析法和波段比率算法研究高光谱图像的可行性。方法 在400~1100 nm波长范围内获取苹果表面的高光谱图像信息, 用主成分分析法处理高光谱下采集的苹果图像, 选取第三主成分图像进行分析, 作为最后的判别依据。波段比率算法中选取了717 nm和530 nm两个有效波段,将两个波段的图像进行比值运算。717 nm波段的图像进行阈值运算、中值滤波及形态学分析得到二值化掩膜图像, 再与二值化后的比率图像进行布尔运算, 提取缺陷的有效信息。结果 基于主成分分析法, 检测苹果表面缺陷的分级准确率为81.25%, 波段比率算法对苹果表面缺陷的分级准确率为93.75%。结论 利用高光谱成像技术下波段比率算法相对于主成分分成法更适合于实时、在线、快速检测。     

Embedded bone fragment detection in chicken fillets using transmittance image enhancement and hyperspectral reflectance imaging

This paper is concerned with the detection of bone fragments embedded in compressed de-boned skinless chicken breast fillets by enhancing single-band transmittance images generated by back-lighting and exploiting spectral information from hyperspectral reflectance images. Optical imaging of chicken fillets is often dominated by multiple scattering properties of the fillets. Thus, resulting images from multiple scattering are diffused, scattered and low contrast. In this study, a fusion of hyperspectral transmittance and reflectance imaging, which is a non-ionized and non-destructive imaging modality, was investigated as an alternative method to the conventional transmittance X-ray imaging technique which is an ionizing imaging modality. An image formation model, called an illumination–transmittance model, was applied for correcting non-uniform illumination effects so that embedded bones are more easily detectable by a simple segmentation method using a single threshold value. Predicted bones from the segmentation were classified by the nearest neighbor classifier that was trained by the spectral library of mean reflectance of chicken tissues like fat, meat and embedded bones. Experimental results with chicken breast fillets and bone fragments are provided.     

Detection of early bruises in apples using hyperspectral data and thermal imaging

The early detection of bruises in apples was studied using a system that included hyperspectral cameras equipped with sensors working in the visible and near-infrared (400–1000 nm), short wavelength infrared (1000–2500 nm) and thermal imaging camera in mid-wavelength infrared (3500–5000 nm) ranges. The principal components analysis (PCA) and minimum noise fraction (MNF) analyses of the images that were captured in particular ranges made it possible to distinguish between areas with defects in the tissue and the sound ones. The fast Fourier analysis of the image sequences after pulse heating of the fruit surface provided additional information not only about the position of the area of damaged tissue but also about its depth. The comparison of the results obtained with supervised classification methods, including soft independent modelling of class analogy (SIMCA), linear discriminant analysis (LDA) and support vector machines (SVM) confirmed that broad spectrum range (400–5000 nm) of fruit surface imaging can improve the detection of early bruises with varying depths.