Search

Potatoes are a staple food crop consumed worldwide, with their significance extending from household kitchens to large-scale food processing industries. Their market value and quality are often compromised by various internal defects such as pythium, bruising, internal browning, hollow heart, gangrene, blackheart, internal sprouting, and dry rot. This study aimed to classify internal-based defects and investigate the quantification of internal defective areas in potatoes using visible and short-wavelength near-infrared spectroscopy. The acquisition of the spectral data of potato tubers was performed using a spectrometer with a wavelength range of 400–1100 nm. The classification of internal-based defects was performed using partial least squares discriminant analysis (PLS-DA), while the quantification of the internal defective area was based on partial least squares regression (PLSR). The PLS-DA double cross-validation accuracy for the distinction between non-defective and all internally defective potatoes was 90.78%. The double cross-validation classification accuracy achieved for pythium, bruising, and non-defective categories was 91.03%. The internal defective area model based on PLSR achieved a correlation coefficient of double cross-validation of 0.91 and a root mean square error of double cross-validation of 0.85 cm2. This study makes a valuable contribution to advancing nondestructive techniques for evaluating internal defects in potatoes.

Citrus diseases are significant threats to citrus groves, causing financial losses through reduced fruit size, blemishes, premature fruit drop, and tree death. The detection of citrus diseases via leaf inspection can improve grove management and mitigation efforts. This study explores the potential of a portable reflectance and fluorescence hyperspectral imaging (HSI) system for detecting and classifying a control group and citrus leaf diseases, including canker, Huanglongbing (HLB), greasy spot, melanose, scab, and zinc deficiency. The HSI system was used to simultaneously collect reflectance and fluorescence images from the front and back sides of the leaves. Nine machine learning classifiers were trained using full spectra and spectral bands selected through principal component analysis (PCA) from the HSI with pixel-based and leaf-based spectra. A support vector machine (SVM) classifier achieved the highest overall classification accuracy of 90.7% when employing the full spectra of combined reflectance and fluorescence data and pixel-based analysis from the back side of the leaves, whereas a discriminant analysis classifier yielded the best accuracy of 94.5% with the full spectra of combined reflectance and fluorescence data and leaf-based analysis. Among the diseases, control, scab, and melanose were classified most accurately, each with over 90% accuracy. Therefore, the integration of the reflectance and fluorescence HSI with advanced machine learning techniques demonstrated the capability to accurately detect and classify these citrus leaf diseases with high precision.

The Contamination Sanitization Inspection and Disinfection (CSI-D) device is a handheld fluorescence-based imaging system designed to disinfect food contact surfaces using ultraviolet-C (UVC) illumination. This study aimed to determine the optimal CSI-D parameters (i.e., UVC exposure time and intensity) for the inactivation of the following foodborne bacteria plated on non-selective media: generic Escherichia coli (indicator organism) and the pathogens enterohemorrhagic E. coli, enterotoxigenic E. coli, Salmonella enterica, and Listeria monocytogenes. Each bacterial strain was spread-plated on non-selective agar and exposed to high-intensity (10 mW/cm2) or low-intensity (5 mW/cm2) UVC for 1–5 s. Control plates were not exposed to UVC. The plates were incubated overnight at 37 °C and then enumerated. Three trials for each bacterial strain were conducted. Statistical analysis was carried out to determine if there were significant differences in bacterial growth between UVC intensities and exposure times. Overall, exposure to low or high intensity for 3–5 s resulted in consistent inhibition of bacterial growth, with reductions of 99.9–100 % for E. coli, 96.8–100 % for S. enterica, and 99.2–100 % for L. monocytogenes. The 1 s exposure time showed inconsistent results, with a 66.0–100 % reduction in growth depending on the intensity and bacterial strain. When the results for all strains within each species were combined, the 3–5 s exposure times showed significantly greater (p 0.05) in growth inhibition between the high and low UVC intensities. The results of this study show that, in pure culture conditions, exposure to UVC with the CSI-D device for ≥3 s is required to achieve consistent reduction of E. coli, S. enterica, and L. monocytogenes.

This study systematically reviews the integration of artificial intelligence (AI) and remote sensing technologies to address the issue of crop water stress caused by rising global temperatures and climate change; in particular, it evaluates the effectiveness of various non-destructive remote sensing platforms (RGB, thermal imaging, and hyperspectral imaging) and AI techniques (machine learning, deep learning, ensemble methods, GAN, and XAI) in monitoring and predicting crop water stress. The analysis focuses on variability in precipitation due to climate change and explores how these technologies can be strategically combined under data-limited conditions to enhance agricultural productivity. Furthermore, this study is expected to contribute to improving sustainable agricultural practices and mitigating the negative impacts of climate change on crop yield and quality.

Fruits and vegetables have always had a significant economic impact on human survival, providing food security and boosting output with minimal input. This review focuses on an in-depth analysis of the grading criteria and the identification of exterior quality characteristics of major vegetables and fruits through various noninvasive spectroscopic and imaging methods, along with a brief discussion of their key components, schematic operations, potential for application in place of conventional approaches, and highlights the potential research gaps. In this review, the attention was focused on preprocessing, data analysis techniques, and the specific and overall values of performance accuracy by using a specific performance metric in relation to fruits and vegetables. Several machine learning (ML), as well as deep learning (DL) techniques, such as K-nearest neighbor (KNN), artificial neural networks (ANN), support vector machines (SVM), convolutional neural networks (CNN) with transfer learning (TL), generative adversarial networks (GAN) and recurrent neural network (RNN), have recently been used for inspection along with the processing of spectral data. ML and DL techniques have been proposed in recent publications for the external quality inspection of fruits and vegetables.

Fresh-cut vegetables are a food product susceptible to contamination by foreign materials (FMs). To detect a range of potential FMs in fresh-cut vegetables, a dual imaging technique (fluorescence and color imaging) with a simple and effective image processing algorithm in a user-friendly software interface was developed for a real-time inspection system. The inspection system consisted of feeding and sensing units, including two cameras positioned in parallel, illuminations (white LED and UV light), and a conveyor unit. A camera equipped with a long-pass filter was used to collect fluorescence images. Another camera collected color images of fresh-cut vegetables and FMs. The feeding unit fed FMs mixed with fresh-cut vegetables onto a conveyor belt. Two cameras synchronized programmatically in the software interface simultaneously collected fluorescence and color image samples based on the region of interest as they moved through the conveyor belt. Using simple image processing algorithms, FMs could be detected and depicted in two different image windows. The results demonstrated that the dual imaging technique can effectively detect potential FMs in two types of fresh-cut vegetables (cabbage and green onion), as indicated by the combined fluorescence and color imaging accuracy. The test results showed that the real-time inspection system could detect FMs measuring 0.5 mm in fresh-cut vegetables. The results showed that the combined detection accuracy of FMs in the cabbage (95.77%) sample was superior to that of green onion samples (87.89%). Therefore, the inspection system was more effective at detecting FMs in cabbage samples than in green onion samples.

Increasing food demands, global climatic variations, and population growth have spurred the growth of crop yield driven by plant phenotyping in the age of Big Data. High-throughput phenotyping of sorghum at each plant and organ level is vital in molecular plant breeding to increase crop yield. LiDAR (light detection and ranging) sensor provides 3-D point clouds of plants with the advantages of high precision, high resolution, and rapid measurement. However, need to develop robust algorithms for extracting the phenotypic traits of sorghum plants using LiDAR 3-D point cloud. This study utilized four 3-D point cloud-based deep learning models named PointNet, PointNet++, PointCNN, and dynamic graph CNN for the specific objective of the segmentation of sorghum plants. Subsequently, phenotypic traits were extracted using the segmentation results. Study plants sample were grown under controlled conditions at various developmental stages. The extracted phenotypic traits outcome has been validated through the manually measured phenotypic traits of the sorghum plant. PointNet++ outperformed the other three deep learning models and provided the best segmentation result with a mean accuracy of 91.5%. The correlations of the six phenotypic traits, such as plant height, plant crown diameter, plant compactness, stem diameter, panicle length, and panicle width were calculated from the segmentation results of the PointNet++ model and the measured coefficient of determination (R2) were 0.97, 0.96, 0.94, 0.90, 0.95, and 0.88, respectively. The obtained results showed that LiDAR 3-D point cloud have good potential to measure the sorghum plant phenotype traits rapidly and accurately using deep learning techniques.

The quality of tropical fruits and vegetables and the expanding global interest in eating healthy foods have resulted in the continual development of reliable, quick, and cost-effective quality assurance methods. The present review discusses the advancement of non-destructive spectral measurements for evaluating the quality of major tropical fruits and vegetables. Fourier transform infrared (FTIR), Near-infrared (NIR), Raman spectroscopy, and hyperspectral imaging (HSI) were used to monitor the external and internal parameters of papaya, pineapple, avocado, mango, and banana. The ability of HSI to detect both spectral and spatial dimensions proved its efficiency in measuring external qualities such as grading 516 bananas, and defects in 10 mangoes and 10 avocados with 98.45%, 97.95%, and 99.9%, respectively. All of the techniques effectively assessed internal characteristics such as total soluble solids (TSS), soluble solid content (SSC), and moisture content (MC), with the exception of NIR, which was found to have limited penetration depth for fruits and vegetables with thick rinds or skins, including avocado, pineapple, and banana. The appropriate selection of NIR optical geometry and wavelength range can help to improve the prediction accuracy of these crops. The advancement of spectral measurements combined with machine learning and deep learning technologies have increased the efficiency of estimating the six maturity stages of papaya fruit, from the unripe to the overripe stages, with F1 scores of up to 0.90 by feature concatenation of data developed by HSI and visible light. The presented findings in the technological advancements of non-destructive spectral measurements offer promising quality assurance for tropical fruits and vegetables.

Unlike standard chemical analysis methods involving time-consuming, labor-intensive, and invasive pretreatment procedures, Raman hyperspectral imaging (HSI) can rapidly and non-destructively detect components without professional supervision. Generally, the Kjeldahl methods and Soxhlet extraction are used to chemically determine the protein and lipid content of soybeans. This study is aimed at developing a high-performance model for estimating soybean protein and lipid content using a non-destructive Raman HSI. Partial least squares regression (PLSR) techniques were used to develop the model using a calibration model based on 70% spectral data, and the remaining 30% of the data were used for validation. The results indicate that the Raman HSI, combined with PLSR, resulted in a protein and lipid model Rp2 of 0.90 and 0.82 with Root Mean Squared Error Prediction (RMSEP) 1.27 and 0.79, respectively. Additionally, this study successfully used the Raman HSI approach to create a prediction image showing the distribution of the targeted components, and could predict protein and lipid based on a single seeds.

Compact and automated sensing systems are needed to monitor plant health for NASA’s controlled-environment space crop production. A new hyperspectral system was designed for early detection of plant stresses using both reflectance and fluorescence imaging in visible and near-infrared (VNIR) wavelength range (400–1000 nm). The prototype system mainly includes two LED line lights providing VNIR broadband and UV-A (365 nm) light for reflectance and fluorescence measurement, respectively, a line-scan hyperspectral camera, and a linear motorized stage with a travel range of 80 cm. In an overhead sensor-to-sample arrangement, the stage translates the lights and camera over the plants to acquire reflectance and fluorescence images in sequence during one cycle of line-scan imaging. System software was developed using LabVIEW to realize hardware parameterization, data transfer, and automated imaging functions. The imaging unit was installed in a plant growth chamber at NASA Kennedy Space Center for health monitoring studies for pick-and-eat salad crops. A preliminary experiment was conducted to detect plant drought stress for twelve Dragoon lettuce samples, of which half were well-watered and half were under-watered while growing. A machine learning method using an optimized discriminant classifier based on VNIR reflectance spectra generated classification accuracies over 90% for the first four days of the stress treatment, showing great potential for early detection of the drought stress on lettuce leaves before any visible symptoms and size differences were evident. The system is promising to provide useful information for optimization of growth environment and early mitigation of stresses in space crop production.

Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.

Abstract Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.

Root rot of Panax ginseng caused by Cylindrocarpon destructans, a soil-borne fungus is typically diagnosed by frequently checking the ginseng plants or by evaluating soil pathogens in a farm, which is a time- and cost-intensive process. Because this disease causes huge economic losses to ginseng farmers, it is important to develop reliable and non-destructive techniques for early disease detection. In this study, we developed a non-destructive method for the early detection of root rot. For this, we used crop phenotyping and analyzed biochemical information collected using the HSI technique. Soil infected with root rot was divided into sterilized and infected groups and seeded with 1-year-old ginseng plants. HSI data were collected four times during weeks 7–10 after sowing. The spectral data were analyzed and the main wavelengths were extracted using partial least squares discriminant analysis. The average model accuracy was 84% in the visible/near-infrared region (29 main wavelengths) and 95% in the short-wave infrared (19 main wavelengths). These results indicated that root rot caused a decrease in nutrient absorption, leading to a decline in photosynthetic activity and the levels of carotenoids, starch, and sucrose. Wavelengths related to phenolic compounds can also be utilized for the early prediction of root rot. The technique presented in this study can be used for the early and timely detection of root rot in ginseng in a non-destructive manner.

Consumption of aflatoxin-contaminated food can cause severe illness when consumed by humans or livestock. Because the mycotoxin frequently occurs in cereal grains and other agricultural crops, it is crucial to develop portable devices that can be used non-destructively and in real-time to identify aflatoxin-contaminated food materials during early stages of harvesting or processing. In this study, an aflatoxin detection method was developed using a compact Raman device that can be used in the field. Data were obtained using maize samples naturally contaminated with aflatoxin, and the data were analyzed using a machine learning method. Of the multiple classification models evaluated, such as linear discriminant analysis (LDA), linear support vector machines (LSVM), quadratic discriminant analysis (QDA), and quadratic support vector machines and spectral preprocessing methods, the best classification accuracy was achieved at 95.7% using LDA in combination with Savitzky-Golay 2nd derivative (SG2) preprocessing. Partial least squares regression (PLSR) models demonstrated a close-range accuracy within the scope of standard normal variate (SNV) and multiplicative scatter correction (MSC) preprocessing methods, with determination of coefficient values of R2C and R2V of 0.9998 and 0.8322 respectively for SNV, and 0.9916 and 0.8387 respectively for MSC. This study demonstrates the potential use of compact and automated Raman spectroscopy, coupled with chemometrics and machine learning methods, as a tool for rapidly screening food and feed for hazardous substances at on-site field processing locations.

The food service industry must ensure that service facilities are free of foodborne pathogens hosted by organic residues and biofilms. Foodborne diseases put customers at risk and compromise the reputations of service providers. Fluorescence imaging, empowered by state-of-the-art artificial intelligence (AI) algorithms, can detect invisible residues. However, using AI requires large datasets that are most effective when collected from actual users, raising concerns about data privacy and possible leakage of sensitive information. In this study, we employed a decentralized privacy-preserving technology to address client data privacy issues. When federated learning (FL) is used, there is no need for data sharing across clients or data centralization on a server. We used FL and a new fluorescence imaging technology and applied two deep learning models, MobileNetv3 and DeepLabv3+, to identify and segment invisible residues on food preparation equipment and surfaces. We used FedML as our FL framework and Fedavg as the aggregation algorithm. The model achieved training and testing accuracies of 95.83% and 94.94% for classification between clean and contamination frames, respectively, and resulted in intersection over union (IoU) scores of 91.23% and 89.45% for training and testing, respectively, of segmentation of the contaminated areas. The results demonstrated that using federated learning combined with fluorescence imaging and deep learning algorithms can improve the performance of cleanliness auditing systems while assuring client data privacy.

Aflatoxins and fumonisins, commonly found in maize and maize-derived products, frequently co-occur and can cause dangerous illness in humans and animals if ingested in large amounts. Efforts are being made to develop suitable analytical methods for screening that can rapidly detect mycotoxins in order to prevent illness through early detection. A method for classifying contaminated maize by applying hyperspectral imaging techniques including reflectance in the visible and near-infrared (VNIR) and short-wave infrared (SWIR) regions, and fluorescence was investigated. Machine learning classification models in combination with different preprocessing methods were applied to screen ground maize samples for naturally occurring aflatoxin and fumonisin as single contaminants and as co-contaminants. Partial least squares–discriminant analysis (PLS-DA) and support vector machine (SVM) with the radial basis function (RBF) kernel were employed as classification models using cut-off values of each mycotoxin. The classification performance of the SVM was better than that of PLS-DA, and the highest classification accuracies for fluorescence, VNIR, and SWIR were 89.1%, 71.7%, and 95.7%, respectively. SWIR imaging with the SVM model resulted in higher classification accuracies compared to the fluorescence and VNIR models, suggesting that as an alternative to conventional wet chemical methods, the hyperspectral SWIR imaging detection model may be the more effective and efficient analytical tool for mycotoxin analysis compared to fluorescence or VNIR imaging models. These methods represent a food safety screening tool capable of rapidly detecting mycotoxins in maize or other food ingredients consumed by animals or humans.

Precise, reliable, and speedy contamination detection and disinfection is an ongoing challenge for the food-service industry. Contamination in food-related services can cause foodborne illness, endangering customers and jeopardizing provider reputations. Fluorescence imaging has been shown to be capable of identifying organic residues and biofilms that can host pathogens. We use new fluorescence imaging technology, applying Xception and DeepLabv3+ deep learning algorithms to identify and segment contaminated areas in images of equipment and surfaces. Deep learning models demonstrated a 98.78% accuracy for differentiation between clean and contaminated frames on various surfaces and resulted in an intersection over union (IoU) score of 95.13% for the segmentation of contamination. The portable imaging system’s intrinsic disinfection capability was evaluated on S. enterica, E. coli, and L. monocytogenes, resulting in up to 8-log reductions in under 5 s. Results showed that fluorescence imaging with deep learning algorithms could help assure safety and cleanliness in the food-service industry.

This study demonstrates a method to select wavelength-specific spectral resolutions to optimize a line-scan hyperspectral imaging method for its intended use, which in this case was visible/near-infrared imaging-based multiple-waveband detection of apple bruises. Many earlier studies have explored important aspects of developing apple bruise detection systems, such as key wavelengths and image processing algorithms. Despite the endeavors of many, development of a real-time bruise detection system is not yet a simple task. To overcome these problems, this study investigated selection of optimal wavelength-specific spectral resolutions for detecting bruises on apples by using hyperspectral line-scan imaging with the Random Track function for non-contiguous partial readout, with two experimental parts. The first part identified key-wavelengths and the optimal number of key-wavelengths to use for detecting low-, medium-, and high-impact bruises on apples. These parameters were determined by principal component analysis (PCA) and sequential forward selection (SFS) with four classification methods. The second part determined the optimal spectral resolution for each of the key-wavelengths by selecting and evaluating 21 combinations of exposure time and key-wavelength bandwidths, and then selecting the best combination based on the bruise detection accuracies achieved by each classification method. Each of the four classification methods was found to have a different optimized resolution for high accuracy bruise detection, and the optimized resolutions also allowed for use of shorter exposure times. The results of this work can be used to help develop multispectral imaging systems that provide rapid, cost-effective post-harvest processing to identify bruised apples on commercial processing lines.

Melamine and its derivative, cyanuric acid, are occasionally added to pet meals because of their nitrogen-rich qualities, leading to the development of several health-related issues. A nondestructive sensing technique that offers effective detection must be developed to address this problem. In conjunction with machine learning and deep learning technique, Fourier transform infrared (FT-IR) spectroscopy was employed in this investigation for the nondestructive quantitative measurement of eight different concentrations of melamine and cyanuric acid added to pet food. The effectiveness of the one-dimensional convolutional neural network (1D CNN) technique was compared with that of partial least squares regression (PLSR), principal component regression (PCR), and a net analyte signal (NAS)-based methodology, called hybrid linear analysis (HLA/GO). The 1D CNN model developed for the FT-IR spectra attained correlation coefficients of 0.995 and 0.994 and root mean square error of prediction values of 0.090% and 0.110% for the prediction datasets on the melamine- and cyanuric acid-contaminated pet food samples, respectively, which were superior to those of the PLSR and PCR models. Therefore, when FT-IR spectroscopy is employed in conjunction with a 1D CNN model, it serves as a potentially rapid and nondestructive method for identifying toxic chemicals added to pet food.

This study is directed towards developing a fast, non-destructive, and easy-to-use handheld multimode spectroscopic system for fish quality assessment. We apply data fusion of visible near infra-red (VIS-NIR) and short wave infra-red (SWIR) reflectance and fluorescence (FL) spectroscopy data features to classify fish from fresh to spoiled condition. Farmed Atlantic and wild coho and chinook salmon and sablefish fillets were measured. Three hundred measurement points on each of four fillets were taken every two days over 14 days for a total of 8400 measurements for each spectral mode. Multiple machine learning techniques including principal component analysis, self-organized maps, linear and quadratic discriminant analyses, k-nearest neighbors, random forest, support vector machine, and linear regression, as well as ensemble and majority voting methods, were used to explore spectroscopy data measured on fillets and to train classification models to predict freshness. Our results show that multi-mode spectroscopy achieves 95% accuracy, improving the accuracies of the FL, VIS-NIR and SWIR single-mode spectroscopies by 26, 10 and 9%, respectively. We conclude that multi-mode spectroscopy and data fusion analysis has the potential to accurately assess freshness and predict shelf life for fish fillets and recommend this study be expanded to a larger number of species in the future.

Watermelon (Citrullus lanatus) is a widely consumed, nutritious fruit, rich in water and sugars. In most crops, abiotic stresses caused by changes in temperature, moisture, etc., are a significant challenge during production. Due to the temperature sensitivity of watermelon plants, temperatures must be closely monitored and controlled when the crop is cultivated in controlled environments. Studies have found direct responses to these stresses include reductions in leaf size, number of leaves, and plant size. Stress diagnosis based on plant morphological features (e.g., shape, color, and texture) is important for phenomics studies. The purpose of this study is to classify watermelon plants exposed to low-temperature stress conditions from the normal ones using features extracted using image analysis. In addition, an attempt was made to develop a model for estimating the number of leaves and plant age (in weeks) using the extracted features. A model was developed that can classify normal and low-temperature stress watermelon plants with 100% accuracy. The R2, RMSE, and mean absolute difference (MAD) of the predictive model for the number of leaves were 0.94, 0.87, and 0.88, respectively, and the R2 and RMSE of the model for estimating the plant age were 0.92 and 0.29 weeks, respectively. The models developed in this study can be utilized in high-throughput phenotyping systems for growth monitoring and analysis of phenotypic traits during watermelon cultivation.

The key elements that underpin food security require the adaptation of agricultural systems to support productivity increases while minimizing inputs and the adverse effects of climate change. The advances in precision agriculture over the past few years have substantially enhanced the efficiency of applying spatially variable agronomic inputs for irrigation, such as fertilizers, pesticides, seeds, and water, and we can attribute them to the increasing number of innovations that utilize new technologies that are capable of monitoring field crops for varying spatial and temporal changes. Remote sensing technology is the primary driver of success in precision agriculture, along with other technologies, such as the Internet of Things (IoT), robotic systems, weather forecasting technology, and global positioning systems (GPSs). More specifically, multispectral imaging (MSI) and hyperspectral imaging (HSI) have made the monitoring of the field crop health to aid decision making and the application of spatially and temporally variable agronomic inputs possible. Furthermore, the fusion of remotely sensed multisource data—for instance, HSI and LiDAR (light detection and ranging) data fusion—has even made it possible to monitor the changes in different parts of an individual plant. To the best of our knowledge, in most reviews on this topic, the authors focus on specific methods and/or technologies, with few or no comprehensive reviews that expose researchers, and especially students, to the vast possible range of remote sensing technologies used in agriculture. In this article, we describe/evaluate the remote sensing (RS) technologies for field crop monitoring using spectral imaging, and we provide a thorough and discipline-specific starting point for researchers of different levels by supplying sufficient details and references. We also high light strengths and drawbacks of each technology, which will help readers select the most appropriate method for their intended uses.

Ginseng is a perennial herbaceous plant that has been widely consumed for medicinal and dietary purposes since ancient times. Ginseng plants require shade and cool temperatures for better growth; climate warming and rising heat waves have a negative impact on the plants’ productivity and yield quality. Since Republic of Korea’s temperature is increasing beyond normal expectations and is seriously threatening ginseng plants, an early-stage non-destructive diagnosis of stressed ginseng plants is essential before symptomatic manifestation to produce high-quality ginseng roots. This study demonstrated the potential of fluorescence hyperspectral imaging to achieve the early high-throughput detection and prediction of chlorophyll composition in four varieties of heat-stressed ginseng plants: Chunpoong, Jakyeong, Sunil, and Sunmyoung. Hyperspectral imaging data of 80 plants from these four varieties (temperature-sensitive and temperature-resistant) were acquired before and after exposing the plants to heat stress. Additionally, a SPAD-502 meter was used for the non-destructive measurement of the greenness level. In accordance, the mean spectral data of each leaf were extracted from the region of interest (ROI). Analysis of variance (ANOVA) was applied for the discrimination of heat-stressed plants, which was performed with 96% accuracy. Accordingly, the extracted spectral data were used to develop a partial least squares regression (PLSR) model combined with multiple preprocessing techniques for predicting greenness composition in ginseng plants that significantly correlates with chlorophyll concentration. The results obtained from PLSR analysis demonstrated higher determination coefficients of R2val = 0.90, and a root mean square error (RMSE) of 3.59%. Furthermore, five proposed bands (683 nm, 688 nm, 703 nm, 731 nm, and 745 nm) by stepwise regression (SR) were developed into a PLSR model, and the model coefficients were used to create a greenness-level concentration in images that showed differences between the control and heat-stressed plants for all varieties.

Strawberry (Fragaria × ananassa Duch) plants are vulnerable to climatic change. The strawberry plants suffer from heat and water stress eventually, and the effects are reflected in the development and yields. In this investigation, potential chlorophyll-fluorescence-based indices were selected to detect the early heat and water stress in strawberry plants. The hyperspectral images were used to capture the fluorescence reflectance in the range of 500 nm–900 nm. From the hyperspectral cube, the region of interest (leaves) was identified, followed by the extraction of eight chlorophyll-fluorescence indices from the region of interest (leaves). These eight chlorophyll-fluorescence indices were analyzed deeply to identify the best indicators for our objective. The indices were used to develop machine-learning models to assess the performance of the indicators by accuracy assessment. The overall procedure is proposed as a new workflow for determining strawberry plants’ early heat and water stress. The proposed workflow suggests that by including all eight indices, the random-forest classifier performs well, with an accuracy of 94%. With this combination of the potential indices, namely the red-edge vegetation stress index (RVSI), chlorophyll B (Chl-b), pigment-specific simple ratio for chlorophyll B (PSSRb), and the red-edge chlorophyll index (CIREDEDGE), the gradient-boosting classifier performs well, with an accuracy of 91%. The proposed workflow works well with a limited number of training samples which is an added advantage.

The increasing interest in plant phenolic compounds in the past few years has become necessary because of their several important physicochemical properties. Thus, their identification through non-destructive methods has become crucial. This study carried out comparative non-destructive measurements of Arabidopsis thaliana leaf powder sample phenolic compounds using Fourier-transform infrared and near-infrared spectroscopic techniques under six distinct stress conditions. The prediction analysis of 600 leaf powder samples under different stress conditions (LED lights and drought) was performed using PLSR, PCR, and NAS-based HLA/GO regression analysis methods. The results obtained through FT-NIR spectroscopy yielded the highest correlation coefficient (Rp2) value of 0.999, with a minimum error (RMSEP) value of 0.003 mg/g, based on the PLSR model using the MSC preprocessing method, which was slightly better than the correlation coefficient (Rp2) value of 0.980 with an error (RMSEP) value of 0.055 mg/g for FT-IR spectroscopy. Additionally, beta coefficient plots present spectral differences and the identification of important spectral signatures sensitive to the phenolic compounds in the measured powdered samples. Thus, the obtained results demonstrated that FT-NIR spectroscopy combined with partial least squares regression (PLSR) and suitable preprocessing method has a solid potential for non-destructively predicting phenolic compounds in Arabidopsis thaliana leaf powder samples.

Ginseng is an important medicinal plant in Korea. The roots of the ginseng plant have medicinal properties; thus, it is very important to maintain the quality of ginseng roots. Root rot disease is a major disease that affects the quality of ginseng roots. It is important to predict this disease before it causes severe damage to the plants. Hence, there is a need for a non-destructive method to identify root rot disease in ginseng plants. In this paper, a method to identify the root rot disease by analyzing the RGB plant images using image processing and deep learning is proposed. Initially, plant segmentation is performed, and then the noise regions are removed in the plant images. These images are given as input to the proposed linear deep learning model to identify root rot disease in ginseng plants. Transfer learning models are also applied to these images. The performance of the proposed method is promising in identifying root rot disease.

Ensuring the quality of fresh-cut vegetables is the greatest challenge for the food industry and is equally as important to consumers (and their health). Several investigations have proven the necessity of advanced technology for detecting foreign materials (FMs) in fresh-cut vegetables. In this study, the possibility of using near infrared spectral analysis as a potential technique was investigated to identify various types of FMs in seven common fresh-cut vegetables by selecting important wavebands. Various waveband selection methods, such as the weighted regression coefficient (WRC), variable importance in projection (VIP), sequential feature selection (SFS), successive projection algorithm (SPA), and interval PLS (iPLS), were used to investigate the optimal multispectral wavebands to classify the FMs and vegetables. The application of selected wavebands was further tested using NIR imaging, and the results showed good potentiality by identifying 99 out of 107 FMs. The results indicate the high applicability of the multispectral NIR imaging technique to detect FMs in fresh-cut vegetables for industrial application.

The demand for rapid and nondestructive methods to determine chemical components in food and agricultural products is proliferating due to being beneficial for screening food quality. This research investigates the feasibility of Fourier transform near-infrared (FT-NIR) and Fourier transform infrared spectroscopy (FT-IR) to predict total as well as an individual type of isoflavones and oligosaccharides using intact soybean samples. A partial least square regression method was performed to develop models based on the spectral data of 310 soybean samples, which were synchronized to the reference values evaluated using a conventional assay. Furthermore, the obtained models were tested using soybean varieties not initially involved in the model construction. As a result, the best prediction models of FT-NIR were allowed to predict total isoflavones and oligosaccharides using intact seeds with acceptable performance (R2p: 0.80 and 0.72), which were slightly better than the model obtained based on FT-IR data (R2p: 0.73 and 0.70). The results also demonstrate the possibility of using FT-NIR to predict individual types of evaluated components, denoted by acceptable performance values of prediction model (R2p) of over 0.70. In addition, the result of the testing model proved the model’s performance by obtaining a similar R2 and error to the calibration model.

To minimize production costs, reduce mistakes, and improve consistency, modern-day slaughterhouses have turned to automated technologies for operations such as cutting, deboning, etc. One of the most vital operations in the slaughterhouse is carcass grading, usually performed manually by grading staff, which creates a bottleneck in terms of production speed and consistency. To speed up the carcass grading process, we developed an online system that uses image analysis and statistical tools to estimate up to 23 key yield parameters. A thorough economic analysis is required to aid slaughterhouses in making informed decisions about the risks and benefits of investing in the system. We therefore conducted an economic analysis of the system using a cost-benefit analysis (the methods considered were net present value (NPV), internal rate of return (IRR), and benefit/cost ratio (BCR)) and sensitivity analysis. The benefits considered for analysis include labor cost reduction and gross margin improvement arising from optimizing breeding practices with the use of the data obtained from the system. The cost-benefit analysis of the system resulted in an NPV of approximately 310.9 million Korean Won (KRW), a BCR of 1.72, and an IRR of 22.28%, which means the benefits outweigh the costs in the long term.

This study performed non-destructive measurements of phenolic compounds in moringa powder using Fourier Transform Infrared (FT-IR) spectroscopy within a spectral range of 3500–700 cm−1. Three major phenolic compounds, namely, kaempferol, benzoic acid, and rutin, were measured in five different varieties of moringa powder, which was approved with respect to the high-performance liquid chromatography (HPLC) method. The prediction performance of three different regression methods, i.e., partial least squares regression (PLSR), principal component regression (PCR), and net analyte signal (NAS)-based methodology, called hybrid linear analysis (HLA/GO), were compared to achieve the best prediction model. The obtained results for the PLS regression method resulted in better performance for the prediction analysis of phenolic compounds in moringa powder. The PLSR model attained a correlation coefficient (Rp2) value of 0.997 and root mean square error of prediction (RMSEP) of 0.035 mg/g, respectively, which is comparatively higher than the other two regression models. Based on the results, it can be concluded that FT-IR spectroscopy in conjugation with a suitable regression analysis method could be an effective analytical tool for the non-destructive prediction of phenolic compounds in moringa powder.

Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to collect images in multiple wavelengths. This paper proposes a new methodology to support the design of a hypothesized system that uses three imaging modes—fluorescence, visible/near-infrared (VNIR) reflectance, and shortwave infrared (SWIR) reflectance—to capture narrow-band spectral data at only three to seven narrow wavelengths. Simulated annealing is applied to identify the optimal wavelengths for sparse spectral measurement with a cost function based on the accuracy provided by a weighted k-nearest neighbors (WKNN) classifier, a common and relatively robust machine learning classifier. Two separate classification approaches are presented, the first using a multi-layer perceptron (MLP) artificial neural network trained on sparse data from the three individual spectra and the second using a fusion of the data from all three spectra. The results are compared with those from four alternative classifiers based on common machine learning algorithms. To validate the proposed methodology, reflectance and fluorescence spectra in these three spectroscopic modes were collected from fish fillets and used to classify the fillets by species. Accuracies determined from the two classification approaches are compared with benchmark values derived by training the classifiers with the full resolution spectral data. The results of the single-layer classification study show accuracies ranging from ~68% for SWIR reflectance to ~90% for fluorescence with just seven wavelengths. The results of the fusion classification study show accuracies of about 95% with seven wavelengths and more than 90% even with just three wavelengths. Reducing the number of required wavelengths facilitates the creation of rapid and cost-effective spectral imaging systems that can be used for widespread analysis in food monitoring/food fraud, agricultural, and biomedical applications.

Contamination inspection is an ongoing concern for food distributors, restaurant owners, caterers, and others who handle food. Food contamination must be prevented, and zero tolerance legal requirements and damage to the reputation of institutions or restaurants can be very costly. This paper introduces a new handheld fluorescence-based imaging system that can rapidly detect, disinfect, and document invisible organic residues and biofilms which may host pathogens. The contamination, sanitization inspection, and disinfection (CSI-D) system uses light at two fluorescence excitation wavelengths, ultraviolet C (UVC) at 275 nm and violet at 405 nm, for the detection of organic residues, including saliva and respiratory droplets. The 275 nm light is also utilized to disinfect pathogens commonly found within the contaminated residues. Efficacy testing of the neutralizing effects of the ultraviolet light was conducted for Aspergillus fumigatus, Streptococcus pneumoniae, and the influenza A virus (a fungus, a bacterium, and a virus, respectively, each commonly found in saliva and respiratory droplets). After the exposure to UVC light from the CSI-D, all three pathogens experienced deactivation (> 99.99%) in under ten seconds. Up to five-log reductions have also been shown within 10 s of UVC irradiation from the CSI-D system.

Excessive addition of food waste fertilizer to organic fertilizer (OF) is forbidden in the Republic of Korea because of high sodium chloride and capsaicin concentrations in Korean food. Thus, rapid and nondestructive evaluation techniques are required. The objective of this study is to quantitatively evaluate food-waste components (FWCs) using hyperspectral imaging (HSI) in the visible–near-infrared (Vis/NIR) region. A HSI system for evaluating fertilizer components and prediction algorithms based on partial least squares (PLS) analysis and least squares support vector machines (LS-SVM) are developed. PLS and LS-SVM preprocessing methods are employed and compared to select the optimal of two chemometrics methods. Finally, distribution maps visualized using the LS-SVM model are created to interpret the dynamic changes in the OF FWCs with increasing FWC concentration. The developed model quantitively evaluates the OF FWCs with a coefficient of determination of 0.83 between the predicted and actual values. The developed Vis/NIR HIS system and optimized model exhibit high potential for OF FWC discrimination and quantitative evaluation.

Panax ginseng has been used as a traditional medicine to strengthen human health for centuries. Over the last decade, significant agronomical progress has been made in the development of elite ginseng cultivars, increasing their production and quality. However, as one of the significant environmental factors, heat stress remains a challenge and poses a significant threat to ginseng plants’ growth and sustainable production. This study was conducted to investigate the phenotype of ginseng leaves under heat stress using hyperspectral imaging (HSI). A visible/near-infrared (Vis/NIR) and short-wave infrared (SWIR) HSI system were used to acquire hyperspectral images for normal and heat stress-exposed plants, showing their susceptibility (Chunpoong) and resistibility (Sunmyoung and Sunil). The acquired hyperspectral images were analyzed using the partial least squares-discriminant analysis (PLS-DA) technique, combining the variable importance in projection and successive projection algorithm methods. The correlation of each group was verified using linear discriminant analysis. The developed models showed 12 bands over 79.2% accuracy in Vis/NIR and 18 bands with over 98.9% accuracy at SWIR in validation data. The constructed beta-coefficient allowed the observation of the key wavebands and peaks linked to the chlorophyll, nitrogen, fatty acid, sugar and protein content regions, which differentiated normal and stressed plants. This result shows that the HSI with the PLS-DA technique significantly differentiated between the heat-stressed susceptibility and resistibility of ginseng plants with high accuracy.

Plant phenomics has been rapidly advancing over the past few years. This advancement is attributed to the increased innovation and availability of new technologies which can enable the high-throughput phenotyping of complex plant traits. The application of artificial intelligence in various domains of science has also grown exponentially in recent years. Notably, the computer vision, machine learning, and deep learning aspects of artificial intelligence have been successfully integrated into non-invasive imaging techniques. This integration is gradually improving the efficiency of data collection and analysis through the application of machine and deep learning for robust image analysis. In addition, artificial intelligence has fostered the development of software and tools applied in field phenotyping for data collection and management. These include open-source devices and tools which are enabling community driven research and data-sharing, thereby availing the large amounts of data required for the accurate study of phenotypes. This paper reviews more than one hundred current state-of-the-art papers concerning AI-applied plant phenotyping published between 2010 and 2020. It provides an overview of current phenotyping technologies and the ongoing integration of artificial intelligence into plant phenotyping. Lastly, the limitations of the current approaches/methods and future directions are discussed.

With increasing public demand for ready-to-eat fresh-cut food products, proper sanitation of food-processing equipment surfaces is essential to mitigate potential contamination of these products to ensure safe consumption. This study presents a sanitation monitoring technique using hyperspectral fluorescence images to detect fruit residues on food-processing equipment surfaces. An algorithm to detect residues on the surfaces of 2B-finished and #4-finished stainless-steel, both commonly used in food processing equipment, was developed. Honeydew, orange, apple, and watermelon were selected as representatives since they are mainly used as fresh-cut fruits. Hyperspectral fluorescence images were obtained for stainless steel sheets to which droplets of selected fruit juices at six concentrations were applied and allowed to dry. The most significant wavelengths for detecting juice at each concentration were selected through ANOVA analysis. Algorithms using a single waveband and using a ratio of two wavebands were developed for each sample and for all the samples combined. Results showed that detection accuracies were better for the samples with higher concentrations. The integrated algorithm had a detection accuracy of 100% and above 95%, respectively, for the original juice up to the 1:20 diluted samples and for the more dilute 1:50 to 1:100 samples, respectively. The results of this study establish that using hyperspectral imaging, even a small residual quantity that may exist on the surface of food processing equipment can be detected and that sanitation monitoring and management is possible.

Geographical origin discrimination of white rice is an important endeavor in preventing illegal distribution of white rice and regulating and standardizing food safety and quality assurance. The aim of this study was to develop a method for geographical origin discrimination between South Korean and Chinese rice using a hyperspectral fluorescence imaging technique and multivariate analysis. Hyperspectral fluorescence images of South Korean and Chinese rice samples were obtained in the wavelength range of 420 nm to 780 nm with intervals of 4.8 nm using 365 nm wavelength ultraviolet-A excitation light. Partial least squares discriminant analysis models were developed and applied to the acquired image to determine the geographical origins of the rice samples. In addition, various pre-processing techniques were applied to improve the discrimination accuracy. Accordingly, the pixel size of the hyperspectral image was determined. The results revealed that the optimum pixel size of the hyperspectral image that was above 7 mm × 7 mm showed a high discrimination accuracy. Moreover, the geographical origin discrimination model that applied the first-order derivative achieved a high discrimination accuracy of 98.89%. The results of this study showed that hyperspectral fluorescence imaging technology can be used to quickly and accurately discriminate the geographical origins of white rice.

Methods that combine targeted techniques and chemometrics for analyzing food authenticity can only facilitate the detection of predefined or known adulterants, while unknown adulterants cannot be detected using such methods. Therefore, the non-targeted detection of adulterants in food products is currently in great demand. In this study, FT-IR and FT-NIR spectroscopic techniques were used in combination with non-targeted chemometric approaches, such as one-class partial least squares (OCPLS) and data-driven soft independent modeling of class analogy (DD-SIMCA), to detect adulterants in almond powder adulterated with apricot and peanut powders. The reflectance spectra of 100 pure almond powder samples from two different varieties (50 each) were collected to develop a calibration model based on each spectroscopic technique; each model was then evaluated for four independent sets of two varieties of almond powder samples adulterated with different concentrations of apricot and peanut powders. Classification using both techniques was highly sensitive, the OCPLS approach yielded 90–100% accuracy in different varieties of samples with both spectroscopic techniques, and the DD-SIMCA approach achieved the highest accuracy of 100% when used in combination with FT-IR in all validation sets. Moreover, DD-SIMCA, combined with FT-NIR, achieved a detection accuracy between 91% and 100% for the different validation sets and the misclassified samples belong to the 5% and 7% adulteration sets. These results suggest that spectroscopic techniques, combined with one-class classifiers, can be used effectively in the high-throughput screening of potential adulterants in almond powder.

This study provides detailed information about the use of a hyperspectral imaging system mounted on a motor-driven multipurpose floating platform (MFP) for water quality sensing and water sampling, including the spatial and spectral calibration for the camera, image acquisition and correction procedures. To evaluate chlorophyll-a concentrations in an irrigation pond, visible/near-infrared hyperspectral images of the water were acquired as the MFP traveled to ten water sampling locations along the length of the pond, and dimensionality reduction with correlation analysis was performed to relate the image data to the measured chlorophyll-a data. About 80,000 sample images were acquired by the line-scan method. Image processing was used to remove sun-glint areas present in the raw hyperspectral images before further analysis was conducted by principal component analysis (PCA) to extract three key wavelengths (662 nm, 702 nm, and 752 nm) for detecting chlorophyll-a in irrigation water. Spectral intensities at the key wavelengths were used as inputs to two near-infrared (NIR)-red models. The determination coefficients (R2) of the two models were found to be about 0.83 and 0.81. The results show that hyperspectral imagery from low heights can provide valuable information about water quality in a fresh water source.

The grading of ginseng (Panax ginseng) including the evaluation of internal quality attributes is essential in the ginseng industry for quality control. Assessment for inner whitening, a major internal disorder, must be conducted when identifying high quality ginseng. Conventional methods for detecting inner whitening in ginseng root samples use manual inspection, which is time-consuming and inaccurate. This study develops an internal quality measurement technique using near-infrared transmittance spectral imaging to evaluate inner whitening in ginseng samples. Principle component analysis (PCA) was used on ginseng hypercube data to evaluate the developed technique. The transmittance spectra and spectral images of ginseng samples exhibiting inner whitening showed weak intensity characteristics compared to normal ginseng in the region of 900−1050 nm and 1150−1400 nm respectively, owing to the presence of whitish internal tissues that have higher optical density. On the basis of the multivariate analysis method, even a simple waveband ratio image has the great potential to quickly detect inner whitening in ginseng samples, since these ratio images show a significant difference between whitened and non-whitened regions. Therefore, it is possible to develop an efficient and rapid spectral imaging system for the real-time detection of inner whitening in ginseng using minimal spectral wavebands. This novel strategy for the rapid, cost-effective, non-destructive detection of ginseng’s inner quality can be a key component for the automation of ginseng grading.

Rapid and reliable inspection of food is essential to ensure food safety, particularly in mass production and processing environments. Many studies have focused on spectral imaging for poultry inspection; however, no research has explored the use of multispectral fluorescence imaging (MFI) for on-line poultry inspection. In this study, the feasibility of MFI for on-line detection of fecal matter from the ceca, colon, duodenum, and small intestine of poultry carcasses was investigated for the first time. A multispectral line-scan fluorescence imaging system was integrated with a commercial poultry conveying system, and the images of chicken carcasses with fecal contaminants were scanned at processing line speeds of one, three, and five birds per second. To develop an optimal detection and classification algorithm to distinguish upper and lower feces-contaminated parts from skin, the principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) were first performed using the spectral data of the selected regions, and then applied in spatial domain to visualize the feces-contaminated area based on binary images. Our results demonstrated that for the spectral data analysis, both the PCA and PLS-DA can distinguish the high and low feces-contaminated area from normal skin; however, the PCA analysis based on selected band ratio images (F630 nm/F600 nm) exhibited better visualization and discrimination of feces-contaminated area, compared with the PLS-DA-based developed chemical images. A color image analysis using histogram equalization, sharpening, median filter, and threshold value (1) demonstrated 78% accuracy. Thus, the MFI system can be developed utilizing the two band ratios for on-line implementation for the effective detection of fecal contamination on chicken carcasses.

The inspection of rice grain that may be infected by seedborne disease is important for ensuring uniform plant stands in production fields as well as preventing proliferation of some seedborne diseases. The goal of this study was to use a hyperspectral imaging (HSI) technique to find optimal wavelengths and develop a model for detecting discolored, diseased rice seed infected by bacterial panicle blight (Burkholderia glumae), a seedborne pathogen. For this purpose, the HSI data spanning the visible/near-infrared wavelength region between 400 and 1000 nm were collected for 500 sound and discolored rice seeds. For selecting optimal wavelengths to use for detecting diseased seed, a sequential forward selection (SFS) method combined with various spectral pretreatments was employed. To evaluate performance based on optimal wavelengths, support vector machine (SVM) and linear and quadratic discriminant analysis (LDA and QDA) models were developed for detection of discolored seeds. As a result, the violet and red regions of the visible spectrum were selected as key wavelengths reflecting the characteristics of the discolored rice seeds. When using only two or only three selected wavelengths, all of the classification methods achieved high classification accuracies over 90% for both the calibration and validation sample sets. The results of the study showed that only two to three wavelengths are needed to differentiate between discolored, diseased and sound rice, instead of using the entire HSI wavelength regions. This demonstrates the feasibility of developing a low cost multispectral imaging technology based on these selected wavelengths for non-destructive and high-throughput screening of diseased rice seed.

Viability is an important quality factor influencing seed germination and crop yield. Current seed-viability testing methods rely on conventional manual inspections, which use destructive, labor-intensive and time-consuming measurements. The aim of this study is to distinguish between viable and nonviable soybean seeds, using a near-infrared (NIR) hyperspectral imaging (HSI) technique in a rapid and nondestructive manner. The data extracted from the NIR–HSI of viable and nonviable soybean seeds were analyzed using a partial least-squares discrimination analysis (PLS-DA) technique for classifying the viable and nonviable soybean seeds. Variable importance in projection (VIP) was used as a waveband selection method to develop a multispectral imaging model. Initially, the spectral profile of each pixel in the soybean seed images was subjected to PLS-DA analysis, which yielded a reasonable classification accuracy; however, the pixel-based classification method was not successful for high accuracy detection for nonviable seeds. Another viability detection method was then investigated: a kernel image threshold method with an optimum-detection-rate strategy. The kernel-based classification of seeds showed over 95% accuracy even when using only seven optimal wavebands selected through VIP. The results show that the proposed multispectral NIR imaging method is an effective and accurate nondestructive technique for the discrimination of soybean seed viability.

A novel multimodal optical sensing system was developed for automated and intelligent food safety inspection. The system uses two pairs of compact point lasers and dispersive spectrometers at 785 and 1064 nm to realize dual-band Raman spectroscopy and imaging, which is suitable to measure samples generating low- and high-fluorescence interference signals, respectively. Automated spectral acquisition can be performed using a direct-drive XY moving stage for solid, powder, and liquid samples placed in customized well plates or randomly scattered in standard Petri dishes (e.g., bacterial colonies). Three LED lights (white backlight, UV ring light, and white ring light) and two miniature color cameras are used for machine vision measurements of samples in the Petri dishes using different combinations of illuminations and imaging modalities (e.g., transmission, fluorescence, and color). Real-time image processing and motion control techniques are used to implement automated sample counting, positioning, sampling, and synchronization functions. System software was developed using LabVIEW with integrated artificial intelligence functions able to identify and label interesting targets instantly. The system capability was demonstrated by an example application for rapid identification of five common foodborne bacteria, including Bacillus cereus, E. coli, Listeria monocytogenes, Staphylococcus aureus, and Salmonella spp. Using a machine learning model based on a linear support vector machine, a classification accuracy of 98.6% was achieved using Raman spectra automatically collected from 222 bacterial colonies of the five species grown on nutrient nonselective agar in 90 mm Petri dishes. The entire system was built on a 30Ã--45 cm2 breadboard, enabling it compact and portable and its use for field and on-site biological and chemical food safety inspection in regulatory and industrial applications. [ABSTRACT FROM AUTHOR]