Hyperspectral imaging for seed quality and safety inspection: a review

An exploration of the influence of ZnO NPs treatment on germination of radish seeds under salt stress based on the YOLOv8-R lightweight model

BACKGROUND

Since traditional germination test methods have drawbacks such as slow efficiency, proneness to error, and damage to seeds, a non-destructive testing method is proposed for full-process germination of radish seeds, which improves the monitoring efficiency of seed quality.

RESULTS

Based on YOLOv8n, a lightweight test model YOLOv8-R is proposed, where the number of parameters, the amount of calculation, and size of weights are significantly reduced by replacing the backbone network with PP-LCNet, the neck part with CCFM, the C2f of the neck part with OREPA, the SPPF with FocalModulation, and the Detect of the head part with LADH. The ablation test and comparative test prove the performance of the model. With adoption of germination rate, germination index, and germination potential as the three vitality indicators, the seed germination phenotype collection system and YOLOv8-R model are used to analyze the full time-series sequence effects of different ZnO NPs concentrations on germination of radish seeds under varying degrees of salt stress.

CONCLUSIONS

The results show that salt stress inhibits the germination of radish seeds and that the inhibition effect is more obvious with the increased concentration of NaCl solution; in cultivation with deionized water, the germination rate of radish seeds does not change significantly with increased concentration of ZnO NPs, but the germination index and germination potential increase initially and then decline; in cultivation with NaCl solution, the germination rate, germination potential and germination index of radish seeds first increase and then decline with increased concentration of ZnO NPs.

A LIBSVM quality assessment model for apple spoilage during storage based on hyperspectral data

To assess the quality of apple samples during storage, this study proposes a spoilage benchmark based on hyperspectral data feature indicators and the Mahalanobis Distance (MD). Additionally, a quality assessment model was developed utilizing LIB Support Vector Machine (LIBSVM). Initially, a spoilage benchmark for apple samples was preliminarily established using hyperspectral data feature indicators, including the color feature, texture feature of sample hyperspectral images, and wavelet packet energy (WPE) of sample spectral information. Secondly, this study utilized the successive projection algorithm (SPA) to extract three wavelength sets sensitive to changes in the three indicators. This process resulted in the identification of 20 feature wavelengths based on the three sets. Subsequently, the spoilage benchmark for apple samples was verified using MD based on the spectral information of feature wavelengths. Ultimately, utilizing pre-processed spectral information enhanced by the sliding window algorithm and spoilage benchmark, the LIBSVM quality assessment model was developed, achieving a training set accuracy of 99.94% and a test set accuracy of 99.66%. Moreover, to assess the strength and applicability of the model, a verification experiment was conducted using a different set of apple samples. The training set accuracy was 100% and the test set accuracy was 99.83%. These findings indicate that the model can effectively indicate the level of spoilage in each sample during long-term storage. This also serves to demonstrate the robustness of the model and the effectiveness of the spoilage benchmark determination method during apple storage.

A novel method combining deep learning with the Kennard-Stone algorithm for training dataset selection for image-based rice seed variety identification

BACKGROUND

Different varieties of rice vary in planting time, stress resistance, and other characteristics. With advances in rice-breeding technology, the number of rice varieties has increased significantly, making variety identification crucial for both trading and planting.

RESULTS

This study collected RGB images of 20 hybrid rice seed varieties. An enhanced deep super-resolution network (EDSR) was employed to enhance image resolution, and a variety classification model utilizing the high-resolution dataset demonstrated superior performance to that of the model using the low-resolution dataset. A novel training sample selection methodology was introduced integrating deep learning with the Kennard-Stone (KS) algorithm. Convolutional neural networks (CNN) and autoencoders served as supervised and unsupervised feature extractors, respectively. The extracted feature vectors were subsequently processed by the KS algorithm to select training samples. The proposed methodologies exhibited superior performance over the random selection approach in rice variety classification, with an approximately 10.08% improvement in overall classification accuracy. Furthermore, the impact of noise on the proposed methodology was investigated by introducing noise to the images, and the proposed methodologies maintained superior performance relative to the random selection approach on the noisy image dataset.

CONCLUSION

The experimental results indicate that both supervised and unsupervised learning models performed effectively as feature extractors, and the deep learning framework significantly influenced the selection of training set samples. This study presents a novel approach for training sample selection in classification tasks and suggests the potential for extending the proposed method to image datasets and other types of datasets. Further exploration of this potential is warranted. © 2024 Society of Chemical Industry.

Cotton seed cultivar identification based on the fusion of spectral and textural features

The mixing of cotton seeds of different cultivars and qualities can lead to differences in growth conditions and make field management difficult. In particular, except for yield loss, it can also lead to inconsistent cotton quality and poor textile product quality, causing huge economic losses to farmers and the cotton processing industry. However, traditional cultivar identification methods for cotton seeds are time-consuming, labor-intensive, and cumbersome, which cannot meet the needs of modern agriculture and modern cotton processing industry. Therefore, there is an urgent need for a fast, accurate, and non-destructive method for identifying cotton seed cultivars. In this study, hyperspectral images (397.32 nm-1003.58 nm) of five cotton cultivars, namely Jinke 20, Jinke 21, Xinluzao 64, Xinluzao 74, and Zhongmiansuo 5, were captured using a Specim IQ camera, and then the average spectral information of seeds of each cultivar was used for spectral analysis, aiming to estab-lish a cotton seed cultivar identification model. Due to the presence of many obvious noises in the < 400 nm and > 1000 nm regions of the collected spectral data, spectra from 400 nm to 1000 nm were selected as the representative spectra of the seed samples. Then, various denoising techniques, including Savitzky-Golay (SG), Standard Normal Variate (SNV), and First Derivative (FD), were applied individually and in combination to improve the quality of the spectra. Additionally, a successive projections algorithm (SPA) was employed for spectral feature selection. Based on the full-band spectra, a Partial Least Squares-Discriminant Analysis (PLS-DA) model was established. Furthermore, spectral features and textural features were fused to create Random Forest (RF), Convolutional Neural Network (CNN), and Extreme Learning Machine (ELM) identification models. The results showed that: (1) The SNV-FD preprocessing method showed the optimal denoising performance. (2) SPA highlighted the near-infrared region (800-1000 nm), red region (620-700 nm), and blue-green region (420-570 nm) for identifying cotton cultivar. (3) The fusion of spectral features and textural features did not consistently improve the accuracy of all modeling strategies, suggesting the need for further research on appropriate modeling strategies. (4) The ELM model had the highest cotton cultivar identification accuracy, with an accuracy of 100% for the training set and 98.89% for the test set. In conclusion, this study successfully developed a highly accurate cotton seed cultivar identification model (ELM model). This study provides a new method for the rapid and non-destructive identification of cotton seed cultivars, which will help ensure the cultivar consistency of seeds used in cotton planting, and improve the overall quality and yield of cotton.

A deep learning-based radiomics model for predicting lymph node status from lung adenocarcinoma

OBJECTIVES

At present, there are many limitations in the evaluation of lymph node metastasis of lung adenocarcinoma. Currently, there is a demand for a safe and accurate method to predict lymph node metastasis of lung cancer. In this study, radiomics was used to accurately predict the lymph node status of lung adenocarcinoma patients based on contrast-enhanced CT.

METHODS

A total of 503 cases that fulfilled the analysis requirements were gathered from two distinct hospitals. Among these, 287 patients exhibited lymph node metastasis (LNM +) while 216 patients were confirmed to be without lymph node metastasis (LNM-). Using both traditional and deep learning methods, 22,318 features were extracted from the segmented images of each patient's enhanced CT. Then, the spearman test and the least absolute shrinkage and selection operator were used to effectively reduce the dimension of the feature data, enabling us to focus on the most pertinent features and enhance the overall analysis. Finally, the classification model of lung adenocarcinoma lymph node metastasis was constructed by machine learning algorithm. The Accuracy, AUC, Specificity, Precision, Recall and F1 were used to evaluate the efficiency of the model.

RESULTS

By incorporating a comprehensively selected set of features, the extreme gradient boosting method (XGBoost) effectively distinguished the status of lymph nodes in patients with lung adenocarcinoma. The Accuracy, AUC, Specificity, Precision, Recall and F1 of the prediction model performance on the external test set were 0.765, 0.845, 0.705, 0.784, 0.811 and 0.797, respectively. Moreover, the decision curve analysis, calibration curve and confusion matrix of the model on the external test set all indicated the stability and accuracy of the model.

CONCLUSIONS

Leveraging enhanced CT images, our study introduces a noninvasive classification prediction model based on the extreme gradient boosting method. This approach exhibits remarkable precision in identifying the lymph node status of lung adenocarcinoma patients, offering a safe and accurate alternative to invasive procedures. By providing clinicians with a reliable tool for diagnosing and assessing disease progression, our method holds the potential to significantly improve patient outcomes and enhance the overall quality of clinical practice.

Determination of fumonisin content in maize using near-infrared hyperspectral imaging (NIR-HSI) technology and chemometric methods

Maize (Zea mays L.) is of socioeconomic importance as an essential food for human and animal nutrition. However, cereals are susceptible to attack by mycotoxin-producing fungi, which can damage health. The methods most commonly used to detect and quantify mycotoxins are expensive and time-consuming. Therefore, alternative non-destructive methods are required urgently. The present study aimed to use near-infrared spectroscopy with hyperspectral imaging (NIR-HSI) and multivariate image analysis to develop a rapid and accurate method for quantifying fumonisins in whole grains of six naturally contaminated maize cultivars. Fifty-eight samples, each containing 40 grains, were subjected to NIR-HSI. These were subsequently divided into calibration (38 samples) and prediction sets (20 samples) based on the multispectral data obtained. The averaged spectra were subjected to various pre-processing techniques (standard normal variate (SNV), first derivative, or second derivative). The most effective pre-treatment performed on the spectra was SNV. Partial least squares (PLS) models were developed to quantify the fumonisin content. The final model presented a correlation coefficient (R2) of 0.98 and root mean square error of calibration (RMSEC) of 508 µg.kg-1 for the calibration set, an R2 of 0.95 and root mean square error of prediction (RMSEP) of 508 µg.kg-1 for the test validation set and a ratio of performance to deviation of 4.7. It was concluded that NIR-HSI with partial least square regression is a rapid, effective, and non-destructive method to determine the fumonisin content in whole maize grains.

Rapid and accurate identification of bakanae pathogens carried by rice seeds based on hyperspectral imaging and deep transfer learning

Bakanae disease is a common seed-borne disease of rice. Rapid and accurate detection of bakanae pathogens carried by rice seeds is essential for the health of rice germplasm resources and the safety of rice production. This study aims to propose a general framework for species identification of major bakanae pathogens carried by rice seeds based on hyperspectral imaging and deep transfer learning. Seven varieties of rice seeds and four kinds of bakanae pathogens were analyzed. One-dimensional deep convolution neural networks (DCNNs) were first constructed using complete datasets. They achieved accuracies larger than 96.5% on the testing sets of most datasets, exceeding the conventional SVM and PLS-DA models. Then the developed DCNNs were transferred to detect other complete training sets. Most of the deep transferred models achieved comparable or even better performance than the original DCNNs. Two smaller target training sets were further constructed by randomly selecting spectra from the complete training sets. As the size of the target training sets reduced, the accuracies of all models on the corresponding testing sets also decreased gradually. Visualization analysis were conducted using the t-distribution stochastic neighbor embedding (t-SNE) algorithm and a proposed gradient-weighted activation wavelength (Grad-AW) method. They all showed that deep transfer learning could utilize the representation patterns in the source datasets to improve the target tasks. The overall results indicated that the bakanae pathogens were all identified accurately under our proposed framework. Hyperspectral imaging combined with deep transfer learning provided a new idea for the quality detection of large-scale seeds in modern seed industry.

Hyperspectral imaging for the detection of plant pathogens in seeds: recent developments and challenges

Food security, a critical concern amid global population growth, faces challenges in sustainable agricultural production due to significant yield losses caused by plant diseases, with a multitude of them caused by seedborne plant pathogen. With the expansion of the international seed market with global movement of this propagative plant material, and considering that about 90% of economically important crops grown from seeds, seed pathology emerged as an important discipline. Seed health testing is presently part of quality analysis and carried out by seed enterprises and governmental institutions looking forward to exclude a new pathogen in a country or site. The development of seedborne pathogens detection methods has been following the plant pathogen detection and diagnosis advances, from the use of cultivation on semi-selective media, to antibodies and DNA-based techniques. Hyperspectral imaging (HSI) associated with artificial intelligence can be considered the new frontier for seedborne pathogen detection with high accuracy in discriminating infected from healthy seeds. The development of the process consists of standardization of methods and protocols with the validation of spectral signatures for presence and incidence of contamined seeds. Concurrently, epidemiological studies correlating this information with disease outbreaks would help in determining the acceptable thresholds of seed contamination. Despite the high costs of equipment and the necessity for interdisciplinary collaboration, it is anticipated that health seed certifying programs and seed suppliers will benefit from the adoption of HSI techniques in the near future.

Advancements, limitations and challenges in hyperspectral imaging for comprehensive assessment of wheat quality: An up-to-date review

The potential of hyperspectral imaging technology (HIT) for the determination of physicochemical and nutritional components, evaluation of fungal/mycotoxins contamination, wheat varieties classification, identification of non-mildew-damaged wheat kernels, as well as detection of flour adulteration is comprehensively illustrated and reviewed. The latest findings (2018-2023) of HIT in wheat quality evaluation through internal and external attributes are compared and summarized in detail. The limitations and challenges of HIT to improve assessment accuracy are clearly described. Additionally, various practical recommendations and strategies for the potential application of HIT are highlighted. The future trends and prospects of HIT in evaluating wheat quality are also mentioned. In conclusion, HIT stands as a cutting-edge technology with immense potential for revolutionizing wheat quality evaluation. As advancements in HIT continue, it will play a pivotal role in shaping the future of wheat quality assessment and contributing to a more sustainable and efficient food supply chain.

Rapid Determination of Positive-Negative Bacterial Infection Based on Micro-Hyperspectral Technology

To meet the demand for rapid bacterial detection in clinical practice, this study proposed a joint determination model based on spectral database matching combined with a deep learning model for the determination of positive-negative bacterial infection in directly smeared urine samples. Based on a dataset of 8124 urine samples, a standard hyperspectral database of common bacteria and impurities was established. This database, combined with an automated single-target extraction, was used to perform spectral matching for single bacterial targets in directly smeared data. To address the multi-scale features and the need for the rapid analysis of directly smeared data, a multi-scale buffered convolutional neural network, MBNet, was introduced, which included three convolutional combination units and four buffer units to extract the spectral features of directly smeared data from different dimensions. The focus was on studying the differences in spectral features between positive and negative bacterial infection, as well as the temporal correlation between positive-negative determination and short-term cultivation. The experimental results demonstrate that the joint determination model achieved an accuracy of 97.29%, a Positive Predictive Value (PPV) of 97.17%, and a Negative Predictive Value (NPV) of 97.60% in the directly smeared urine dataset. This result outperformed the single MBNet model, indicating the effectiveness of the multi-scale buffered architecture for global and large-scale features of directly smeared data, as well as the high sensitivity of spectral database matching for single bacterial targets. The rapid determination solution of the whole process, which combines directly smeared sample preparation, joint determination model, and software analysis integration, can provide a preliminary report of bacterial infection within 10 min, and it is expected to become a powerful supplement to the existing technologies of rapid bacterial detection.

Integrating spectral and image information for prediction of cottonseed vitality

Cotton plays a significant role in people's lives, and cottonseeds serve as a vital assurance for successful cotton cultivation and production. Premium-quality cottonseeds can significantly enhance the germination rate of cottonseeds, resulting in increased cotton yields. The vitality of cottonseeds is a crucial metric that reflects the quality of the seeds. However, currently, the industry lacks a non-destructive method to directly assess cottonseed vitality without compromising the integrity of the seeds. To address this challenge, this study employed a hyperspectral imaging acquisition system to gather hyperspectral data on cottonseeds. This system enables the simultaneous collection of hyperspectral data from 25 cottonseeds. This study extracted spectral and image information from the hyperspectral data of cottonseeds to predict their vitality. SG, SNV, and MSC methods were utilized to preprocess the spectral data of cottonseeds. Following this preprocessing step, feature wavelength points of the cottonseeds were extracted using SPA and CARS algorithms. Subsequently, GLCM was employed to extract texture features from images corresponding to these feature wavelength points, including attributes such as Contrast, Correlation, Energy, and Entropy. Finally, the vitality of cottonseeds was predicted using PLSR, SVR, and a self-built 1D-CNN model. For spectral data analysis, the 1D-CNN model constructed after MSC+CARS preprocessing demonstrated the highest performance, achieving a test set correlation coefficient of 0.9214 and an RMSE of 0.7017. For image data analysis, the 1D-CNN model constructed after SG+CARS preprocessing outperformed the others, yielding a test set correlation coefficient of 0.8032 and an RMSE of 0.9683. In the case of fused spectral and image data, the 1D-CNN model built after SG+SPA preprocessing displayed the best performance, attaining a test set correlation coefficient of 0.9427 and an RMSE of 0.6872. These findings highlight the effectiveness of the 1D-CNN model and the fusion of spectral and image features for cottonseed vitality prediction. This research contributes significantly to the development of automated detection devices for assessing cottonseed vitality.

Digital techniques and trends for seed phenotyping using optical sensors

BACKGROUND

The breeding of high-quality, high-yield, and disease-resistant varieties is closely related to food security. The investigation of breeding results relies on the evaluation of seed phenotype, which is a key step in the process of breeding. In the global digitalization trend, digital technology based on optical sensors can perform the digitization of seed phenotype in a non-contact, high throughput way, thus significantly improving breeding efficiency.

AIM OF REVIEW

This paper provides a comprehensive overview of the principles, characteristics, data processing methods, and bottlenecks associated with three digital technique types based on optical sensors: spectroscopy, digital imaging, and three-dimensional (3D) reconstruction techniques. In addition, the applicability and adaptability of digital techniques based on the optical sensors of maize seed phenotype traits, namely external visible phenotype (EVP) and internal invisible phenotype (IIP), are investigated. Furthermore, trends in future equipment, platform, phenotype data, and processing algorithms are discussed. This review offers conceptual and practical support for seed phenotype digitization based on optical sensors, which will provide reference and guidance for future research.

KEY SCIENTIFIC CONCEPTS OF REVIEW

The digital techniques based on optical sensors can perform non-contact and high-throughput seed phenotype evaluation. Due to the distinct characteristics of optical sensors, matching suitable digital techniques according to seed phenotype traits can greatly reduce resource loss, and promote the efficiency of seed evaluation as well as breeding decision-making. Future research in phenotype equipment and platform, phenotype data, and processing algorithms will make digital techniques better meet the demands of seed phenotype evaluation, and promote automatic, integrated, and intelligent evaluation of seed phenotype, further helping to lessen the gap between digital techniques and seed phenotyping.

Last-percent improvement in eligibility rates of crop seeds based on quality evaluation using near-infrared imaging spectrometry

As the world population continues to grow, the need for high-quality crop seeds that promise stable food production is increasing. Conversely, excessive demand for high quality is causing "seed loss and waste" due to slight shortfalls in eligibility rates. In this study, we applied near-infrared imaging spectrometry combined with machine learning techniques to evaluate germinability and paternal haplotype in crop seeds from 6 species and 8 cultivars. Candidate discriminants for quality evaluation were derived by linear sparse modeling using the seed reflectance spectra as explanatory variables. To systematically proceed with model selection, we defined the sorting condition where the recovery rate of seeds matches the initial eligibility rate (iP) as "standard condition". How much the eligibility rate after sorting (P) increases from iP under this condition offers a reasonable criterion for ranking candidate models. Moreover, the model performance under conditions with adjusted discrimination strength was verified using a metric "relative precision" (rP) defined as (P-iP)/(1-iP). Because rP, compared to precision (= P), is less dependent on iP in relation to recall (R), i.e., recovery rate of eligible seeds, the rP-R curve and area under the curve also offer useful criteria for spotting better discriminant models. We confirmed that the batches of seeds given higher discriminant scores by the models selected with reference to these criteria were more enriched with eligible seeds. The method presented can be readily implemented in developing a sorting device that enables "last-percent improvement" in eligibility rates of crop seeds.

Visualized and Nondestructive Quality Identification of Two-Dimensional MoS2 Based on Principal Component Analysis

To date, the common quality characterizations for MoS2 are inefficient or cause irreversible damage to the samples, which have limited scalability and low throughput. Here, we propose a visualized and nondestructive approach to evaluate the quality of MoS2 based on the PCA machine learning method. Through PCA processing of PL mapping, the CVD grown MoS2 with different edge defect densities can be well distinguished. Furthermore, six twin GBs along the sulfur zigzag direction of the six pointed MoS2 stars are also successfully identified. To verify the correctness of the identification results, we measured the lifetime mapping and thermal expansion coefficient of the synthesized MoS2 samples. It is found that the high quality MoS2 samples have a shorter carrier lifetime (∼0.291 ns) and lower thermal expansion coefficient (∼2.03 × 10-5K-1). Therefore, our work offers a new approach to evaluate the quality of MoS2 to drive their practical application.

Noninvasive Methods to Detect Reactive Oxygen Species as a Proxy of Seed Quality

ROS homeostasis is crucial to maintain radical levels in a dynamic equilibrium within physiological ranges. Therefore, ROS quantification in seeds with different germination performance may represent a useful tool to predict the efficiency of common methods to enhance seed vigor, such as priming treatments, which are still largely empirical. In the present study, ROS levels were investigated in an experimental system composed of hydroprimed and heat-shocked seeds, thus comparing materials with improved or damaged germination potential. A preliminary phenotypic analysis of germination parameters and seedling growth allowed the selection of the best-per-forming priming protocols for species like soybean, tomato, and wheat, having relevant agroeconomic value. ROS levels were quantified by using two noninvasive assays, namely dichloro-dihydro-fluorescein diacetate (DCFH-DA) and ferrous oxidation-xylenol orange (FOX-1). qRT-PCR was used to assess the expression of genes encoding enzymes involved in ROS production (respiratory burst oxidase homolog family, RBOH) and scavenging (catalase, superoxide dismutase, and peroxidases). The correlation analyses between ROS levels and gene expression data suggest a possible use of these indicators as noninvasive approaches to evaluate seed quality. These findings are relevant given the centrality of seed quality for crop production and the potential of seed priming in sustainable agricultural practices.

Integrating optical imaging techniques for a novel approach to evaluate Siberian wild rye seed maturity

Advances in optical imaging technology using rapid and non-destructive methods have led to improvements in the efficiency of seed quality detection. Accurately timing the harvest is crucial for maximizing the yield of higher-quality Siberian wild rye seeds by minimizing excessive shattering during harvesting. This research applied integrated optical imaging techniques and machine learning algorithms to develop different models for classifying Siberian wild rye seeds based on different maturity stages and grain positions. The multi-source fusion of morphological, multispectral, and autofluorescence data provided more comprehensive information but also increases the performance requirements of the equipment. Therefore, we employed three filtering algorithms, namely minimal joint mutual information maximization (JMIM), information gain, and Gini impurity, and set up two control methods (feature union and no-filtering) to assess the impact of retaining only 20% of the features on the model performance. Both JMIM and information gain revealed autofluorescence and morphological features (CIELab A, CIELab B, hue and saturation), with these two filtering algorithms showing shorter run times. Furthermore, a strong correlation was observed between shoot length and morphological and autofluorescence spectral features. Machine learning models based on linear discriminant analysis (LDA), random forests (RF) and support vector machines (SVM) showed high performance (>0.78 accuracies) in classifying seeds at different maturity stages. Furthermore, it was found that there was considerable variation in the different grain positions at the maturity stage, and the K-means approach was used to improve the model performance by 5.8%-9.24%. In conclusion, our study demonstrated that feature filtering algorithms combined with machine learning algorithms offer high performance and low cost in identifying seed maturity stages and that the application of k-means techniques for inconsistent maturity improves classification accuracy. Therefore, this technique could be employed classification of seed maturity and superior physiological quality for Siberian wild rye seeds.

Identification of Defective Maize Seeds Using Hyperspectral Imaging Combined with Deep Learning

Seed quality affects crop yield and the quality of agricultural products, and traditional identification methods are time-consuming, complex, and irreversibly destructive. This study aims to establish a fast, non-destructive, and effective approach for defect detection in maize seeds based on hyperspectral imaging (HSI) technology combined with deep learning. Raw spectra collected from maize seeds (200 each healthy and worm-eaten) were pre-processed using detrending (DE) and multiple scattering correction (MSC) to highlight the spectral differences between samples. A convolutional neural network architecture (CNN-FES) based on a feature selection mechanism was proposed according to the importance of wavelength in the target classification task. The results show that the subset of 24 feature wavelengths selected by the proposed CNN-FES can capture important feature information in the spectral data more effectively than the conventional successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) algorithms. In addition, a convolutional neural network architecture (CNN-ATM) based on an attentional classification mechanism was designed for one-dimensional spectral data classification and compared with three commonly used machine learning methods, linear discriminant analysis (LDA), random forest (RF), and support vector machine (SVM). The results show that the classification performance of the designed CNN-ATM on the full wavelength does not differ much from the above three methods, and the classification accuracy is above 90% on both the training and test sets. Meanwhile, the accuracy, sensitivity, and specificity of CNN-ATM based on feature wavelength modeling can reach up to 97.50%, 98.28%, and 96.77% at the highest, respectively. The study shows that hyperspectral imaging-based defect detection of maize seed is feasible and effective, and the proposed method has great potential for the processing and analysis of complex hyperspectral data.

Prediction of chemical indicators for quality of Zanthoxylum spices from multi-regions using hyperspectral imaging combined with chemometrics

Fruits of Zanthoxylum bungeanum Maxim (Red “Huajiao,” RHJ) and Z. schinifolium Sieb. et Zucc. (Green “Huajiao,” GHJ) are famous spices around the world. Antioxidant capability (AOC), total alkylamides content (TALC) and volatile oil content (VOC) in HJ are three important quality indicators and lack rapid and effective methods for detection. Non-destructive, time-saving, and effective technology of hyperspectral imaging (HSI) combined with chemometrics was adopted to improve the indicators prediction in this study. Results showed that the three chemical indexes exhibited significant differences between different regions and varieties (P &lt; 0.05). Specifically, the mass percentages of TALC were 11–22% in RHJ group and 21–36% in GHJ group. The mass percentages of VOC content were 23–31% and 16–24% in RHJ and GHJ groups, respectively. More importantly, these indicators could be well predicted based on the full or effective HSI wavelengths via model adaptive space shrinkage (MASS) and iteratively variable subset optimization (IVSO) selections combined with wavelet transform (WT) method for noise reduction. The best prediction results of AOC, TALC, and VOC indicators were achieved with the highest residual predictive deviation (RPD) values of 7.43, 7.82, and 3.73 for RHJ, respectively, and 6.82, 2.66, and 4.64 for GHJ, respectively. The above results highlight the great potential of HSI assisted with chemometrics in the rapid and effective prediction of chemical indicators of Zanthoxylum spices.

Predicting F v /F m and evaluating cotton drought tolerance using hyperspectral and 1D-CNN

The chlorophyll fluorescence parameter F_v/F_m is significant in abiotic plant stress. Current acquisition methods must deal with the dark adaptation of plants, which cannot achieve rapid, real-time, and high-throughput measurements. However, increased inputs on different genotypes based on hyperspectral model recognition verified its capabilities of handling large and variable samples. F_v/F_m is a drought tolerance index reflecting the best drought tolerant cotton genotype. Therefore, F_v/F_m hyperspectral prediction of different cotton varieties, and drought tolerance evaluation, are worth exploring. In this study, 80 cotton varieties were studied. The hyperspectral cotton data were obtained during the flowering, boll setting, and boll opening stages under normal and drought stress conditions. Next, One-dimensional convolutional neural networks (1D-CNN), Categorical Boosting (CatBoost), Light Gradient Boosting Machines (LightBGM), eXtreme Gradient Boosting (XGBoost), Decision Trees (DT), Random Forests (RF), Gradient elevation decision trees (GBDT), Adaptive Boosting (AdaBoost), Extra Trees (ET), and K-Nearest Neighbors (KNN) were modeled with F _v /F _m. The Savitzky-Golay + 1D-CNN model had the best robustness and accuracy (RMSE = 0.016, MAE = 0.009, MAPE = 0.011). In addition, the F _v /F _m prediction drought tolerance coefficient and the manually measured drought tolerance coefficient were similar. Therefore, cotton varieties with different drought tolerance degrees can be monitored using hyperspectral full band technology to establish a 1D-CNN model. This technique is non-destructive, fast and accurate in assessing the drought status of cotton, which promotes smart-scale agriculture.

Nutrient content prediction and geographical origin identification of red raspberry fruits by combining hyperspectral imaging with chemometrics

The geographical origin and the important nutrient contents greatly affect the quality of red raspberry (RRB, Rubus idaeus L.), a popular fruit with various health benefits. In this study, a chemometrics-assisted hyperspectral imaging (HSI) method was developed for predicting the nutrient contents, including pectin polysaccharides (PPS), reducing sugars (RS), total flavonoids (TF) and total phenolics (TP), and identifying the geographical origin of RRB fruits. The results showed that these nutrient contents in RRB fruits had significant differences between regions (P &lt; 0.05) and could be well predicted based on the HSI full or effective wavelengths selected through competitive adaptive reweighted sampling (CARS) and variable iterative space shrinkage approach (VISSA). The best prediction results of PPS, RS, TF, and TP contents were achieved with the highest residual predictive deviation (RPD) values of 3.66, 3.95, 2.85, and 4.85, respectively. The RRB fruits from multi-regions in China were effectively distinguished by using the first derivative-partial least squares discriminant analysis (DER-PLSDA) model, with an accuracy of above 97%. Meanwhile, the fruits from three protected geographical indication (PGI) regions were successfully classified by using the orthogonal partial least squares discrimination analysis (OPLSDA) model, with an accuracy of above 98%. The study results indicate that HSI assisted with chemometrics is a promising method for predicting the important nutrient contents and identifying the geographical origin of red raspberry fruits.

Rice Chalky Grain 5 regulates natural variation for grain quality under heat stress

Heat stress occurring during rice (Oryza sativa) grain development reduces grain quality, which often manifests as increased grain chalkiness. Although the impact of heat stress on grain yield is well-studied, the genetic basis of rice grain quality under heat stress is less explored as quantifying grain quality is less tractable than grain yield. To address this, we used an image-based colorimetric assay (Red, R; and Green, G) for genome-wide association analysis to identify genetic loci underlying the phenotypic variation in rice grains exposed to heat stress. We found the R to G pixel ratio (RG) derived from mature grain images to be effective in distinguishing chalky grains from translucent grains derived from control (28/24°C) and heat stressed (36/32°C) plants. Our analysis yielded a novel gene, rice Chalky Grain 5 (OsCG5) that regulates natural variation for grain chalkiness under heat stress. OsCG5 encodes a grain-specific, expressed protein of unknown function. Accessions with lower transcript abundance of OsCG5 exhibit higher chalkiness, which correlates with higher RG values under stress. These findings are supported by increased chalkiness of OsCG5 knock-out (KO) mutants relative to wildtype (WT) under heat stress. Grains from plants overexpressing OsCG5 are less chalky than KOs but comparable to WT under heat stress. Compared to WT and OE, KO mutants exhibit greater heat sensitivity for grain size and weight relative to controls. Collectively, these results show that the natural variation at OsCG5 may contribute towards rice grain quality under heat stress.

Single Seed Identification in Three Medicago Species via Multispectral Imaging Combined with Stacking Ensemble Learning

Multispectral imaging (MSI) has become a new fast and non-destructive detection method in seed identification. Previous research has usually focused on single models in MSI data analysis, which always employed all features and increased the risk to efficiency and that of system cost. In this study, we developed a stacking ensemble learning (SEL) model for successfully identifying a single seed of sickle alfalfa (Medicago falcata), hybrid alfalfa (M. varia), and alfalfa (M. sativa). SEL adopted a three-layer structure, i.e., level 0 with principal component analysis (PCA), linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) as models of dimensionality reduction and feature extraction (DRFE); level 1 with support vector machine (SVM), multiple logistic regression (MLR), generalized linear models with elastic net regularization (GLMNET), and eXtreme Gradient Boosting (XGBoost) as basic learners; and level 3 with XGBoost as meta-learner. We confirmed that the values of overall accuracy, kappa, precision, sensitivity, specificity, and sensitivity in the SEL model were all significantly higher than those in basic models alone, based on both spectral features and a combination of morphological and spectral features. Furthermore, we also developed a feature filtering process and successfully selected 5 optimal features out of 33 ones, which corresponded to the contents of chlorophyll, anthocyanin, fat, and moisture in seeds. Our SEL model in MSI data analysis provided a new way for seed identification, and the feature filter process potentially could be used widely for development of a low-cost and narrow-channel sensor.

The Use of Novel, Rapid Analytical Tools in the Assessment of the Stability of Tablets—A Pilot Analysis of Expired and Unexpired Tablets Containing Nifuroxazide

In the analysis of finished pharmaceutical products, numerous innovative analytical techniques are often used, i.e., Raman spectroscopy, scanning electron microscopy, computer microtomography, directional hemispherical reflectance, and hyperspectral analyses. These techniques allow for the identification of changes in solid phases. Many advantages over other techniques can be attributed to these techniques, e.g., they are rapid, non-destructive, and comprehensive. They allow for the identification of changes occurring in solid phases. However, the above-mentioned methods are still not standard procedures in pharmaceutical research. The present study aimed to assess the possible usefulness of total directional hemispherical reflectance (THR), hyperspectral imaging, and computer microtomography to evaluate the stability of tablets containing nifuroxazide during storage. In the study, expired and unexpired coating tablets containing nifuroxazide (n = 10 each) were analyzed. In addition, four unexpired tablets were stored at 40°C over 3 months (stressed tablets). Reflectance was determined with seven wavelength bands from 335 nm to 2500 nm using an SOC-410 Directional Hemispherical Reflectometer (Surface Optics Corporation, San Diego, CA, USA). A Specim IQ hyperspectral camera (Spectral Imaging Ltd., Oulu, Finland) was used with a wavelength range of 400–1030 nm. Tablets were also scanned using X-ray microtomography (Phoenix vǀtomeǀx, GE Sensing & Inspection Technologies GmbH, Wunstorf, Germany). The results indicated that total reflectance was lower in expired tablets than in unexpired tablets in all spectral bands, except for 700–1100 nm and 1700–2500 nm. In turn, the stressed tablets showed higher THR values than expired tablets in all spectral bands, except for 1000–1700 nm. In addition, hyperspectral analysis of the homogeneity of the tablets, as well as X-ray microtomographic analysis of tablet density and coating thickness, indicated that these parameters differed significantly between the analyzed tablets.

The use of multispectral imaging for the discrimination of Arabica and Robusta coffee beans

Arabica coffee beans are sold at twice the price, or more, compared to Robusta beans and consequently are susceptible to economically motivated adulteration by substitution. There is a need for rapid, non-destructive, and efficient analytical techniques for monitoring the authenticity of Arabica coffee beans in the supply chain. In this study, multispectral imaging (MSI) was applied to discriminate roasted Arabica and Robusta coffee beans and perform quantitative prediction of Arabica coffee bean adulteration with Robusta. The Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA) model, built using selected spectral and morphological features from individual coffee beans, achieved 100% correct classification of the two coffee species in the test dataset. The OPLS regression model was able to successfully predict the level of adulteration of Arabica with Robusta. MSI analysis has potential as a rapid screening tool for the detection of fraud issues related to the authenticity of Arabica coffee beans.

Experimental data manipulations to assess performance of hyperspectral classification models of crop seeds and other objects

BACKGROUND

Optical sensing solutions are being developed and adopted to classify a wide range of biological objects, including crop seeds. Performance assessment of optical classification models remains both a priority and a challenge.

METHODS

As training data, we acquired hyperspectral imaging data from 3646 individual tomato seeds (germination yes/no) from two tomato varieties. We performed three experimental data manipulations: (1) Object assignment error: effect of individual object in the training data being assigned to the wrong class. (2) Spectral repeatability: effect of introducing known ranges (0-10%) of stochastic noise to individual reflectance values. (3) Size of training data set: effect of reducing numbers of observations in training data. Effects of each of these experimental data manipulations were characterized and quantified based on classifications with two functions [linear discriminant analysis (LDA) and support vector machine (SVM)].

RESULTS

For both classification functions, accuracy decreased linearly in response to introduction of object assignment error and to experimental reduction of spectral repeatability. We also demonstrated that experimental reduction of training data by 20% had negligible effect on classification accuracy. LDA and SVM classification algorithms were applied to independent validation seed samples. LDA-based classifications predicted seed germination with RMSE = 10.56 (variety 1) and 26.15 (variety 2), and SVM-based classifications predicted seed germination with RMSE = 10.44 (variety 1) and 12.58 (variety 2).

CONCLUSION

We believe this study represents the first, in which optical seed classification included both a thorough performance evaluation of two separate classification functions based on experimental data manipulations, and application of classification models to validation seed samples not included in training data. Proposed experimental data manipulations are discussed in broader contexts and general relevance, and they are suggested as methods for in-depth performance assessments of optical classification models.

Rapid and Non-destructive Classification of New and Aged Maize Seeds Using Hyperspectral Image and Chemometric Methods

The aged seeds have a significant influence on seed vigor and corn growth. Therefore, it is vital for the planting industry to identify aged seeds. In this study, hyperspectral reflectance imaging (1,000-2,000 nm) was employed for identifying aged maize seeds using seeds harvested in different years. The average spectra of the embryo side, endosperm side, and both sides were extracted. The support vector machine (SVM) algorithm was used to develop classification models based on full spectra to evaluate the potential of hyperspectral imaging for maize seed detection and using the principal component analysis (PCA) and ANOVA to reduce data dimensionality and extract feature wavelengths. The classification models achieved perfect performance using full spectra with an accuracy of 100% for the prediction set. The performance of models established with the first three principal components was similar to full spectrum models, but that of PCA loading models was worse. Compared to other spectra, the two-band ratio (1,987 nm/1,079 nm) selected by ANOVA from embryo-side spectra achieved a better classification accuracy of 95% for the prediction set. The image texture features, including histogram statistics (HS) and gray-level co-occurrence matrix (GLCM), were extracted from the two-band ratio image to establish fusion models. The results demonstrated that the two-band ratio selected from embryo-side spectra combined with image texture features achieved the classification of maize seeds harvested in different years with an accuracy of 97.5% for the prediction set. The overall results indicated that combining the two wavelengths with image texture features could detect aged maize seeds effectively. The proposed method was conducive to the development of multi-spectral detection equipment.

Optical imaging spectroscopy for rapid, primary screening of SARS-CoV-2: a proof of concept

Effective testing is essential to control the coronavirus disease 2019 (COVID-19) transmission. Here we report a-proof-of-concept study on hyperspectral image analysis in the visible and near-infrared range for primary screening at the point-of-care of SARS-CoV-2. We apply spectral feature descriptors, partial least square-discriminant analysis, and artificial intelligence to extract information from optical diffuse reflectance measurements from 5 µL fluid samples at pixel, droplet, and patient levels. We discern preparations of engineered lentiviral particles pseudotyped with the spike protein of the SARS-CoV-2 from those with the G protein of the vesicular stomatitis virus in saline solution and artificial saliva. We report a quantitative analysis of 72 samples of nasopharyngeal exudate in a range of SARS-CoV-2 viral loads, and a descriptive study of another 32 fresh human saliva samples. Sensitivity for classification of exudates was 100% with peak specificity of 87.5% for discernment from PCR-negative but symptomatic cases. Proposed technology is reagent-free, fast, and scalable, and could substantially reduce the number of molecular tests currently required for COVID-19 mass screening strategies even in resource-limited settings.

Identification of Rice Seed Varieties Based on Near-Infrared Hyperspectral Imaging Technology Combined with Deep Learning

Rice is one of the most important food crops in the world, and rice seed varieties are related to the yield and quality of rice. This study used near-infrared (NIR) hyperspectral technology with conventional machine learning methods (support vector machine (SVM), logistic regression (LR), and random forest (RF)) and deep learning methods (LeNet, GoogLeNet, and residual network (ResNet)) to establish variety identification models for five common types of rice seeds. Among the deep learning methods, the classification accuracies of most models were higher than 95%. This study further used the deep learning methods to establish variety identification models for 10 varieties of rice seeds without considering their types. Among them, the ResNet model had the best classification results. The classification accuracy on the test set was 86.08%. This study used the saliency map method to visualize each convolutional neural network (CNN) model to find the band region that contributed the most to the data. The results showed that the bands with the largest data contribution were mainly concentrated at approximately 1300-1400 nm and secondarily concentrated at approximately 1050-1250 nm. The overall results showed that NIR hyperspectral imaging technology combined with deep learning could effectively distinguish rice seeds of different varieties. This method provided an effective way to identify rice seed varieties in a quick and nondestructive manner.

Chemometric strategies for near infrared hyperspectral imaging analysis: classification of cotton seed genotypes

Hyperspectral images have been increasingly employed in the agricultural sector for seed classification for different purposes. In the present paper we propose a new methodology based on HSI in the near infrared range (HSI-NIR) to distinguish conventional from transgenic cotton seeds. Three different chemometric approaches, one pixel-based and two object-based, using partial least squares discriminant analysis (PLS-DA) were built and their performances were compared considering the pros and cons of each approach. Specificity and sensitivity values ranged from 0.78-0.92 and 0.62-0.93, respectively, for the different approaches.

A Critical Review of the Current Global Ex Situ Conservation System for Plant Agrobiodiversity. II. Strengths and Weaknesses of the Current System and Recommendations for Its Improvement

In this paper, we review gene bank operations that have an influence on the global conservation system, with the intention to identify critical aspects that should be improved for optimum performance. We describe the role of active and base collections and the importance of linking germplasm conservation and use, also in view of new developments in genomics and phenomics that facilitate more effective and efficient conservation and use of plant agrobiodiversity. Strengths, limitations, and opportunities of the existing global ex situ conservation system are discussed, and measures are proposed to achieve a rational, more effective, and efficient global system for germplasm conservation and sustainable use. The proposed measures include filling genetic and geographic gaps in current ex situ collections; determining unique accessions at the global level for long-term conservation in virtual base collections; intensifying existing international collaborations among gene banks and forging collaborations with the botanic gardens community; increasing investment in conservation research and user-oriented supportive research; improved accession-level description of the genetic diversity of crop collections; improvements of the legal and policy framework; and oversight of the proposed network of global base collections.

Hyperspectral Dimensionality Reduction Based on Inter-Band Redundancy Analysis and Greedy Spectral Selection

Hyperspectral imaging systems are becoming widely used due to their increasing accessibility and their ability to provide detailed spectral responses based on hundreds of spectral bands. However, the resulting hyperspectral images (HSIs) come at the cost of increased storage requirements, increased computational time to process, and highly redundant data. Thus, dimensionality reduction techniques are necessary to decrease the number of spectral bands while retaining the most useful information. Our contribution is two-fold: First, we propose a filter-based method called interband redundancy analysis (IBRA) based on a collinearity analysis between a band and its neighbors. This analysis helps to remove redundant bands and dramatically reduces the search space. Second, we apply a wrapper-based approach called greedy spectral selection (GSS) to the results of IBRA to select bands based on their information entropy values and train a compact convolutional neural network to evaluate the performance of the current selection. We also propose a feature extraction framework that consists of two main steps: first, it reduces the total number of bands using IBRA; then, it can use any feature extraction method to obtain the desired number of feature channels. We present classification results obtained from our methods and compare them to other dimensionality reduction methods on three hyperspectral image datasets. Additionally, we used the original hyperspectral data cube to simulate the process of using actual filters in a multispectral imager.

Automated In Situ Seed Variety Identification via Deep Learning: A Case Study in Chickpea

On-time seed variety recognition is critical to limit qualitative and quantitative yield loss and asynchronous crop production. The conventional method is a subjective and error-prone process, since it relies on human experts and usually requires accredited seed material. This paper presents a convolutional neural network (CNN) framework for automatic identification of chickpea varieties by using seed images in the visible spectrum (400–700 nm). Two low-cost devices were employed for image acquisition. Lighting and imaging (background, focus, angle, and camera-to-sample distance) conditions were variable. The VGG16 architecture was modified by a global average pooling layer, dense layers, a batch normalization layer, and a dropout layer. Distinguishing the intricate visual features of the diverse chickpea varieties and recognizing them according to these features was conceivable by the obtained model. A five-fold cross-validation was performed to evaluate the uncertainty and predictive efficiency of the CNN model. The modified deep learning model was able to recognize different chickpea seed varieties with an average classification accuracy of over 94%. In addition, the proposed vision-based model was very robust in seed variety identification, and independent of image acquisition device, light environment, and imaging settings. This opens the avenue for the extension into novel applications using mobile phones to acquire and process information in situ. The proposed procedure derives possibilities for deployment in the seed industry and mobile applications for fast and robust automated seed identification practices.

Application of long-wave near infrared hyperspectral imaging for determination of moisture content of single maize seed

Moisture content (MC) is one of the most important factors for assessment of seed quality. However, the accurate detection of MC in single seed is very difficult. In this study, single maize seed was used as research object. A long-wave near infrared (LWNIR) hyperspectral imaging system was developed for acquiring reflectance images of the embryo and endosperm side of maize seed in the spectral range of 930-2548 nm, and the mixed spectra were extracted from both side of maize seeds. Then, Full-spectrum models were established and compared based on different types of spectra. It showed that models established based on spectra of the embryo side and mixed spectra obtained better performance than the endosperm side. Next, a combination of competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) was proposed to select the most effective wavelengths from full-spectrum data. In order to explore the stableness of wavelength selection algorithm, these methods were used for 200 independent experiments based on embryo side and mixed spectra, respectively. Each selection result was used as input of partial least squares regression (PLSR) and least squares support vector machine (LS-SVM) to build calibration models for determining the MC of single maize seed. Results indicated that the CARS-SPA-LS-SVM model established with mixed spectra was optimal for MC prediction in all models by considering the accuracy, stableness and complexity of models. The prediction accuracy of CARS-SPA-LS-SVM model is R_pre = 0.9311 ± 0.0094 and RMSEP = 1.2131 ± 0.0702 in 200 independent assessment. The overall study revealed that the long-wave near infrared hyperspectral imaging can be used to non-invasively and fast measure the MC in single maize seed and a robust and accurate model could be established based on CARS-SPA-LS-SVM method coupled with mixed spectral. These results can provide a useful reference for assessment of other internal quality attributes (such as starch content) of single maize seed.

Recent innovations of ultrasound green technology in herbal phytochemistry: A review

Ultrasound (US) has become one of the most important techniques in green chemistry and emerging technologies. Many research investigations documented the usefulness of US in a wide range of applications in food science, nanotechnology, and complementary medicine, where effective extraction of natural products is important. However, as with all novel technologies, US has advantages and limitations that require clarification for full adaptation at an industrial scale. The present review discusses recent applications of US in herbal phytochemistry with the emphasis on US effects on chemical structures of bioactive compounds extracted from herbs and their bioactivities. The impact of different US processing conditions such as frequency, intensity, duration, temperature, and pressure on the effectiveness of the extraction process and the properties of the extracted materials are also discussed. Different frequencies and intensities of US have demonstrated its potential applications in modifying, determining, and predicting the physicochemical properties of herbs and their extracts. US has important applications in nanotechnology where it supports the fabrication of inexpensive and eco-friendly herbal nanostructures, as well as acoustic-based biosensors for chemical imaging of the herbal tissues. The application of US enhances the rates of chemical processes such as hydrolysis of herbal fibers, which reduces the time and energy consumed without affecting the quality of the final products. Overall, the use of US in herbal science has great potential to create novel chemical constructions and to be used as an innovative diagnostic system in various biomedical, food, and analytical applications.

Multi-Way Analysis Coupled with Near-Infrared Spectroscopy in Food Industry: Models and Applications

Near-infrared spectroscopy (NIRS) is a fast and powerful analytical tool in the food industry. As an advanced chemometrics tool, multi-way analysis shows great potential for solving a wide range of food problems and analyzing complex spectroscopic data. This paper describes the representative multi-way models which were used for analyzing NIRS data, as well as the advances, advantages and limitations of different multi-way models. The applications of multi-way analysis in NIRS for the food industry in terms of food process control, quality evaluation and fraud, identification and classification, prediction and quantification, and image analysis are also reviewed. It is evident from this report that multi-way analysis is presently an attractive tool for modeling complex NIRS data in the food industry while its full potential is far from reached. The combination of multi-way analysis with NIRS will be a promising practice for turning food data information into operational knowledge, conducting reliable food analyses and improving our understanding about food systems and food processes. To the best of our knowledge, this is the first paper that systematically reports the advances on models and applications of multi-way analysis in NIRS for the food industry.

Phytosanitary Interventions for Safe Global Germplasm Exchange and the Prevention of Transboundary Pest Spread: The Role of CGIAR Germplasm Health Units

The inherent ability of seeds (orthodox, intermediate, and recalcitrant seeds and vegetative propagules) to serve as carriers of pests and pathogens (hereafter referred to as pests) and the risk of transboundary spread along with the seed movement present a high-risk factor for international germplasm distribution activities. Quarantine and phytosanitary procedures have been established by many countries around the world to minimize seed-borne pest spread by screening export and import consignments of germplasm. The effectiveness of these time-consuming and cost-intensive procedures depends on the knowledge of pest distribution, availability of diagnostic tools for seed health testing, qualified operators, procedures for inspection, and seed phytosanitation. This review describes a unique multidisciplinary approach used by the CGIAR Germplasm Health Units (GHUs) in ensuring phytosanitary protection for the safe conservation and global movement of germplasm from the 11 CGIAR genebanks and breeding programs that acquire and distribute germplasm to and from all parts of the world for agricultural research and food security. We also present the challenges, lessons learned, and recommendations stemming from the experience of GHUs, which collaborate with the national quarantine systems to export and distribute about 100,000 germplasm samples annually to partners located in about 90 to 100 countries. Furthermore, we describe how GHUs adjust their procedures to stay in alignment with evolving phytosanitary regulations and pest risk scenarios. In conclusion, we state the benefits of globally coordinated phytosanitary networks for the prevention of the intercontinental spread of pests that are transmissible through plant propagation materials.

A Review of the Discriminant Analysis Methods for Food Quality Based on Near-Infrared Spectroscopy and Pattern Recognition

Near-infrared spectroscopy (NIRS) combined with pattern recognition technique has become an important type of non-destructive discriminant method. This review first introduces the basic structure of the qualitative analysis process based on near-infrared spectroscopy. Then, the main pretreatment methods of NIRS data processing are investigated. Principles and recent developments of traditional pattern recognition methods based on NIRS are introduced, including some shallow learning machines and clustering analysis methods. Moreover, the newly developed deep learning methods and their applications of food quality analysis are surveyed, including convolutional neural network (CNN), one-dimensional CNN, and two-dimensional CNN. Finally, several applications of these pattern recognition techniques based on NIRS are compared. The deficiencies of the existing pattern recognition methods and future research directions are also reviewed.

Application of Hyperspectral Imaging for Maturity and Soluble Solids Content Determination of Strawberry With Deep Learning Approaches

Maturity degree and quality evaluation are important for strawberry harvest, trade, and consumption. Deep learning has been an efficient artificial intelligence tool for food and agro-products. Hyperspectral imaging coupled with deep learning was applied to determine the maturity degree and soluble solids content (SSC) of strawberries with four maturity degrees. Hyperspectral image of each strawberry was obtained and preprocessed, and the spectra were extracted from the images. One-dimension residual neural network (1D ResNet) and three-dimension (3D) ResNet were built using 1D spectra and 3D hyperspectral image as inputs for maturity degree evaluation. Good performances were obtained for maturity identification, with the classification accuracy over 84% for both 1D ResNet and 3D ResNet. The corresponding saliency maps showed that the pigments related wavelengths and image regions contributed more to the maturity identification. For SSC determination, 1D ResNet model was also built, with the determination of coefficient (R ²) over 0.55 of the training, validation, and testing sets. The saliency maps of 1D ResNet for the SSC determination were also explored. The overall results showed that deep learning could be used to identify strawberry maturity degree and determine SSC. More efforts were needed to explore the use of 3D deep learning methods for the SSC determination. The close results of 1D ResNet and 3D ResNet for classification indicated that more samples might be used to improve the performances of 3D ResNet. The results in this study would help to develop 1D and 3D deep learning models for fruit quality inspection and other researches using hyperspectral imaging, providing efficient analysis approaches of fruit quality inspection using hyperspectral imaging.

Nondestructive Classification of Soybean Seed Varieties by Hyperspectral Imaging and Ensemble Machine Learning Algorithms

During the processing and planting of soybeans, it is greatly significant that a reliable, rapid, and accurate technique is used to detect soybean varieties. Traditional chemical analysis methods of soybean variety sampling (e.g., mass spectrometry and high-performance liquid chromatography) are destructive and time-consuming. In this paper, a robust and accurate method for nondestructive soybean classification is developed through hyperspectral imaging and ensemble machine learning algorithms. Image acquisition, preprocessing, and feature selection are used to obtain different types of soybean hyperspectral features. Based on these features, one of ensemble classifiers-random subspace linear discriminant (RSLD) algorithm is used to classify soybean seeds. Compared with the linear discrimination (LD) and linear support vector machine (LSVM) methods, the results show that the RSLD algorithm in this paper is more stable and reliable. In classifying soybeans in 10, 15, 20, and 25 categories, the RSLD method achieves the highest classification accuracy. When 155 features are used to classify 15 types of soybeans, the classification accuracy of the RSLD method reaches 99.2%, while the classification accuracies of the LD and LSVM methods are only 98.6% and 69.7%, respectively. Therefore, the ensemble classification algorithm RSLD can maintain high classification accuracy when different types and different classification features are used.

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Near-infrared (NIR) hyperspectroscopy becomes an emerging nondestructive sensing technology for inspection of crop seeds. A large spectral dataset of more than 140,000 wheat kernels in 30 varieties was prepared for classification. Feature selection is a critical segment in large spectral data analysis. A novel convolutional neural network-based feature selector (CNN-FS) was proposed to screen out deeply target-related spectral channels. A convolutional neural network with attention (CNN-ATT) framework was designed for one-dimension data classification. Popular machine learning models including support vector machine (SVM) and partial least square discrimination analysis were used as the benchmark classifiers. Features selected by conventional feature selection algorithms were considered for comparison. Results showed that the designed CNN-ATT produced a higher performance than the compared classifier. The proposed CNN-FS found a subset of features, which made a better representation of raw dataset than conventional selectors did. The CNN-ATT achieved an accuracy of 93.01% using the full spectra and keep its high precision (90.20%) by training on the 60-channel features obtained via the CNN-FS method. The proposed methods have great potential for handling the analyzing tasks on other large spectral datasets. The proposed feature selection structure can be extended to design other new model-based selectors. The combination of NIR hyperspectroscopic technology and the proposed models has great potential for automatic nondestructive classification of single wheat kernels.

Genebank Phenomics: A Strategic Approach to Enhance Value and Utilization of Crop Germplasm

Genetically diverse plant germplasm stored in ex-situ genebanks are excellent resources for breeding new high yielding and sustainable crop varieties to ensure future food security. Novel alleles have been discovered through routine genebank activities such as seed regeneration and characterization, with subsequent utilization providing significant genetic gains and improvements for the selection of favorable traits, including yield, biotic, and abiotic resistance. Although some genebanks have implemented cost-effective genotyping technologies through advances in DNA technology, the adoption of modern phenotyping is lagging. The introduction of advanced phenotyping technologies in recent decades has provided genebank scientists with time and cost-effective screening tools to obtain valuable phenotypic data for more traits on large germplasm collections during routine activities. The utilization of these phenotyping tools, coupled with high-throughput genotyping, will accelerate the use of genetic resources and fast-track the development of more resilient food crops for the future. In this review, we highlight current digital phenotyping methods that can capture traits during annual seed regeneration to enrich genebank phenotypic datasets. Next, we describe strategies for the collection and use of phenotypic data of specific traits for downstream research using high-throughput phenotyping technology. Finally, we examine the challenges and future perspectives of genebank phenomics.

Identification of heat damage in imported soybeans based on hyperspectral imaging technology

BACKGROUND

Imported soybeans are prone to heat damage due to high storage temperatures or poor ventilation during transportation. Heat damage directly degrades the quality of the produce and greatly reduces the edible value of soybeans. Rapid and nondestructive techniques for assessing the quality of imported soybeans are in demand. Hyperspectral imaging (HSI) technology was used to distinguish sound soybeans from heat-damaged soybeans.

RESULTS

For testing the effectiveness of preprocessing methods in enhancing model performance, five different preprocessing methods were implemented to original spectra. To solve problems related to accuracy, efficiency, and model interpretability caused by high-dimensional HSI data, three waveband selection algorithms - dependency measure (DM-NRS), mutual information (MI-NRS) and variable precision (VP-NRS) - based on neighborhood rough set (NRS) theory were proposed to identify the waveband subsets with optimal distinguishing ability. The effectiveness of preprocessing methods and waveband selection algorithms was validated by establishing two kinds of models: extreme learning machine (ELM) and random forest (RF) models. In addition to the classification accuracy, the robustness of the waveband selection algorithms was studied. The results demonstrated that the Savitzky-Golay (SG) smoothing preprocessing method combined with the MI-NRS waveband selection algorithm and the ELM classifier achieved the best classification and robustness results. Classification accuracy reached 99.98% when using only two optimal wavebands, and reached 100% when using more than four optimal wavebands.

CONCLUSION

The results prove that the HSI technology is an accurate, effective, and nondestructive technique for classifying sound and heat-damaged soybeans. © 2019 Society of Chemical Industry.

Rapid and Nondestructive Discrimination of Geographical Origins of Longjing Tea using Hyperspectral Imaging at Two Spectral Ranges Coupled with Machine Learning Methods

Longjing tea is one of China’s protected geographical indication products with high commercial and nutritional value. The geographical origin of Longjing tea is an important factor influencing its commercial and nutritional value. Hyperspectral imaging systems covering the two spectral ranges of 380–1030 nm and 874–1734 nm were used to identify a single tea leaf of Longjing tea from six geographical origins. Principal component analysis (PCA) was conducted on hyperspectral images to form PCA score images. Differences among samples from different geographical origins were visually observed from the PCA score images. Support vector machine (SVM) and partial least squares discriminant analysis (PLS-DA) models were built using the full spectra at the two spectral ranges. Decent classification performances were obtained at the two spectral ranges, with the overall classification accuracy of the calibration and prediction sets over 84%. Furthermore, prediction maps for geographical origins identification of Longjing tea were obtained by applying the SVM models on the hyperspectral images. The overall results illustrate that hyperspectral imaging at both spectral ranges can be applied to identify the geographical origin of single tea leaves of Longjing tea. This study provides a new, rapid, and non-destructive alternative for Longjing tea geographical origins identification.

Application of near-infrared hyperspectral imaging to identify a variety of silage maize seeds and common maize seeds

Common maize seeds and silage maize seeds are similar in appearance and are difficult to identify with the naked eye. Four varieties of common maize seeds and four varieties of silage maize seeds were identified by near-infrared hyperspectral imaging (NIR-HSI) combined with chemometrics. The pixel-wise principal component analysis was used to distinguish the differences among different varieties of maize seeds. The object-wise spectra of each single seed sample were extracted to build classification models. Support vector machine (SVM) and radial basis function neural network (RBFNN) classification models were established using two different classification strategies. First, the maize seeds were directly classified into eight varieties with the prediction accuracy of the SVM model and RBFNN model over 86%. Second, the seeds of silage maize and common maize were firstly classified with the classification accuracy over 88%, then the seeds were classified into four varieties, respectively. The classification accuracy of silage maize seeds was over 98%, and the classification accuracy of common maize seeds was over 97%. The results showed that the varieties of common maize seeds and silage maize seeds could be classified by NIR-HSI combined with chemometrics, which provided an effective means to ensure the purity of maize seeds, especially to isolate common seeds and silage seeds.

NIR-HSI and chemometrics were used to identify different varieties of common and silage maize seeds.