Vis-NIR Hyperspectral Imaging Research Articles

Maiolica seen by Vis–NIR hyperspectral imaging spectroscopy: the application of an ultraportable camera at the Museo Nazionale del Bargello

An ultraportable hyperspectral camera operating in the Vis–NIR range (400–1000 nm) was used in this study for the non-invasive analysis of a selection of Italian maiolica wares and sherds from the Museo Nazionale del Bargello in Florence, Italy. The studied objects included authentic archaeological sherds, nineteenth-century forgeries, and ceramics of uncertain origin. The primary aim of this study was to evaluate the efficacy of hyperspectral imaging (HSI) spectroscopy combined with multivariate analysis for examining highly refractive and three-dimensional glazed ceramic artefacts within the constraints of a museum environment, including imperfect lighting conditions. Two data processing pipelines were tested: one based on principal component analysis (PCA) with score plots and the other on spectral angle mapper (SAM) classification obtained through the ENVI Spectral Hourglass Wizard (ENVI-SHW). The analyses enabled the discrimination between original parts and/or restored parts and additions. Among others, a complex assemblage of original sherds, restored parts, and non-ceramic parts was observed in a Renaissance pastiche vase. Furthermore, the method enabled the identification of the various chromophores providing clues on the artistic colour palette. In particular, the identification of chromium in the blue and green glazes of two objects of uncertain chronology suggested that they were not made before the nineteenth century. The acquisition of a larger and more detailed database of HSI data on maiolica glazes is strongly encouraged to improve the applicability of this method in authenticity, art-historical and archaeological studies.

Using VIS-NIR hyperspectral imaging and deep learning for non-destructive high-throughput quantification and visualization of nutrients in wheat grains

Using VIS-NIR hyperspectral imaging and deep learning for non-destructive high-throughput quantification and visualization of nutrients in wheat grains

Rapid non-destructive monitoring and quality assessment of the fumigation process of Shanxi aged vinegar based on Vis-NIR hyperspectral imaging combined with multiple chemometric algorithms

The quality of the grains during the fumigation process can significantly affect the flavour and nutritional value of Shanxi aged vinegar (SAV). Hyperspectral imaging (HSI) was used to monitor the extent of fumigated grains, and it was combined with chemometrics to quantitatively predict three key physicochemical constituents: moisture content (MC), total acid (TA) and amino acid nitrogen (AAN). The noise reduction effects of five spectral preprocessing methods were compared, followed by the screening of optimal wavelengths using competitive adaptive reweighted sampling. Support vector machine classification was employed to establish a model for discriminating fumigated grains, and the best recognition accuracy reached 100%. Furthermore, the results of partial least squares regression slightly outperformed support vector machine regression, with correlation coefficient for prediction (Rp) of 0.9697, 0.9716, and 0.9098 for MC, TA, and AAN, respectively. The study demonstrates that HSI can be employed for rapid non-destructive monitoring and quality assessment of the fumigation process in SAV.

Time and spatially resolved VIS-NIR hyperspectral imaging as a novel monitoring tool for laser-based spectroscopy to mitigate radiation damage on paintings.

The increased adoption of non-invasive laser-based techniques for analysis of cultural assets has recently called into question the non-invasiveness of the techniques in practical operation. The methods to assess the occurrence of radiation-induced alteration on paintings are very limited and none of them can predict damage. Here we present a novel multimodal imaging approach to understand the time and spatial evolution and types of laser-induced surface alterations, through simultaneous monitoring using visible and near infrared (VIS-NIR) reflectance hyperspectral imaging (HSI) and thermal imaging during Raman spectroscopy. The resultant physical and chemical changes were examined in detail by optical coherence tomography and synchrotron based micro-X-ray powder diffraction. HSI was found to be the most sensitive in detecting laser induced alternations compared with conventional methods. It is orders of magnitude more sensitive than Raman spectroscopy and even synchrotron-based micro-X-ray powder diffraction. In cases of thermally driven alterations, transient and reversible reflectance changes were found to be the first indications of laser-induced modifications and can therefore be used as precursors to prevent damage. VIS-NIR reflectance spectroscopy should be used to monitor laser-based analysis and potentially other radiation-based techniques in situ to mitigate laser induced alteration.

A new comprehensive quantitative index for the assessment of essential amino acid quality in beef using Vis-NIR hyperspectral imaging combined with LSTM

The quality of beef is usually predicted by measuring a single index rather than a comprehensive index. To precisely determine the essential amino acid (EAA) contents in 360 beef samples, the feasibility of optimized spectral detection techniques based on the comprehensive EAA index (CEI) and comprehensive weight index (CWI) constructed by factor analysis was explored. Two-dimensional correlation spectroscopy (2D-COS) was used to analyse the mechanisms of spectral peak shifts in complex disturbance systems with CEI and CWI contents, and 15 sensitive feature variables were extracted to establish a quantitative analysis model of a long short-term memory network (LSTM). The results indicated that 2D-COS had good predictive performance in both CEI-LSTM (R2P of 0.9095 and RPD of 2.76) and CWI-LSTM (R2P of 0.8449 and RPD of 2.45), which reduced data information by 88%. This indicates that utilizing 2D-COS can eliminate collinearity and redundant information among variables while achieving data dimensionality reduction and simplification of calibration models. Furthermore, a spatial distribution map of the comprehensive EAA content was generated by combining the optimal prediction model. This study demonstrated that the comprehensive index method furnishes a new approach to rapidly evaluate EAA content.

Generalized and hetero two-dimensional correlation analysis of hyperspectral imaging combined with three-dimensional convolutional neural network for evaluating lipid oxidation in pork

Lipid oxidation is the main cause of meat deterioration. Hyperspectral imaging (HSI) technique has attracted attention as a non-destructive testing method. However, the complexity and overlap of the pork hyperspectral data lead to difficult band interpretation and computational overload. In this paper, a lightweight three-dimensional convolutional neural network (3D-CNN) model combined with two-dimensional correlation spectroscopy (2D-COS) analysis was proposed to monitor the lipid oxidation of frozen pork. Through the generalized 2D-COS analysis, the band interpretation of visible near-infrared (vis-NIR) HSI was established and the sequence of event changes caused by pork deterioration was monitored. It was found that sulfmyoglobin and oxymyoglobin were prone to change, and the decomposition of sulfmyoglobin and metmyoglobin occurred before the formation of oxymyoglobin. Moreover, the hetero 2D-COS analysis was used for the first time to correlate vis-NIR with fluorescence spectra to analyze more feature bands of vis-NIR HSI. A lightweight 3D-CNN regression model was developed for hyperspectral images of feature bands to quantitatively predict TBARS. It was found that 10 feature bands were obtained by integrating bands identified by generalized and hetero 2D-COS. The 3D-CNN model of these feature bands has yielded good results in predicting TBARS with R2p of 0.9214 and RMSEP of 0.0364 mg kg−1. Overall, this study provided a method for band assignment and interpretation of vis-NIR HSI and an end-to-end new approach for rapid and non-destructive monitoring of pork oxidative damage.

New model for the automatic detection of anthracnose in mango fruits based on Vis/NIR hyperspectral imaging and discriminant analysis

Anthracnose is one of the most relevant diseases of mango crops in producing regions, affecting 60% of production. Currently, its detection is carried out in late stages by human visual inspection. Hyperspectral imaging systems allow the development of non-destructive solutions to inspect and detect internal damage. This work aimed to develop a system for detecting anthracnose in mango fruits using Vis–NIR hyperspectral imaging and discriminant analysis. The usefulness of three-dimensionality reduction methods to minimise redundancy in the spectral data and to obtain a compact number of wavelengths that effectively allow the detection of anthracnose symptoms in mango fruits is also explored. As a result, a classification model based on discriminant analysis and Pearson correlation coefficient was obtained, showing the potential of hyperspectral data to robustly allow the detection of anthracnose symptoms with full or reduced spectra. The findings reported in this study can serve as the basis for developing an anthracnose detection system in mango fruits with multispectral cameras.

Application of VIS-NIR Hyperspectral Imaging to the Detection and Quantification of MPs in Simulant Shellfish

As the world has become increasingly reliant on single-use plastics, plastic litter has increased exponentially, especially in marine ecosystems. One type of plastic litter affecting marine life is microplastics, which are plastics under 5mm in diameter. Microplastics are consumed by marine animals, which are then consumed by people. Study of the environmental and human health effects of these microplastics has proven difficult, in part due to difficulty detecting and quantifying microplastics. This study aims to detect microplastics in shellfish by utilizing the nondestructive method of hyperspectral imaging as an indicator of both marine ecosystem health and food quality. Gelatin models of shellfish were injected with a known concentration of microplastics (polyvinyl chloride (PVC) and polystyrene (PS), specifically). The hyperspectral camera then took 3-dimensional images of the models, with the wavelength dimension ranging from 400 nm to 1000 nm. Next, an algorithm called Partial Least Squares Regression Analysis was developed to analyze the relationship between the wavelengths and the amount of plastic in the sample. Preliminary results have shown slight variation in reflectance spectra between models spiked with microplastics and control models past the 950 nm range. Therefore, hyperspectral imaging might be a viable tool to detect and quantify microplastics in shellfish, but the range of the camera used in this study is a limitation.

The Automated Detection of Fusarium Wilt on Phalaenopsis Using VIS-NIR and SWIR Hyperspectral Imaging

Phalaenopsis, an essential flower for export, is significantly affected by fusarium wilt, which impacts its export quality. Hyperspectral imaging technology offers the potential to detect fusarium wilt on Phalaenopsis. The goal of this study was to establish an automated platform for the rapid detection of fusarium wilt on Phalaenopsis. In this research, the automatic target generation process (ATGP) method was employed to identify outliers in the hyperspectral spectrum. Subsequently, the Spectral Angle Mapper (SAM) method was utilized to detect signals similar to the outliers. To suppress background noise and extract the region of interest (ROI), the Constrained Energy Minimization (CEM) method was implemented. For ROI classification and detection, a deep neural network (DNN), a support vector machine (SVM), and a Random Forest Classifier (RFC) were employed. Model performance was evaluated using three-dimensional receiver operating characteristics (3D ROC), and the automated identification system was integrated into hyperspectrometers. The proposed system achieved an accuracy of 95.77% with a total detection time of 3380 ms ± 86.36 ms, proving to be a practical and effective tool for detecting fusarium wilt on Phalaenopsis in the industry.

Study of light penetration depth of a Vis-NIR hyperspectral imaging system for the assessment of fruit quality. A case study in persimmon fruit

Hyperspectral imaging (HSI) is one of the most studied optical techniques to estimate the internal quality of fruits and vegetables. Absorbance and reflectance of the light radiation are specific to each biological tissue and are directly related to its chemical composition and physical characteristics. These properties are influenced by other extrinsic factors, such as the instrumentation or the light source, which can reduce the reproducibility of the experiments. Determining the actual depth of light penetration into tissue could help validate non-contact methods as accurate tools to assess quality properties based on optical properties. In the case of HSI systems, it is crucial to know how far the light penetrates at each wavelength. A non-destructive approach, based on the spatially resolved spectroscopic principle, was proposed to estimate the light penetration depth of a HSI system in a Vis-NIR configuration (in the range 450–1050 nm). This method was applied to measure the light penetration depth in persimmon fruit. The absorption (μa) and scattering (μ's) coefficients from Farrell's diffusion theory were estimated using the backscattered light measured at different distances from the incident point light at each wavelength in hyperspectral images of persimmon fruit. The actual light penetration depth was obtained by measuring the reflectance of cut pieces of persimmon fruit with different thicknesses. Linear regression was used to relate the depth of penetrability obtained by both protocols, the estimated or non-destructive protocol and the actual or destructive protocol, showing a high relationship (R2 > 0.8 and RPD>2.5) in the range 610–1050 nm. This confirms that this non-destructive approach proposed for estimating the light penetration depth of a Vis-NIR HSI system in persimmon fruit is accurate, so it could be used as a valuable method to evaluate other HSI systems for different fruits.

Nondestructive detection of lipid oxidation in frozen pork using hyperspectral imaging technology

Lipid oxidation is an important cause of pork quality degradation during freezing. Traditional chemical methods are time-consuming and destructive. In this paper, two hyperspectral imaging (HSI) techniques, including visible near-infrared (vis-NIR HSI) (400–1002 nm) and fluorescence (F-HSI) (400–1002 nm), were tested for non-destructive detection of lipid oxidation in pork. Two types of hyperspectral image data were collected from pork samples with 0–9 freeze-thaw cycles. The model performance based on the two spectra data was then tested by three multivariate analysis methods of partial least squares regression, support vector regression and Gaussian process regression (GPR). It was found that the GPR models using vis-NIR HSI and F-HSI acquired optimal prediction results of R2p = 0.9697, RMSEP= 0.0184 mg/kg and R2p = 0.9726, RMSEP= 0.0182 mg/kg, respectively. The results showed that the two techniques have shown reliable performance in predicting TBARS, and the performance of F-HSI was slightly superior to vis-NIR HSI. A pseudo-color map of TBARS was drawn using the F-HSI model to provide a visual screening method for lipid oxidation in pork. Moreover, another batch of pork with different freeze-thaw cycles (0–5 cycles) was successfully quantified and visualized for TBARS content using the F-HSI model. It demonstrated the feasibility of using F-HSI for quantitative monitoring of lipid oxidation in pork.

Cross-cultivar prediction of quality indicators of tea based on VIS-NIR hyperspectral imaging

The rapid detection of quality indicators of fresh tea leaves is helpful to guide tea garden management. Therefore, it is very important to develop a fast and reliable detection method for fresh tea leaf quality indicators. In this study, the feasibility of visible-near-infrared hyperspectral image (VNHI) combined with stoichiometry for the determination of tea polyphenols (TP) and crude fiber (CF) in 14 cultivars of tea plants was investigated. Based on the VNHI, different tea cultivars were distinguished with an accuracy of 99.56% by using one-dimensional ResNet18 (1D-ResNet18). For the quantitative determination of CF and TP contents, the prediction determination coefficient (r2) reached 0.80 and 0.77, respectively, by integrating VNHI with PLS. In addition, we proposed a generalization index (GI) that can evaluate the cross-cultivar generalization ability of models. The GI can judge if the model built on a few tea cultivars can predict the quality indicators of other cultivars. Then, the predicted distribution maps of CF and TP contents were analyzed. The results showed that the quantitative models based on spectra (474–1734 nm) had higher cross-cultivar generalization ability with higher mean GI_0.7 in predicting the cross-cultivar content of CF (mean GI_0.7 = 2.563) and TP (mean GI_0.7 = 1.376). The models based on spectra (474–1030 nm) had stronger visualization ability with lower mean predictive variance. This study proved the feasibility of the VNHI technique in predicting the content of TP and CF of multiple cultivars of tea plants and provided methods with higher generalization, perceptual intuition, and speediness for the detection of quality indicators of tea in the field.

Comparison of a portable Vis-NIR hyperspectral imaging and a snapscan SWIR hyperspectral imaging for evaluation of meat authenticity.

The performance of visible-near infrared hyperspectral imaging (Vis-NIR-HSI) (400-1000nm) and shortwave infrared hyperspectral imaging (SWIR-HSI) (1116-1670nm) combined with different classification and regression (linear and non-linear) multivariate methods were assessed for meat authentication. In Vis-NIR-HSI, total accuracies in the prediction set for SVM and ANN-BPN (the best classification models) were 96 and 94% surpassing the performance of SWIR-HSI with 88 and 89% accuracy, respectively. In Vis-NIR-HSI, the best-obtained coefficient of determinations for the prediction set (R2p) were 0.99, 0.88, and 0.99 with root mean square error in prediction (RMSEP) of 9, 24 and 4 (%w/w) for pork in beef, pork in lamb and pork in chicken, respectively. In SWIR-HSI, the best-obtained R2p were 0.86, 0.77, and 0.89 with RMSEP of 16, 23 and 15 (%w/w) for pork in beef, pork in lamb and pork in chicken, respectively. The results ascertain that Vis-NIR-HSI coupled with multivariate data analysis has better performance rather than SWIR-HIS.

Vis-NIR and SWIR hyperspectral imaging method to detect bruises in pomegranate fruit.

Fresh pomegranate fruit is susceptible to bruising, a common type of mechanical damage during harvest and at all stages of postharvest handling. Accurate and early detection of such damages in pomegranate fruit plays an important role in fruit grading. This study investigated the detection of bruises in fresh pomegranate fruit using hyperspectral imaging technique. A total of 90 sample of pomegranate fruit were divided into three groups of 30 samples, each representing purposefully induced pre-scanning bruise by dropping samples from 100 cm and 60 cm height on a metal surface. The control has no pre-scanning bruise (no drop). Two hyperspectral imaging setups were examined: visible and near infrared (400 to 1000 nm) and short wavelength infrared (1000 to 2500 nm). Region of interest (ROI) averaged reflectance spectra was implemented to reduce the image data. For all hypercubes a principal components analysis (PCA) based background removal were done prior to segmenting the region of interest (ROI) using the Evince® multi-variate analysis software 2.4.0. Then the average spectrum of the ROI of each sample was computed and transferred to the MATLAB 2022a (The MathWorks, Inc., Mass., USA) for classification. A two-layer feed-forward artificial neural network (ANN) is used for classification. The accuracy of bruise severity classification ranged from 80 to 96.7%. When samples from both bruise severity (Bruise damage induced from a 100cm and 60 cm drop heights respectively) cases were merged, class recognition accuracy were 88.9% and 74.4% for the SWIR and Vis-NIR, respectively. This study implemented the method of selecting out informative bands and disregarding the redundant ones to decreases the data size and dimension. The study developed a more compact classification model by the data dimensionality reduction method. This study demonstrated the potential of using hyperspectral imaging technology in sensing and classification of bruise severity in pomegranate fruit. This work provides the foundation to build a compact and fast multispectral imaging-based device for practical farm and packhouse applications.

A Novel Transmittance Vis–NIR Hyper-Spectral Imaging Scanner for Analysis of Photographic Negatives: A Potential Tool for Photography Conservation

This work illustrates a novel prototype of a transmittance hyperspectral imaging (HSI) scanner, operating in the 400-900 nm range, and designed on purpose for non-invasive analysis of photographic materials, such as negatives, films and slides. The instrument provides high-quality spectral data and high-definition spectral images on targets of small size (e.g., 35 mm film strips) and is the first example of HSI instrumentation specifically designed for applications in the photographic conservation field. The instrument was tested in laboratory and on a set of specimens selected from a damaged photographic archive. This experimentation, though preliminary, demonstrated the soundness of a technical approach based on HSI for large-scale spectroscopic characterization of photographic archival materials. The obtained results encourage the continuation of experimentation of HSI as an advanced tool for photography conservation.

Nontradional Detection of Soil Moisture Content Based On Hyperspectral Imaging Technique

In the study, Vis-NIR hyperspectral imaging technique was investigated for non-destructive determination of soil moisture content. A total of 208 spectral information of soil samples by hyperspectral imaging system were collected. The differences between soil's moisture content and spectral changes were compared. Different methods of spectral data preprocessing methods, characteristic wavelengths extraction, and building models had influences on the performance of model established. Results from this investigation demonstrated that the reflectivity of soil spectrum were declining with the increase of soil moisture content. Once soil moisture content reached the limit of the field water holding capacity, the reflectivity of soil spectrum were increasing with the increase of soil moisture content. The methods of different pretreatment were analyzed, and the pretreatment method of normalization of unit vector was proposed. The number of characteristic wavelengths extracted by the method of uninformative variable eliminate (UVE), competitive adaptive reweighted sampling (CARS), beta coefficient (β), successive projections algorithm (SPA) were 49, 30, 5, 7, respectively. In order to reduce data redundancy, characteristic wavelengths extracted by the method of UVE and CARS were further extracted by SPA method. The number of characteristic wavelengths extracted by the method of UVE + SPA and CARS + SPA were 5, 8, respectively. The MLR model built based on the characteristic wavelengths extracted by the β coefficient was chosen as the best model, which of the optimal characteristic wavelengths were 411, 440, 622, 713, 790 nm, respectively. The correlation coefficient (Rp) and the root mean square error (RMSEP) for prediction set were 0.979 and 0.763, respectively. Therefore, it is feasible to predict soil moisture content using hyperspectral imaging technique. Bangladesh J. Bot. 51(4): 1039-1049, 2022 (December) Special

Study on Black Spot Disease Detection and Pathogenic Process Visualization on Winter Jujubes Using Hyperspectral Imaging System.

In this work, the potential of a hyperspectral imaging (HSI) system for the detection of black spot disease on winter jujubes infected by Alternaria alternata during postharvest storage was investigated. The HSI images were acquired using two systems in the visible and near-infrared (Vis-NIR, 400-1000 nm) and short-wave infrared (SWIR, 1000-2000 nm) spectral regions. Meanwhile, the change of physical (peel color, weight loss) and chemical parameters (soluble solids content, chlorophyll) and the microstructure of winter jujubes during the pathogenic process were measured. The results showed the spectral reflectance of jujubes in both the Vis-NIR and SWIR wavelength ranges presented an overall downtrend during the infection. Partial least squares discriminant models (PLS-DA) based on the HSI spectra in Vis-NIR and SWIR regions of jujubes both gave satisfactory discrimination accuracy for the disease detection, with classification rates of over 92.31% and 91.03%, respectively. Principal component analysis (PCA) was carried out on the HSI images of jujubes to visualize their infected areas during the pathogenic process. The first principal component of the HSI spectra in the Vis-NIR region could highlight the diseased areas of the infected jujubes. Consequently, Vis-NIR HSI and NIR HSI techniques had the potential to detect the black spot disease on winter jujubes during the postharvest storage, and the Vis-NIR HSI spectral information could visualize the diseased areas of jujubes during the pathogenic process.

Non-destructive detection of bruises in pomegranate fruit by Vis-NIR and SWIR hyperspectral imaging

Non-destructive detection of bruises in pomegranate fruit by Vis-NIR and SWIR hyperspectral imaging

Development and comparison of classification models on VIS-NIR hyperspectral imaging spectra for qualitative detection of the Staphylococcus aureus in fresh chicken breast

Chicken is at risk of contaminated foodborne pathogens in the production process. Timely and nondestructive detection of foodborne pathogens in chicken is essential for food security. The study aims to explore the feasibility of developing efficient classification models for qualitative detection of Staphylococcus aureus in chicken breast using the hyperspectral imaging technique. Principal component analysis was used to process the full spectral information and three wavelength selection methods (competitive adaptive reweighted sampling, genetic algorithm, and successive projections algorithm) were applied to extract effective wavelengths. These methods were combined with the support vector machine algorithm to develop conventional classification models, respectively. In addition, a convolutional neural network model based on deep learning was designed and trained for comparison. The performance of the convolutional neural network model was significantly better than that of conventional classification models. The overall accuracy for chicken sample classifications was improved from 83.88% to 91.38%. The results demonstrated that deep learning can effectively extract spectral features and promote the application of hyperspectral imaging in foodborne pathogens detection of chicken products.

Vis-NIR hyperspectral imaging combined with incremental learning for open world maize seed varieties identification

There are many maize seed varieties circulating on the Chinese market, some varieties will be added and eliminated by the government every year, and fake varieties cannot be exhaustively listed. Furthermore, the updating of some varieties requires retraining the entire model, which is time-consuming and laborious. This poses a huge challenge for the authenticity identification of varieties and online model updating. Herein, hyperspectral imaging (HSI) combined with incremental learning (IL) was used to solve this problem. A novel radial basis function-biomimetic pattern recognition (RBF-BPR) model for IL was proposed and compared with one-class support vector machine (OCSVM) and BPR models under two test schemes. Hyperspectral images of five varieties of maize seeds were collected, and convolutional autoencoder (CAE) was used to extract features to remove redundant information and improve the generalization ability of models. A unique hybrid model was designed for each variety respectively, and the IL process was simulated. In two test schemes, the overall correct acceptance rate (CAR) for the known varieties and the overall correct rejection rate (CRR) for the unknown varieties of CAE-RBF-BPR model both reached 100%, which was superior to CAE-OCSVM and CAE-BPR models. Especially after RBF was used to map data, the performance of RBF-BPR model had a qualitative improvement compared with the original BPR model. In summary, the proposed method can realize IL without accessing the old classes data, while meeting the requirements of identifying known varieties and rejecting unknown varieties. In addition, if some varieties are eliminated by the government in the future, the corresponding models can also be removed form the whole system. The combination of such method and HSI has a broad application prospect in the identification of maize seed varieties, thus avoiding the trouble of retraining entire model when some maize seed varieties need to be updated.