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

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

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

Detection of fungal infection and Ochratoxin A contamination in stored barley using near-infrared hyperspectral imaging

Near-Infrared hyperspectral imaging system is a promising technique to detect various quality parameters associated with cereals and oilseeds. NIR hyperspectral imaging system can collect both spectral and spatial information of any given object and it can detect chemical constituents of food products, therefore it is also called chemical imaging. The image data obtained from hyperspectral imaging system are in the hypercube form, two spatial dimensions and the third spectral dimension. The image data in the hypercube form cannot be directly used for identification and classification, so the three dimensional data are transformed into two dimensional data using automatic thresholding, labelling and reshaping. The transformed two dimensional data subjected to principal component analysis provide significant wavelengths. Statistical features and histogram features extracted from the significant wavelengths are used in the statistical classification models. Fungal infection and mycotoxin contamination in food products disturb the original chemical composition of food products. The NIR hyperspectral imaging or chemical imaging has the potential to detect the chemical changes occurring in the sample. The NIR hyperspectral imaging system has the potential to detect fungal infection and mycotoxin contamination in food products.

Background and Aims: Detecting detailed atherosclerotic plaques is important to reduce risk factors during vascular surgery. However, there are few methods to evaluate them during surgery. The aim of this study was to establish an in vivo, non-contact, and label-free imaging method for identifying atherosclerotic plaque lesions from outside vessels with a diffuse-reflectance near-infrared (NIR) hyperspectral imaging (HSI) system. Method: NIR spectra between 1000 and 2350 nm were measured using an NIR HSI imaging system outside the exposed abdominal aorta in 5 Watanabe Heritable Hyperlipidemic (WHHL) rabbits in vivo. Preprocessed data were input to a supervised machine learning algorithm called a support vector machine (SVM) to create pixel-based images that can predict atherosclerotic plaques within a vessel. The images were compared with histological findings. Result: Absorbance was significantly higher in plaques than in normal arteries at 1000-1380, 1580-1810, and 1880-2320 nm. Overall predictive performance showed a sensitivity of 0.814 ± 0.017, a specificity of 0.836 ± 0.020, and an accuracy of 0.827 ± 0.008. The area under the receiver operating characteristic curve was 0.905 (95% confidence interval = 0.904-0.906). Conclusion: The NIR HSI system combined with a machine learning algorithm enabled accurate detection of atherosclerotic plaques within an internal vessel with high spatial resolution from outside the vessel. The findings indicate that the NIR HSI system can provide non-contact, label-free, and precise localization of atherosclerotic plaques during vascular surgery.

A nondestructive and rapid method using near-infrared (NIR) hyperspectral imaging was investigated to determine the spatial distribution of fat and moisture in Atlantic salmon fillets. Altogether, 100 samples were studied, cutting out from different parts of five whole fillets. For each sample, the hyperspectral image was collected with a pushbroom NIR (899–1,694 nm) hyperspectral imaging system followed by chemical analysis to measure its reference fat and moisture contents. Mean spectrum were extracted from the region of interest inside each hyperspectral image. The quantitative relationships between spectral data and the reference chemical values were successfully developed based on partial least squares (PLS) regression with correlation coefficient of prediction of 0.93 and 0.94, and root mean square error of prediction of 1.24 and 1.06 for fat and moisture, respectively. Then the PLS models were applied pixel-wise to the hyperspectral images of the prediction samples to produce chemical images for visualizing fat and moisture distribution. The results were promising and demonstrated the potential of this technique to predict constituent distribution in salmon fillets.

Near-infrared (NIR) hyperspectral imaging was used to detect the presence of fungal infection in stored canola. Artificially fungal infected (Aspergillus glaucus group) canola was subjected to single kernel imaging every two weeks after incubation using an NIR imaging system in the wavelength range of 1000 to 1600 nm at 60 evenly distributed wavelengths. Three wavelengths 1100, 1230 and 1300 nm were identified as significant wavelengths and used in the analysis. Statistical discriminant classifiers (Linear and Quadratic) were used to classify healthy, two–, four–, six–, eight–, and ten–week fungal incubated samples. The linear and quadratic statistical classifiers gave maximum accuracy of 99% for healthy samples and 100% for fungal infected samples at later stages of infection levels and 90 to 95% for the first four weeks of A. glaucus infected samples.

In vivo detection of atherosclerotic plaque using non-contact and label-free near-infrared hyperspectral imaging

Detection of cucumber green mottle mosaic virus-infected watermelon seeds using a near-infrared (NIR) hyperspectral imaging system: Application to seeds of the “Sambok Honey” cultivar

A near-infrared (NIR) hyperspectral imaging system was developed in this study. NIR hyperspectral imaging combined with multivariate data analysis was applied to identify rice seed cultivars. Spectral data was exacted from hyperspectral images. Along with Partial Least Squares Discriminant Analysis (PLS-DA), Soft Independent Modeling of Class Analogy (SIMCA), K-Nearest Neighbor Algorithm (KNN) and Support Vector Machine (SVM), a novel machine learning algorithm called Random Forest (RF) was applied in this study. Spectra from 1,039 nm to 1,612 nm were used as full spectra to build classification models. PLS-DA and KNN models obtained over 80% classification accuracy, and SIMCA, SVM and RF models obtained 100% classification accuracy in both the calibration and prediction set. Twelve optimal wavelengths were selected by weighted regression coefficients of the PLS-DA model. Based on optimal wavelengths, PLS-DA, KNN, SVM and RF models were built. All optimal wavelengths-based models (except PLS-DA) produced classification rates over 80%. The performances of full spectra-based models were better than optimal wavelengths-based models. The overall results indicated that hyperspectral imaging could be used for rice seed cultivar identification, and RF is an effective classification technique.

In recent years, near-infrared (NIR) hyperspectral imaging has proved its suitability for quality and safety control in the cereal sector by allowing spectroscopic images to be collected at single-kernel level, which is of great interest to cereal control laboratories. Contaminants in cereals include, inter alia, impurities such as straw, grains from other crops, and insects, as well as undesirable substances such as ergot (sclerotium of Claviceps purpurea). For the cereal sector, the presence of ergot creates a high toxicity risk for animals and humans because of its alkaloid content. A study was undertaken, in which a complete procedure for detecting ergot bodies in cereals was developed, based on their NIR spectral characteristics. These were used to build relevant decision rules based on chemometric tools and on the morphological information obtained from the NIR images. The study sought to transfer this procedure from a pilot online NIR hyperspectral imaging system at laboratory level to a NIR hyperspectral imaging system at industrial level and to validate the latter. All the analyses performed showed that the results obtained using both NIR hyperspectral imaging cameras were quite stable and repeatable. In addition, a correlation higher than 0.94 was obtained between the predicted values obtained by NIR hyperspectral imaging and those supplied by the stereo-microscopic method which is the reference method. The validation of the transferred protocol on blind samples showed that the method could identify and quantify ergot contamination, demonstrating the transferability of the method. These results were obtained on samples with an ergot concentration of 0.02% which is less than the EC limit for cereals (intervention grains) destined for humans fixed at 0.05%.

Quantitative analysis of melamine in milk powders using near-infrared hyperspectral imaging and band ratio

This paper presents a study that was performed for rapid and noninvasive detection of waxed chestnuts using hyper-spectral imaging. A visual near-infrared (400–1026 nm) hyper-spectral imaging system was assembled to acquire scattering images from two groups of chestnuts (waxed and non-waxed chestnuts). The spectra of the samples were extracted from the hyper-spectral images using image segmentation process. Then multiplicative scatter correction (MSC) was conducted to preprocess the original spectra. Effective wavelengths were selected to reduce the computational burden of the hyper-spectral data. Using the seven effective wavelengths that were obtained from a successive projections algorithm (SPA), three calibration algorithms were compared: partial least squares regression (PLSR), multiple linear regression (MLR) and linear discriminant analysis (LDA). The best model for discriminating between waxed and non-waxed chestnuts was found to be the MSC-SPA-MLR model.

Detection of ochratoxin A contamination in stored wheat using near-infrared hyperspectral imaging

Pineapples are a popular tropical fruit with economic value, and determining the optimum ripeness of pineapples to assess their quality is crucial for harvesting, marketing, production, and processing. In this study, spectral information and soluble solid content (SSC) of pineapple ripening stages (unripe, ripe, and overripe) were analyzed by 400-1000 nm hyperspectral imaging (HSI) in order to determine the best classification model of pineapple ripening. Four different preprocessing methods, i.e., standard normal variate (SNV), multiplicative scatter correction (MSC), normalization, and Savitzky-Golay (SG) smoothing, in combination with successive projection algorithms (SPA), and bootstrapping soft shrinkage (BOSS) for feature wavelength extraction, were used to compare the full wavelength and the two types of feature extraction support vector machine (SVM), extreme learning machine (ELM), K-nearest neighbors (KNN), and random forest (RF), four supervised machine learning classifiers for maturity classification. For pineapple ripeness classification, SNV preprocessing RF showed the best results with 94.44% accuracy at both full wavelength and 28 wavelengths selected in SPA. A total of 33 wavelengths selected from BOSS achieved a test accuracy of 97.22% by RF. These results demonstrate the potential of near-infrared hyperspectral imaging (NIR-HSI) as a non-destructive, fast, and correct tool for pineapple ripeness identification. The method can be applied to classify and grade marketed pineapple fruits to address pineapple quality issues related to uneven ripeness. The visible and near-infrared hyperspectral imaging (VIS-NIR-HSI) system combining machine learning and wavelength selection successfully classified pineapple ripening stages, an approach that could improve the ability to classify pineapples at the ripening stage in large packaging companies. In addition, finding key wavelengths or features that can be classified corresponding to pineapple ripening stages has the advantage of developing a low-cost, fast, and effective multispectral imaging system compared to the NIR-HSI system.