Extraction of Spectral Information from Hyperspectral Data and Application of Hyperspectral Imaging for Food and Agricultural Products

A new spectral simulating method based on near-infrared hyperspectral imaging for evaluation of antibiotic mycelia residues in protein feeds

Antibiotic mycelia residues (AMRs) contain antibiotic residues. If AMRs are ingested in excess by livestock, it may cause health problems. To address the current problem of unknown pixel-scale adulteration concentration in NIR-HSI, this paper innovatively proposes a new spectral simulation method for the evaluation of AMRs in protein feeds. Four common protein feeds (soybean meal (SM), distillers dried grains with solubles (DDGS), cottonseed meal (CM), and nucleotide residue (NR)) and oxytetracycline residue (OR) were selected as study materials. The first step of the method is to simulate the spectra of pixels with different adulteration concentrations using a linear mixing model (LMM). Then, a pixel-scale OR quantitative model was developed based on the simulated pixel spectra combined with local PLS based on global PLS scores (LPLS-S) (which solves the problem of nonlinear distribution of the prediction results due to the 0%-100% content of the correction set). Finally, the model was used to quantitatively predict the OR content of each pixel in hyperspectral image. The average value of each pixel was calculated as the OR content of that sample. The implementation of this method can effectively overcome the inability of PLS-DA to achieve qualitative identification of OR in 2%-20% adulterated samples. In compared to the PLS model built by averaging the spectra over the region of interest, this method utilizes the precise information of each pixel, thereby enhancing the accuracy of the detection of adulterated samples. The results demonstrate that the combination of the method of simulated spectroscopy and LPLS-S provides a novel method for the detection and analysis of illegal feed additives by NIR-HSI.

Exploring the potential of hyperspectral imaging for microbial assessment of meat: A review

Food safety is always of paramount importance globally due to the devasting social and economic effects of foodborne disease outbreaks. There is a high consumption rate of meat worldwide, making it an essential protein source in the human diet, hence its microbial safety is of great importance. The food industry stakeholders are always in search of methods that ensure safe food whilst maintaining food quality and excellent sensory attributes. Currently, there are several methods used in microbial food analysis, however, these methods are often time-consuming and do not allow real-time analysis. Considering the recent technological breakthroughs in artificial intelligence and machine learning, it raises the question of whether these advancements could be leveraged within the meat industry to improve turnaround time for microbial assessments. Hyperspectral imaging (HSI) is a highly prospective technology worth exploring for microbial analysis. The rapid, non-destructive method has the potential to be integrated into food production systems and allows foodborne pathogen detection in food samples, thus saving time. Although there has been a substantial increase in research on the utilisation of HSI in food applications over the past years, its use in the microbial assessment of meat is not yet optimal. This review aims to provide a basic understanding of the visible-near infrared HSI system, recent applications in the microbial assessment of meat products, challenges, and possible future applications.

Prediction of freezing point and moisture distribution of beef with dual freeze-thaw cycles using hyperspectral imaging

The freezing point (FP) is an important quality indicator of the superchilled meat. Currently, the potential of hyperspectral imaging (HSI) for predicting beef FP as affected by multiple freeze-thaw (F-T) cycles was explored. Correlation analysis revealed that the FP had a negative correlation with the proportion of bound water (P21) and a positive correlation with the proportion of immobilized water (P22). Moreover, the optimal wavelengths were selected by principal component analysis (PCA). Principal component regression (PCR) and partial least squares regression (PLSR) models were successfully developed based on the optimal wavelengths for predicting FP with determination coefficient in prediction (RP2) of 0.76, 0.76 and root mean square errors in prediction (RMSEP) of 0.12, 0.12, respectively. Additionally, PLSR based on full wavelengths was established for predicting P21 with RP2 of 0.80 and RMSEP of 0.67, and PLSR based on the optimal wavelengths was established for predicting P22 with RP2 of 0.87 and RMSEP of 0.66. The results show the potential of hyperspectral technology to predict the FP and moisture distribution of meat as a nondestructive method.

Feasibility Study of Scanning Spectral Imaging Based on a Birefringence Flat Plate

Hyper-spectral imaging (HSI) systems can be divided into two main types as follows: a group of systems that includes a dedicated dispersion/filtering component whose role is to physically separate the different wavelengths and a group of systems that sample all wavelengths in parallel, so that the separation into wavelengths is performed by signal processing (interferometric method). There is a significant advantage to systems of the second type in terms of the integration time required to obtain a signal with a high signal-to-noise ratio since the signal-to-noise ratio of methods based on scanning interferometry (Windowing method) is better compared to methods based on dispersion. The current research deals with the feasibility study of a new concept for an HSI system that is based on scanning interferometry using the "push-broom" method. In this study, we investigated the viability of incorporating a simple birefringent plate into a scanning optical system. By exploiting the motion of the platform on which the system is mounted, we extracted the spectral information of the scanned region. This approach combines the benefits of scanning interferometry with the simplicity of the setup. According to the theory, a chirped cosine-shaped interferogram is obtained for each wavelength due to the nonlinear behavior of the optical path difference of light in the birefringent plate as a function of the angle. An algorithm converts the signal from a superposition of chirped cosine signals to a scaled interferogram such that Fourier transforming (FT) the interferogram retrieves the spectral information. This innovative idea can turn a simple monochrome camera into a hyperspectral camera by adding a relief lens and a birefringent plate.

High-throughput phenotyping using VIS/NIR spectroscopy in the classification of soybean genotypes for grain yield and industrial traits

Employing visible and near infrared sensors in high-throughput phenotyping provides insight into the relationship between the spectral characteristics of the leaf and the content of grain properties, helping soybean breeders to direct their program towards improving grain traits according to researchers' interests. Our research hypothesis is that the leaf reflectance of soybean genotypes can be directly related to industrial grain traits such as protein and fiber contents. Thus, the objectives of the study were: (i) to classify soybean genotypes according to the grain yield and industrial traits; (ii) to identify the algorithm(s) with the highest accuracy for classifying genotypes using leaf reflectance as model input; (iii) to identify the best input data for the algorithms to improve their performance. A field experiment was carried out in randomized block design with three replications and 32 soybean genotypes. At 60 days after emergence, spectral analysis was carried out on three leaf samples from each plot. A hyperspectral sensor was used to capture reflectance between the wavelengths from 450 to 824 nm. Representative spectral bands were selected and grouped into means. After harvest, grain yield was assessed and laboratory analyses of industrial traits were carried out. Spectral, industrial traits and yield data were subjected to statistical analysis. Data were analyzed by the following machine learning algorithms: J48 (J48) and REPTree (DT) decision trees, Random Forest (RF), Artificial Neural Networks (ANN), Support Vector Machine (SVM), and conventional Logistic Regression (LR) analysis. The clusters formed were used as the output of the models, while two groups of input data were used for the input of the models: the spectral variables (WL) noise-free obtained by the sensor (450-828 nm) and the spectral means of the selected bands (SB) (450.0-720.6 nm). Soybean genotypes were grouped according to their grain yield and industrial traits, in which the SVM and J48 algorithms performed better at classifying them. Using the spectral bands selected in the study improved the classification accuracy of the algorithms.

Enhancing grain drying methods with hyperspectral imaging technology: A visualanalysis

This study proposes a recognition model for different drying methods of grain using hyperspectral imaging technology (HSI) and multivariate analysis. Fresh harvested grain samples were dried using three different methods: rotating ventilation drying, mechanical drying, and natural drying. Hyperspectral images of the samples were collected within the 388-1065 nm band range. The spectral features of the samples were extracted using principal component analysis (PCA), while the texture features were extracted using second-order probability statistical filtering. Partial least squares regression (PLSR) drying models with different characteristics were established. At the same time, a BPNN (Back-propagation neural network, BPNN) based on spectral texture fusion features was established to compare the recognition effects of different models. Texture analysis indicated that the mean-image had the clearest contour, and the texture characteristics of mechanical drying were smaller than those of rotating ventilation drying and natural drying. The BPNN model established using spectral-texture feature variables showed the best performance in distinguishing grain in different drying modes, with a prediction model obtained based on the correlation coefficients of special variables. The spectral and texture feature values were fused for pseudo-color visualization expression, and the three drying methods of grain showed different colors. This study provides a reference for non-destructive and rapid detection of grain with different drying methods.

Quality Characterization of Fava Bean-Fortified Bread Using Hyperspectral Imaging

As the demand for alternative protein sources and nutritional improvement in baked goods grows, integrating legume-based ingredients, such as fava beans, into wheat flour presents an innovative alternative. This study investigates the potential of hyperspectral imaging (HSI) to predict the protein content (short-wave infrared (SWIR) range)) of fava bean-fortified bread and classify them based on their color characteristics (visible-near-infrared (Vis-NIR) range). Different multivariate analysis tools, such as principal component analysis (PCA), partial least square discriminant analysis (PLS-DA), and partial least square regression (PLSR), were utilized to assess the protein distribution and color quality parameters of bread samples. The result of the PLS-DA in the SWIR range yielded a classification accuracy of ˃99%, successfully classifying the samples based on their protein contents (low protein and high protein). The PLSR model showed an RMSEC of 0.086% and an RMSECV of 0.094%. Also, the external validation resulted in an RMSEP of 0.064%. The PLSR model possessed the capability to efficiently predict the protein content of the bread samples. The results suggest that HSI can be successfully used to classify bread samples based on their protein content and for the prediction of protein composition. Hyperspectral imaging can therefore be reliably implemented for the quality monitoring of baked goods in commercial bakeries.

Hyperspectral imaging for estimating leaf, flower, and fruit macronutrient concentrations and predicting strawberry yields

Managing the nutritional status of strawberry plants is critical for optimizing yield. This study evaluated the potential of hyperspectral imaging (400-1,000 nm) to estimate nitrogen (N), phosphorus (P), potassium (K), and calcium (Ca) concentrations in strawberry leaves, flowers, unripe fruit, and ripe fruit and to predict plant yield. Partial least squares regression (PLSR) models were developed to estimate nutrient concentrations. The determination coefficient of prediction (R2P) and ratio of performance to deviation (RPD) were used to evaluate prediction accuracy, which often proved to be greater for leaves, flowers, and unripe fruit than for ripe fruit. The prediction accuracies for N concentration were R2P = 0.64, 0.60, 0.81, and 0.30, and RPD = 1.64, 1.59, 2.64, and 1.31, for leaves, flowers, unripe fruit, and ripe fruit, respectively. Prediction accuracies for Ca concentrations were R2P = 0.70, 0.62, 0.61, and 0.03, and RPD = 1.77, 1.63, 1.60, and 1.15, for the same respective plant parts. Yield and fruit mass only had significant linear relationships with the Difference Vegetation Index (R2 = 0.256 and 0.266, respectively) among the eleven vegetation indices tested. Hyperspectral imaging showed potential for estimating nutrient status in strawberry crops. This technology will assist growers to make rapid nutrient-management decisions, allowing for optimal yield and quality.

Drying and intermittence processes on the polished and brown rice physicochemical and morphological quality by near-infrared spectroscopy, X-ray diffraction, and scanning electron microscopy

In this study was correlate the effects of drying time and intermittence of paddy rice on the physical, physicochemical, and morphological quality of polished and brown rice using near-infrared spectroscopy, X-ray diffraction, and scanning electron microscopy. Rice grain batches from mechanized harvesting with moisture contents between 24 and 20% (w.b.) were immediately subjected to drying and intermittence (average temperature of the grain mass of 40 °C) for a time of 14 h (number of times that the product underwent the drying and intermittence processes). For each drying time, grain sampling was performed to evaluate the physical quality of paddy rice and the physicochemical and morphological quality of polished and brown rice. The accumulated drying time provided an increase in the temperature of the grain mass, altering the physicochemical and morphological quality of polished and brown rice. The intermittence process did not contribute for the quality of the polished rice.

Reviving grain quality in wheat through non-destructive phenotyping techniques like hyperspectral imaging

A long-term goal of breeders and researchers is to develop crop varieties that can resist environmental stressors and produce high yields. However, prioritising yield often compromises improvement of other key traits, including grain quality, which is tedious and time-consuming to measure because of the frequent involvement of destructive phenotyping methods. Recently, non-destructive methods such as hyperspectral imaging (HSI) have gained attention in the food industry for studying wheat grain quality. HSI can quantify variations in individual grains, helping to differentiate high-quality grains from those of low quality. In this review, we discuss the reduction of wheat genetic diversity underlying grain quality traits due to modern breeding, key traits for grain quality, traditional methods for studying grain quality and the application of HSI to study grain quality traits in wheat and its scope in breeding. Our critical review of literature on wheat domestication, grain quality traits and innovative technology introduces approaches that could help improve grain quality in wheat.

Rapid nondestructive detecting of sorghum varieties based on hyperspectral imaging and convolutional neural network

BACKGROUND

The purity of sorghum varieties is an important indicator of the quality of raw materials used in the distillation of liquors. Different varieties of sorghum may be mixed during the acquisition process, which will affect the flavor and quality of liquor. To facilitate the rapid identification of sorghum varieties, this study proposes a sorghum variety identification model using hyperspectral imaging (HSI) technology combined with convolutional neural network (AlexNet).

RESULTS

First, the watershed algorithm, which was modified with the extended-maxim transform, was used to segment the hyperspectral images of a single sorghum grain. The isolated forest algorithm was used to eliminate abnormal spectral data from the complete spectral data. Secondly, the AlexNet model of sorghum variety identification was established based on the two-dimensional gray image data of sorghum grain in group 1. The effects of different preprocessing methods and different convolution kernel sizes on the performance of the AlexNet model were discussed. The eigenvalues of the last layer of the AlexNet model were visualized using the t-distributed random neighborhood embedding method, which is used to evaluate the separability of features extracted by the AlexNet model. The performance differences between the optimal AlexNet model and traditional machine learning models for sorghum variety identification were compared. Finally, the varieties of sorghum grains in groups 2 and 3 were identified based on the optimal AlexNet model, and the average accuracy values of the test set reached 95.62% and 95.91% respectively.

CONCLUSION

The results in this study demonstrated that HSI combined with the AlexNet model could provide a feasible technical approach for the detection of sorghum varieties. © 2022 Society of Chemical Industry.

In-line identification of Pb-based pigments in fishing nets and ropes based on hyperspectral imaging and machine learning

Fishing lines, nets, and ropes represent a significant portion of plastic pollution in marine environments, and can contain hazardous additives. The development of less laborious and faster methods aiming at identifying plastic-related additives is therefore needed, in order to facilitate effective recycling. This work aims to develop an industrial inline method to identify lead-based pigments in fishnets by an industrial hyperspectral imaging (HSI) system working in visible-near-infrared spectral range (Vis-NIR, 450 to 1050 nm) and machine learning. A Vis-NIR spectral sample set comprising un-contaminated and lead contaminated (143 to 2430 mg L^-1) plastic classes were used to build the classification model via Principal Component Analysis and clustering. The content of the samples was characterized by X-ray fluorescence (XRF), Attenuated Total Reflection (ATR-FTIR), differential scanning calorimetry, thermogravimetric analysis, and burning in astmospheric air. Fishnets containing lead-based pigments with lead concentrations > 1000 mg L^-1 (0.1 wt%) were accurately identified by the industrial HSI, and the lead content was corroborated with ATR-FTIR and XRF measurements. In addition, lead contaminated plastic area and mass can be estimated via calibration curve using the pixels numbers vs mass of fibrous plastics with a detectability of 120 mg (R² = 0.997).

Hyperspectral Imaging of Adaxial and Abaxial Leaf Surfaces as a Predictor of Macadamia Crop Nutrition

Tree crop yield is highly dependent on fertiliser inputs, which are often guided by the assessment of foliar nutrient levels. Traditional methods for nutrient analysis are time-consuming but hyperspectral imaging has potential for rapid nutrient assessment. Hyperspectral imaging has generally been performed using the adaxial surface of leaves although the predictive performance of spectral data has rarely been compared between adaxial and abaxial surfaces of tree leaves. We aimed to evaluate the capacity of laboratory-based hyperspectral imaging (400-1000 nm wavelengths) to predict the nutrient concentrations in macadamia leaves. We also aimed to compare the prediction accuracy from adaxial and abaxial leaf surfaces. We sampled leaves from 30 macadamia trees at 0, 6, 10 and 26 weeks after flowering and captured hyperspectral images of their adaxial and abaxial surfaces. Partial least squares regression (PLSR) models were developed to predict foliar nutrient concentrations. Coefficients of determination (R²_P) and ratios of prediction to deviation (RPDs) were used to evaluate prediction accuracy. The models reliably predicted foliar nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), copper (Cu), manganese (Mn), sulphur (S) and zinc (Zn) concentrations. The best-fit models generally predicted nutrient concentrations from spectral data of the adaxial surface (e.g., N: R²_P = 0.55, RPD = 1.52; P: R²_P = 0.77, RPD = 2.11; K: R²_P = 0.77, RPD = 2.12; Ca: R²_P = 0.75, RPD = 2.04). Hyperspectral imaging showed great potential for predicting nutrient status. Rapid nutrient assessment through hyperspectral imaging could aid growers to increase orchard productivity by managing fertiliser inputs in a more-timely fashion.

Quantification of Photosynthetic Pigments in Neopyropia yezoensis Using Hyperspectral Imagery

Phycobilisomes and chlorophyll-a (Chla) play important roles in the photosynthetic physiology of red macroalgae and serve as the primary light-harvesting antennae and reaction center for photosystem II. Neopyropia is an economically important red macroalga widely cultivated in East Asian countries. The contents and ratios of 3 main phycobiliproteins and Chla are visible traits to evaluate its commercial quality. The traditional analytical methods used for measuring these components have several limitations. Therefore, a high-throughput, nondestructive, optical method based on hyperspectral imaging technology was developed for phenotyping the pigments phycoerythrin (PE), phycocyanin (PC), allophycocyanin (APC), and Chla in Neopyropia thalli in this study. The average spectra from the region of interest were collected at wavelengths ranging from 400 to 1000 nm using a hyperspectral camera. Following different preprocessing methods, 2 machine learning methods, partial least squares regression (PLSR) and support vector machine regression (SVR), were performed to establish the best prediction models for PE, PC, APC, and Chla contents. The prediction results showed that the PLSR model performed the best for PE (R _Test ² = 0.96, MAPE = 8.31%, RPD = 5.21) and the SVR model performed the best for PC (R _Test ² = 0.94, MAPE = 7.18%, RPD = 4.16) and APC (R _Test ² = 0.84, MAPE = 18.25%, RPD = 2.53). Two models (PLSR and SVR) performed almost the same for Chla (PLSR: R _Test ² = 0.92, MAPE = 12.77%, RPD = 3.61; SVR: R _Test ² = 0.93, MAPE = 13.51%, RPD =3.60). Further validation of the optimal models was performed using field-collected samples, and the result demonstrated satisfactory robustness and accuracy. The distribution of PE, PC, APC, and Chla contents within a thallus was visualized according to the optimal prediction models. The results showed that hyperspectral imaging technology was effective for fast, accurate, and noninvasive phenotyping of the PE, PC, APC, and Chla contents of Neopyropia in situ. This could benefit the efficiency of macroalgae breeding, phenomics research, and other related applications.

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

Introduction

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.

Methods

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.

Results and discussion

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.

Non-Destructive Hyperspectral Imaging for Rapid Determination of Catalase Activity and Ageing Visualization of Wheat Stored for Different Durations

(1) In order to accurately judge the new maturity of wheat and better serve the collection, storage, processing and utilization of wheat, it is urgent to explore a fast, convenient and non-destructively technology. (2) Methods: Catalase activity (CAT) is an important index to evaluate the ageing of wheat. In this study, hyperspectral imaging technology (850-1700 nm) combined with a BP neural network (BPNN) and a support vector machine (SVM) were used to establish a quantitative prediction model for the CAT of wheat with the classification of the ageing of wheat based on different storage durations. (3) Results: The results showed that the model of 1ST-SVM based on the full-band spectral data had the best prediction performance (R² = 0.9689). The SPA extracted eleven characteristic bands as the optimal wavelengths, and the established model of MSC-SPA-SVM showed the best prediction result with R² = 0.9664. (4) Conclusions: The model of MSC-SPA-SVM was used to visualize the CAT distribution of wheat ageing. In conclusion, hyperspectral imaging technology can be used to determine the CAT content and evaluate wheat ageing, rapidly and non-destructively.

Recent Progress on Techniques in the Detection of Aflatoxin B1 in Edible Oil: A Mini Review

Contamination of agricultural products and foods by aflatoxin B1 (AFB1) is becoming a serious global problem, and the presence of AFB1 in edible oil is frequent and has become inevitable, especially in underdeveloped countries and regions. As AFB1 results from a possible degradation of aflatoxins and the interaction of the resulting toxic compound with food components, it could cause chronic disease or severe cancers, increasing morbidity and mortality. Therefore, rapid and reliable detection methods are essential for checking AFB1 occurrence in foodstuffs to ensure food safety. Recently, new biosensor technologies have become a research hotspot due to their characteristics of speed and accuracy. This review describes various technologies such as chromatographic and spectroscopic techniques, ELISA techniques, and biosensing techniques, along with their advantages and weaknesses, for AFB1 control in edible oil and provides new insight into AFB1 detection for future work. Although compared with other technologies, biosensor technology involves the cross integration of multiple technologies, such as spectral technology and new nano materials, and has great potential, some challenges regarding their stability, cost, etc., need further studies.

Toward in-process technology-aided automation for enhanced microbial food safety and quality assurance in milk and beverages processing

Ensuring the safety of food products is critical to food production and processing. In food processing and production, several standard guidelines are implemented to achieve acceptable food quality and safety. This notwithstanding, due to human limitations, processed foods are often contaminated either with microorganisms, microbial byproducts, or chemical agents, resulting in the compromise of product quality with far-reaching consequences including foodborne diseases, food intoxication, and food recall. Transitioning from manual food processing to automation-aided food processing (smart food processing) which is guided by artificial intelligence will guarantee the safety and quality of food. However, this will require huge investments in terms of resources, technologies, and expertise. This study reviews the potential of artificial intelligence in food processing. In addition, it presents the technologies and methods with potential applications in implementing automated technology-aided processing. A conceptual design for an automated food processing line comprised of various operational layers and processes targeted at enhancing the microbial safety and quality assurance of liquid foods such as milk and beverages is elaborated.

Using hyperspectral imaging technology for assessing internal quality parameters of persimmon fruits during the drying process

The crucial features of persimmon are required to detect real-time moisture, water-soluble tannin, and soluble solids contents during the drying process. This study developed a method based on hyperspectral imaging (HSI) to execute online and non-destructive assaying of persimmon features. A total of 144 samples were collected, and 150 bands were scanned. The spectral data were analyzed by partial least squares regression (PLSR), principal component regression (PCR), least squares support vector regression (LS-SVR), and radial basis function neural network (RBFNN) with seven preprocessing methods. LS-SVR provided excellent performance for moisture content prediction, while PLSR was better in the analysis of water-soluble tannin and soluble solids contents. Successive projection algorithm (SPA) was used to select the optimal wavelengths to simplify the models, and about twenty important variables were chosen. Overall, these results indicate that HSI could be considered a valuable technique to quantify chemical constituents in dried persimmon fruits.

Soybean Cultivars Identification Using Remotely Sensed Image and Machine Learning Models

Using remote sensing combined with machine learning (ML) techniques is a promising approach to classify soybean cultivars. Therefore, the objectives of this study are (i) to verify which input dataset configuration (using only spectral bands, only vegetation indices, or both) is more accurate in the identification of soybean cultivars, and (ii) to verify which ML technique is more accurate in the identification of soybean cultivars. Information was extracted from five central irrigation pivots in the same region and with the same sowing date in the 2015/2016 crop year, in which each pivot was cultivated with a different cultivar, in which the cultivars used were: CV1—P98y12 RR, CV2—Desafio RR, CV3—M6410 IPRO, CV4—M7110 IPRO, and CV5—NA5909 RR. A cloud-free orbital image of the site was acquired from the Google Earth Engine platform. In addition to the spectral bands alone, a total of 13 vegetation indices were calculated. The models tested were: artificial neural networks (ANN), radial basis function network (RBF), decision tree algorithms J48 (DT) and reduced error pruning tree (REP), random forest (RF), and support vector machine (SVM). The five soybean cultivars were classified by the six-machine learning (ML) models in stratified randomized cross-validation with k-fold = 10 and 10 repetitions (100 runs for each model). After obtaining the r and MAE statistics, analysis of variance was performed considering a 6 × 3 factorial scheme (models versus inputs) with 10 repetitions (folds). The means were grouped by the Scott–Knott test at 5% probability. The spectral bands were the most accurate among the tested inputs in the identification of soybean cultivars. ANN was the most accurate model in identifying soybean cultivars.

Rapid and nondestructive determination of sorghum purity combined with deep forest and near-infrared hyperspectral imaging

This study combined hyperspectral imaging (HSI) and deep forest (DF) to develop a reliable model for conducting a rapid and nondestructive determination of sorghum purity. Isolated forest (IF) algorithm and principal component analysis (PCA) were used to remove the abnormal data of sorghum grains. Competitive adaptive reweighted sampling (CARS) algorithm and successive projections algorithm (SPA) were combined and used to extract the characteristic wavelengths. Gray-level co-occurrence matrix (GLCM) was used to extract the textural features. DF models were established based on the different types of data. Specifically, the DF models established using the characteristic spectra produced the best recognition results: the average correct recognition rate (CRR) of the models was greater than 91%. In addition, the average CRR of validation set Ⅰ was 88.89%. These results show that a combination of HSI and DF could be used for the rapid and nondestructive determination of sorghum purity.

Non-destructive assessment of quality parameters of white button mushrooms (Agaricus bisporus) using image processing techniques

Considering that appearance of white button mushroom (WBM) as the trigger for registering its quality, this study was aimed at analyzing the visual cues by the application of image processing tools. While L-a-b colour space and skewness was used for estimating chromatic and morphological characteristics; onset of discolouration of WBM was predicted by hyperspectral image analysis. Undamaged (UD) and damaged (D) mushrooms were stored under refrigerated conditions (3-5 °C and 90% R_h). RGB and hyperspectral images were acquired on alternate storage days 1, 3, 5, 7 and 9. Weight loss, texture and moisture content of stored mushrooms were also recorded during the storage period. Colour changes in stored UD and D were found to be in b (21.55) and a (2399) value, respectively. Browning index in D was 83-212% higher than UD mushrooms across the storage period. Weight and firmness losses in D were higher by 65.9 and 31.4%, respectively than UD. Morphological characteristic in terms of aspect ratio and roundness were not found to vary significantly over the storage period for both UD and D mushrooms. Chemometrics revealed that multiplicative scatter correction was the best pre-processing tool and that onset on discolouration is conspicuous in the spectral region of 520-800 nm. k-NN fared better than PLS-DA for correct classification (100%) of UD and D mushrooms.

LSTNet: A Reference-Based Learning Spectral Transformer Network for Spectral Super-Resolution

Hyperspectral images (HSIs) are data cubes containing rich spectral information, making them beneficial to many Earth observation missions. However, due to the limitations of the associated imaging systems and their sensors, such as the swath width and revisit period, hyperspectral imagery over a large coverage area cannot be acquired in a short amount of time. Spectral super-resolution (SSR) is a method that involves learning the relationship between a multispectral image (MSI) and an HSI, based on the overlap region, followed by reconstruction of the HSI by making full use of the large swath width of the MSI, thereby improving its coverage. Much research has been conducted recently to address this issue, but most existing methods mainly learn the prior spectral information from training data, lacking constraints on the resulting spectral fidelity. To address this problem, a novel learning spectral transformer network (LSTNet) is proposed in this paper, utilizing a reference-based learning strategy to transfer the spectral structure knowledge of a reference HSI to create a reasonable reconstruction spectrum. More specifically, a spectral transformer module (STM) and a spectral reconstruction module (SRM) are designed, in order to exploit the prior and reference spectral information. Experimental results demonstrate that the proposed method has the ability to produce high-fidelity reconstructed spectra.

Near-Infrared Hyperspectral Imaging Pipelines for Pasture Seed Quality Evaluation: An Overview

Near-infrared (800–2500 nm; NIR) spectroscopy coupled to hyperspectral imaging (NIR-HSI) has greatly enhanced its capability and thus widened its application and use across various industries. This non-destructive technique that is sensitive to both physical and chemical attributes of virtually any material can be used for both qualitative and quantitative analyses. This review describes the advancement of NIR to NIR-HSI in agricultural applications with a focus on seed quality features for agronomically important seeds. NIR-HSI seed phenotyping, describing sample sizes used for building high-accuracy calibration and prediction models for full or selected wavelengths of the NIR region, is explored. The molecular interpretation of absorbance bands in the NIR region is difficult; hence, this review offers important NIR absorbance band assignments that have been reported in literature. Opportunities for NIR-HSI seed phenotyping in forage grass seed are described and a step-by-step data-acquisition and analysis pipeline for the determination of seed quality in perennial ryegrass seeds is also presented.

Molecular Aggregation Dynamics via a Liquid-like Cluster Intermediate during Heterogeneous Evaporation as Revealed by Hyperspectral Camera Fluorescence Imaging

A hyperspectral camera (HSC) is a camera with great potential to obtain spectral information at each pixel, together with spatial imaging. HSC fluorescence imaging enables the molecular aggregation dynamics of the evaporative crystallization process to be followed in real-time. The key intermediate liquid-like cluster state for the two-step nucleation mechanism is visualized by the fluorescence color changes of mechanochromic luminescent dibenzoylmethanatoboron difluoride derivatives. Three types of emissive species (Crystal, BG-aggregates, and Amorphous) are generated from monomers in solution (low order and density) via liquid-like cluster (high density and low order) during solvent evaporation. These emissive species have partially different aggregated states based on fluorescence decay and fluorescence excitation spectral measurements. In terms of crystallization dynamics, our results indicate that it is important not only to generate supersaturated states but also to maintain the survival time of the liquid-like cluster. Moreover, we demonstrate that HSC fluorescence imaging can be a powerful tool for visualizing heterogeneous molecular aggregation processes.

Challenges for a Massive Implementation of Phenomics in Plant Breeding Programs

Due to climate change and expected food shortage in the coming decades, not only will it be necessary to develop cultivars with greater tolerance to environmental stress, but it is also imperative to reduce breeding cycle time. In addition to yield evaluation, plant breeders resort to many sensory assessments and some others of intermediate complexity. However, to develop cultivars better adapted to current/future constraints, it is necessary to incorporate a new set of traits, such as morphophysiological and physicochemical attributes, information relevant to the successful selection of genotypes or parents. Unfortunately, because of the large number of genotypes to be screened, measurements with conventional equipment are unfeasible, especially under field conditions. High-throughput plant phenotyping (HTPP) facilitates collecting a significant amount of data quickly; however, it is necessary to transform all this information (e.g., plant reflectance) into helpful descriptors to the breeder. To the extent that a holistic characterization of the plant (phenomics) is performed in challenging environments, it will be possible to select the best genotypes (forward phenomics) objectively but also understand why the said individual differs from the rest (reverse phenomics). Unfortunately, several elements had prevented phenomics from developing as desired. Consequently, a new set of prediction/validation methodologies, seasonal ambient information, and the fusion of data matrices (e.g., genotypic and phenotypic information) need to be incorporated into the modeling. In this sense, for the massive implementation of phenomics in plant breeding, it will be essential to count an interdisciplinary team that responds to the urgent need to release material with greater capacity to tolerate environmental stress. Therefore, breeding programs should (i) be more efficient (e.g., early discarding of unsuitable material), (ii) have shorter breeding cycles (fewer crosses to achieve the desired cultivar), and (iii) be more productive, increasing the probability of success at the end of the breeding process (percentage of cultivars released to the number of initial crosses).

The Influence of Aerial Hyperspectral Image Processing Workflow on Nitrogen Uptake Prediction Accuracy in Maize

A meticulous image processing workflow is oftentimes required to derive quality image data from high-resolution, unmanned aerial systems. There are many subjective decisions to be made during image processing, but the effects of those decisions on prediction model accuracy have never been reported. This study introduced a framework for quantifying the effects of image processing methods on model accuracy. A demonstration of this framework was performed using high-resolution hyperspectral imagery (<10 cm pixel size) for predicting maize nitrogen uptake in the early to mid-vegetative developmental stages (V6–V14). Two supervised regression learning estimators (Lasso and partial least squares) were trained to make predictions from hyperspectral imagery. Data for this use case were collected from three experiments over two years (2018–2019) in southern Minnesota, USA (four site-years). The image processing steps that were evaluated include (i) reflectance conversion, (ii) cropping, (iii) spectral clipping, (iv) spectral smoothing, (v) binning, and (vi) segmentation. In total, 648 image processing workflow scenarios were evaluated, and results were analyzed to understand the influence of each image processing step on the cross-validated root mean squared error (RMSE) of the estimators. A sensitivity analysis revealed that the segmentation step was the most influential image processing step on the final estimator error. Across all workflow scenarios, the RMSE of predicted nitrogen uptake ranged from 14.3 to 19.8 kg ha−1 (relative RMSE ranged from 26.5% to 36.5%), a 38.5% increase in error from the lowest to the highest error workflow scenario. The framework introduced demonstrates the sensitivity and extent to which image processing affects prediction accuracy. It allows remote sensing analysts to improve model performance while providing data-driven justification to improve the reproducibility and objectivity of their work, similar to the benefits of hyperparameter tuning in machine learning applications.

Novel extraction, rapid assessment and bioavailability improvement of quercetin: A review

Quercetin (QUR) have got the attention of scientific society frequently due to their wide range of potential applications. QUR has been the focal point for research in various fields, especially in food development. But, the QUR is highly unstable and can be interrupted by using conventional assessment methods. Therefore, researchers are focusing on novel extraction and non-invasive tools for the non-destructive assessment of QUR. The current review elaborates the different novel extraction (ultrasound-assisted extraction, microwave-assisted extraction, supercritical fluid extraction, and enzyme-assisted extraction) and non-destructive assessment techniques (fluorescence spectroscopy, terahertz spectroscopy, near-infrared spectroscopy, hyperspectral imaging, Raman spectroscopy, and surface-enhanced Raman spectroscopy) for the extraction and identification of QUR in agricultural products. The novel extraction approaches facilitate shorter extraction time, involve less organic solvent, and are environmentally friendly. While the non-destructive techniques are non-interruptive, label-free, reliable, accurate, and environmental friendly. The non-invasive spectroscopic and imaging methods are suitable for the sensitive detection of bioactive compounds than conventional techniques. QUR has potential therapeutic properties such as anti-obesity, anti-diabetes, antiallergic, antineoplastic agent, neuroprotector, antimicrobial, and antioxidant activities. Besides, due to the low bioavailability of QUR innovative drug delivery strategies (QUR loaded gel, QUR polymeric micelle, QUR nanoparticles, glucan-QUR conjugate, and QUR loaded mucoadhesive nanoemulsions) have been proposed to improve its bioavailability and providing novel therapeutic approaches.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

Imaging spectroscopy has emerged as a reliable analytical method for effectively characterizing and quantifying quality attributes of agricultural products. By providing spectral information relevant to food quality properties, imaging spectroscopy has been demonstrated to be a potential method for rapid and non-destructive classification, authentication, and prediction of quality parameters of various categories of tubers, including potato and sweet potato. The imaging technique has demonstrated great capacities for gaining rapid information about tuber physical properties (such as texture, water binding capacity, and specific gravity), chemical components (such as protein, starch, and total anthocyanin), varietal authentication, and defect aspects. This paper emphasizes how recent developments in spectral imaging with machine learning have enhanced overall capabilities to evaluate tubers. The machine learning algorithms coupled with feature variable identification approaches have obtained acceptable results. This review briefly introduces imaging spectroscopy and machine learning, then provides examples and discussions of these techniques in tuber quality determinations, and presents the challenges and future prospects of the technology. This review will be of great significance to the study of tubers using spectral imaging technology.

Rapid and nondestructive prediction of amylose and amylopectin contents in sorghum based on hyperspectral imaging

The contents of amylose and amylopectin in sorghum directly affects the quality and yield of liquor. Hyperspectral imaging (HSI) is an emerging technology widely applied in the content analysis of food ingredients. In this study, the effects of different preprocessing methods on visible-light and near-infrared spectral data were analyzed, and the prediction accuracies of these spectral data were compared. Principal components analysis (PCA) and successive projections algorithm (SPA) were combined to extract the characteristic wavelengths. Using both the full and characteristic wavelengths, partial least square regression (PLSR) and cascade forest (CF) models were developed to predict the contents of amylose and amylopectin in different varieties of sorghum. The average RPD values of the CF models established by the characteristic wavelengths were 4.7622 and 5.5889, respectively. These results corroborated the utility of HSI in achieving the rapid and nondestructive prediction of amylose and amylopectin contents in different varieties of sorghum.

A study of starch content detection and the visualization of fresh-cut potato based on hyperspectral imaging

Fresh-cut potatoes are popular with consumers because of their healthiness, hygiene, and convenience. Currently, starch content is mainly detected using chemical methods, which are time-consuming and laborious. Moreover, these methods may cause some side effects in the human body. Therefore, suitable methods are required for the rapid and accurate detection of starch content. In this study, Zihuabai and Atlantic potatoes were used as experimental samples. The potatoes were sliced with stainless-steel blades, and images of these potatoes were obtained through hyperspectral imaging. The images were preprocessed using different methods. Competitive adaptive reweighed sampling (CARS) and the successive projection algorithm (SPA) were used to extract characteristic wavelengths. A partial least squares regression (PLSR) model was constructed to predict the starch content from the preprocessed full spectrum and the spectrum under the characteristic wavelength. The results indicate that the full spectrum model constructed through standard normal variable transformation (SNV) preprocessing had the best performance, with a correlation coefficient in the calibration set (R c) value of 0.9020, a root mean square error of correction (RMSEC) of 2.06, and a residual prediction deviation (RPD) of 2.33. The characteristic wavelength-based multivariate scattering correction (MSC)-CARS-PLSR model exhibited better performance than the PLSR model constructed using the full spectrum, with an R c value of 0.9276, RMSEC of 1.76, correlation coefficient in the prediction set (R p) value of 0.9467, root mean square error of prediction of 1.63, and RPD of 2.95. The starch content in fresh-cut potatoes was visualized using the best model in combination with pseudocolor technology. The results indicate that hyperspectral imaging is effective for mapping the spatial distribution of starch content; thus, a solid theoretical basis is obtained for the grading and online monitoring of fresh-cut potato slices.

Prediction of dry matter content of recently harvested 'Hass' avocado fruits using hyperspectral imaging

BACKGROUND

'Hass' avocado consumption is increasing due to its organoleptic properties, so it is necessary to develop new technologies to guarantee export quality. Avocado fruits do not ripen on the tree, and the visual classification of its maturity is not accurate. The most commonly used fruit maturity indicator is the percentage of dry matter (DM). The aim of this research was to investigate a non-destructive method with hyperspectral images to predict the percentage of DM of fruits across the spectral range of 400-1000 nm.

RESULTS

No correlation between fruit weight and color with the percentage of DM was found in the study area. Cross-validation efficiency of different data sources, including the spectrum extraction zone (the center, a line from the peduncle to the base, and the whole fruit) and the average of one or two fruit faces, was compared. Four linear regression models were compared. Data of the whole fruit and average of both sides per fruit using a support vector machine regression were selected for the prediction test. Following the cross-validation concept, five sets of calibration and test data were selected and optimized for calibration. The best test prediction set comprised an R² = 0.9, a root-mean-square error of 2.6 g kg^-1 DM, a Pearson correlation of 0.95, and a ratio of prediction to deviation of 3.2.

CONCLUSIONS

The results of the study indicate that hyperspectral images allow classifying export fruits and making harvesting decisions. © 2020 Society of Chemical Industry.

Non-destructive classification and prediction of aflatoxin-B1 concentration in maize kernels using Vis-NIR (400-1000 nm) hyperspectral imaging

Aflatoxin-B1 contamination in maize is a major food safety issue across the world. Conventional detection technique of toxins requires highly skilled technicians and is time-consuming. Application of appropriate chemometrics along with hyperspectral imaging (HSI) can identify aflatoxin-B1 infected maize kernels. Present study was undertaken to classify 240 maize kernels inoculated with six different concentrations (25, 40, 70, 200, 300 and 500 ppb) of aflatoxin-B1 by using Vis-NIR HSI. The reflectance spectral data were pre-processed (multiplicative scatter correction (MSC), standard normal variate (SNV), Savitsky-Golay smoothing and their combinations) and classified using partial least square discriminant analysis (PLS-DA) and k-nearest neighbour (k-NN). PLS model was also developed to predict the concentration of aflatoxin-B1in naturally contaminated maize kernels inoculated with Aspergillus flavus. The potential wavelength (508 nm) was selected based on principal component analysis (PCA) loadings to distinguish between sterile and infected maize kernels. PCA score plots revealed a distinct separation of low contaminated samples (25, 40 and 70 ppb) from highly contaminated samples (200, 300 and 500 ppb) without any overlapping of data. The maximum classification accuracy of 94.7% was obtained using PLS-DA with SNV pre-processed data. Across all the combinations of pre-processing and classification models, the best efficiency (98.2%) was exhibited by k-NN model with raw data. The developed PLS model depicted good prediction accuracy ( R CV 2  = 0.820, SECV = 79.425, RPDCV = 2.382) during Venetian-blinds cross-validation. The results of pixel-wise classification (k-NN) and concentration distribution maps (PLS with raw spectra) were quite close to the result obtained by reference method (HPLC analysis) of aflatoxin-B1 detection.

Identification of plant leaf phosphorus content at different growth stages based on hyperspectral reflectance

BACKGROUND

Modern agriculture strives to sustainably manage fertilizer for both economic and environmental reasons. The monitoring of any nutritional (phosphorus, nitrogen, potassium) deficiency in growing plants is a challenge for precision farming technology. A study was carried out on three species of popular crops, celery (Apium graveolens L., cv. Neon), sugar beet (Beta vulgaris L., cv. Tapir) and strawberry (Fragaria × ananassa Duchesne, cv. Honeoye), fertilized with four different doses of phosphorus (P) to deliver data for non-invasive detection of P content.

RESULTS

Data obtained via biochemical analysis of the chlorophyll and carotenoid contents in plant material showed that the strongest effect of P availability for plants was in the diverse total chlorophyll content in sugar beet and celery compared to that in strawberry, in which P affects a variety of carotenoid contents in leaves. The measurements performed using hyperspectral imaging, obtained in several different stages of plant development, were applied in a supervised classification experiment. A machine learning algorithm (Backpropagation Neural Network, Random Forest, Naive Bayes and Support Vector Machine) was developed to classify plants from four variants of P fertilization. The lowest prediction accuracy was obtained for the earliest measured stage of plant development. Statistical analyses showed correlations between leaf biochemical constituents, phosphorus fertilization and the mass of the leaf/roots of the plants.

CONCLUSIONS

Obtained results demonstrate that hyperspectral imaging combined with artificial intelligence methods has potential for non-invasive detection of non-homogenous phosphorus fertilization on crop levels.