Identification of coffee bean varieties using hyperspectral imaging: influence of preprocessing methods and pixel-wise spectra analysis

Terahertz Spectroscopic Identification of Roast Degree and Variety of Coffee Beans

In this study, terahertz time-domain spectroscopy (THz-TDS) was proposed to identify coffee of three different varieties and three different roasting degrees of one variety. Principal component analysis (PCA) was applied to extract features from frequency-domain spectral data, and the extracted features were used for classification prediction through linear discrimination (LD), support vector machine (SVM), naive Bayes (NB), and k-nearest neighbors (KNN). The classification effect and misclassification of the model were analyzed via confusion matrix. The coffee varieties, namely Catimor, Typica 1, and Typica 2, under the condition of shallow drying were used for comparative tests. The LD classification model combined with PCA had the best effect of dimension reduction classification, while the speed and accuracy reached 20 ms and 100%, respectively. The LD model was found with the highest speed (25 ms) and accuracy (100%) by comparing the classification results of Typica 1 for three different roasting degrees. The coffee bean quality detection method based on THz-TDS combined with a modeling analysis method had a higher accuracy, faster speed, and simpler operation, and it is expected to become an effective detection method in coffee identification.

Hyperspectral estimation of chlorophyll content in jujube leaves: integration of derivative processing techniques and dimensionality reduction algorithms

The leaf chlorophyll content (LCC) of vegetation is closely related to photosynthetic efficiency and biological activity. Jujube (Ziziphus jujuba Mill.) is a traditional economic forest tree species. Non-destructive monitoring of LCC of jujube is of great significance for guiding agroforestry production and promoting ecological environment protection in arid and semi-arid lands. Hyperspectral data is an important data source for LCC detection. However, hyperspectral data consists of a multitude of bands and contains extensive information. As a result, certain bands may exhibit high correlation, leading to redundant spectral information. This redundancy can distort LCC prediction results and reduce accuracy. Therefore, it is crucial to select appropriate preprocessing methods and employ effective data mining techniques when analyzing hyperspectral data. This study aims to evaluate the performance of hyperspectral data for estimating LCC of jujube trees by integrating different derivative processing techniques with different dimensionality reduction algorithms. Hyperspectral reflectance data were obtained through simulations using an invertible forest reflectance model (INFORM) and measurements from jujube tree canopies. The least absolute shrinkage and selection operator (LASSO) and elastic net (EN) were employed to identify the important bands in the original spectra (OS), first derivative spectra (FD), and second derivative spectra (SD). Support vector regression (SVR) was used to establish the estimation model. The results show that compared with full-spectrum modeling, LASSO and EN algorithms are effective methods for preventing overfitting in LCC machine learning estimation models for different spectral derivatives. The LASSO/EN-based estimation models constructed using FD and SD exhibited superior R2 compared to the OS. The important band of SD can best reveal the relevant information of jujube LCC, and SD-EN-SVR is the most ideal model in both the simulated dataset (R2 = 0.99, RMSE=0.61) and measured dataset (R2 = 0.89, RMSE=0.91). Our results provided a reference for rapid and non-destructive estimation of the LCC of agroforestry vegetation using canopy hyperspectral data.

Classification of multi-year and multi-variety pumpkin seeds using hyperspectral imaging technology and three-dimensional convolutional neural network

BACKGROUND

Pumpkin seeds are major oil crops with high nutritional value and high oil content. The collection and identification of different pumpkin germplasm resources play a significant role in the realization of precision breeding and variety improvement. In this research, we collected 75 species of pumpkin from the Zhejiang Province of China. 35,927 near-infrared hyperspectral images of 75 types of pumpkin seeds were used as the research object.

RESULTS

To realize the rapid classification of pumpkin seed varieties, position attention embedded three-dimensional convolutional neural network (PA-3DCNN) was designed based on hyperspectral image technology. The experimental results showed that PA-3DCNN had the best classification effect than other classical machine learning technology. The classification accuracy of 99.14% and 95.20% were severally reached on the training and test sets. We also demonstrated that the PA-3DCNN model performed well in next year's classification with fine-tuning and met with 94.8% accuracy.

CONCLUSIONS

The model performance improved by introducing double convolution and pooling structure and position attention module. Meanwhile, the generalization performance of the model was verified, which can be adopted for the classification of pumpkin seeds in multiple years. This study provided a new strategy and a feasible technical approach for identifying germplasm resources of pumpkin seeds.

Deep Learning Combined with Hyperspectral Imaging Technology for Variety Discrimination of Fritillaria thunbergii

Traditional Chinese herbal medicine (TCHM) plays an essential role in the international pharmaceutical industry due to its rich resources and unique curative properties. The flowers, stems, and leaves of Fritillaria contain a wide range of phytochemical compounds, including flavonoids, essential oils, saponins, and alkaloids, which may be useful for medicinal purposes. Fritillaria thunbergii Miq. Bulbs are commonly used in traditional Chinese medicine as expectorants and antitussives. In this paper, a feasibility study is presented that examines the use of hyperspectral imaging integrated with convolutional neural networks (CNN) to distinguish twelve (12) Fritillaria varieties (n = 360). The performance of support vector machines (SVM) and partial least squares-discriminant analysis (PLS-DA) was compared with that of convolutional neural network (CNN). Principal component analysis (PCA) was used to assess the presence of cluster trends in the spectral data. To optimize the performance of the models, cross-validation was used. Among all the discriminant models, CNN was the most accurate with 98.88%, 88.89% in training and test sets, followed by PLS-DA and SVM with 92.59%, 81.94% and 99.65%, 79.17%, respectively. The results obtained in the present study revealed that application of HSI in conjunction with the deep learning technique can be used for classification of Fritillaria thunbergii varieties rapidly and non-destructively.

Visible-NIR hyperspectral classification of grass based on multivariate smooth mapping and extreme active learning approach

Grass community classification is the basis for the development of animal husbandry and dynamic monitoring of environment, which has become a critical problem to further strengthen the intelligent management of grassland. Compared with grass survey based on satellite remote sensing, the visible near infrared (NIR) hyperspectral not only monitor dynamically in a short distance, but also have high dimensions and detailed spectral information in each pixel. However, the hyperspectral labeled sample for classification is expensive and manual selection is more subjective. In order to solve above limitations, we proposed a visible-NIR hyperspectral classification model for grass based on multivariate smooth mapping and extreme active learning (MSM–EAL). Firstly, MSM is used to preprocess and reconstruct the spectrum. Secondly, by jointing XGBoost and active learning (AL), the advanced samples with the largest amount of information are actively selected to improve the performance of target classification. Innovation lies in: (1) MSM global enhanced preprocessing spectral reconstruction algorithm is proposed, in which isometric feature mapping is effectively applied to the grass hyperspectral for the first time. (2) EAL framework is constructed to solve the issue of high cost and small number for hyperspectral labeled samples, at the same time, enhance the physical essence behind spectral classification more intuitively. A field hyperspectral collection platform is assembled to establish nm resolution visible-NIR hyperspectral dataset of grass, Grass1, containing 750 samples, which to verify the effectiveness of the model. Experiments on the Grass1 dataset confirmed that compared with the full spectrum, the time consumption of MSM was reduced by 9.471 s with guaranteed overall accuracy (OA). Comparing EAL with AL, and other classification algorithms, EAL improves OA 22.2% over AL, and XAL has the best performance value on Kappa, Macro, Recall and F1-score, respectively. Altogether, the lightweight MSM–EAL model realizes intelligent and real-time classification, providing a new method for obtaining high-precision inter group classification of grass.

A Rapid Non-Destructive Hyperspectral Imaging Data Model for the Prediction of Pungent Constituents in Dried Ginger

Ginger is best known for its aromatic odour, spicy flavour and health-benefiting properties. Its flavour is derived primarily from two compound classes (gingerols and shogaols), with the overall quality of the product depending on the interaction between these compounds. Consequently, a robust method for determining the ratio of these compounds would be beneficial for quality control purposes. This study investigated the feasibility of using hyperspectral imaging to rapidly determine the ratio of 6-gingerol to 6-shogoal in dried ginger powder. Furthermore, the performance of several pre-processing methods and two multivariate models was explored. The best-performing models used partial least squares regression (PSLR) and least absolute shrinkage and selection operator (LASSO), using multiplicative scatter correction (MSC) and second derivative Savitzky–Golay (2D-SG) pre-processing. Using the full range of wavelengths (~400–1000 nm), the performance was similar for PLSR (R² ≥ 0.73, RMSE ≤ 0.29, and RPD ≥ 1.92) and LASSO models (R² ≥ 0.73, RMSE ≤ 0.29, and RPD ≥ 1.94). These results suggest that hyperspectral imaging combined with chemometric modelling may potentially be used as a rapid, non-destructive method for the prediction of gingerol-to-shogaol ratios in powdered ginger samples.

Visual detection of microbial community during three bacteria mixed fermentation through hyperspectral imaging technology

Hyperspectral imaging technology with chemometrics was used for identifying and counting each species in microbial community during mixed fermentation. Hyperspectral images of microbial community of <i>Enterobacter</i> sp, <i>Acetobacter pasteurianus</i>, and <i>Lactobacillus paracasei</i> colonies were obtained and the spectra of strain colonies were extracted. Identification models were developed using linear discriminant analysis (LDA) and least-squares support vector machine (LS-SVM) by using 23 variables selected by genetic algorithm. The optimal LS-SVM model with identification rate of 96.67 % was used to identify colonies and prepare colony distribution maps in color for strains counting. The counting results by hyperspectral imaging technology agree with that of the manual counting method with average relative error of 3.70 %. The developed counting method has been successfully used to identify and count the specific strain from the mixed strains simultaneously. The hyperspectral imaging technology has a great potential to monitor changes in the microbial community structure.

SVM optimization using a grid search algorithm to identify robusta coffee bean images based on circularity and eccentricity

Coffee variety is one of the main factors affecting the quality and price of coffee, so it is important to recognize coffee varieties. This study aims to optimize the recognition of robusta coffee beans based on circularity and eccentricity image features using a support vector machine (SVM) and Grid search algorithm. The methods used included image acquisition, preprocessing, feature extraction, classification, and evaluation. Circularity and eccentricity are used in the feature extraction process, while the grid search algorithm is used to optimize SVM parameters in the classification process for four different kernels. This study produced the best classification model with the highest accuracy of 94% for the RBF and Polynomial kernels.

Agricultural Potentials of Molecular Spectroscopy and Advances for Food Authentication: An Overview

Meat, fish, coffee, tea, mushroom, and spices are foods that have been acknowledged for their nutritional benefits but are also reportedly targets of fraud and tampering due to their economic value. Conventional methods often take precedence for monitoring these foods, but rapid advanced instruments employing molecular spectroscopic techniques are gradually claiming dominance due to their numerous advantages such as low cost, little to no sample preparation, and, above all, their ability to fingerprint and detect a deviation from quality. This review aims to provide a detailed overview of common molecular spectroscopic techniques and their use for agricultural and food quality management. Using multiple databases including ScienceDirect, Scopus, Web of Science, and Google Scholar, 171 research publications including research articles, review papers, and book chapters were thoroughly reviewed and discussed to highlight new trends, accomplishments, challenges, and benefits of using molecular spectroscopic methods for studying food matrices. It was observed that Near infrared spectroscopy (NIRS), Infrared spectroscopy (IR), Hyperspectral imaging (his), and Nuclear magnetic resonance spectroscopy (NMR) stand out in particular for the identification of geographical origin, compositional analysis, authentication, and the detection of adulteration of meat, fish, coffee, tea, mushroom, and spices; however, the potential of UV/Vis, 1H-NMR, and Raman spectroscopy (RS) for similar purposes is not negligible. The methods rely heavily on preprocessing and chemometric methods, but their reliance on conventional reference data which can sometimes be unreliable, for quantitative analysis, is perhaps one of their dominant challenges. Nonetheless, the emergence of handheld versions of these techniques is an area that is continuously being explored for digitalized remote analysis.

Differentiation of Organic Cocoa Beans and Conventional Ones by Using Handheld NIR Spectroscopy and Multivariate Classification Techniques

The global market for organic cocoa beans continues to show sturdy growth. A low-cost handheld NIR spectrometer (900-1700 nm) combined with multivariate classification algorithms was used for rapid differentiation analysis of organic cocoa beans' integrity. In this research, organic and conventionally cultivated cocoa beans were collected from different locations in Ghana and scanned nondestructively with a handheld spectrometer. Different preprocessing treatments were employed. Principal component analysis (PCA) and classification analysis, RF (random forest), KNN (K-nearest neighbours), LDA (linear discriminant analysis), and PLS-DA (partial least squares-discriminant analysis) were performed comparatively to build classification models. The performance of the models was evaluated by accuracy, specificity, sensitivity, and efficiency. Second derivative preprocessing together with PLS-DA algorithm was superior to the rest of the algorithms with a classification accuracy of 100.00% in both the calibration set and prediction set. Second derivative algorithm was found to be the best preprocessing tool. The identification rates for the calibration set and prediction set were 96.15% and 98.08%, respectively, for RF, 91.35% and 92.31% for KNN, and 90.38% and 98.08% for LDA. Generally, the results showed that a handheld NIR spectrometer coupled with an appropriate multivariate algorithm could be used in situ for the differentiation of organic cocoa beans from conventional ones to ensure food integrity along the cocoa bean value chain.

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Food quality and safety are strongly related to human health. Food quality varies with variety and geographical origin, and food fraud is becoming a threat to domestic and global markets. Visible/infrared spectroscopy and hyperspectral imaging techniques, as rapid and non-destructive analytical methods, have been widely utilized to trace food varieties and geographical origins. In this review, we outline recent research progress on identifying food varieties and geographical origins using visible/infrared spectroscopy and hyperspectral imaging with the help of machine learning techniques. The applications of visible, near-infrared, and mid-infrared spectroscopy as well as hyperspectral imaging techniques on crop food, beverage, fruits, nuts, meat, oil, and some other kinds of food are reviewed. Furthermore, existing challenges and prospects are discussed. In general, the existing machine learning techniques contribute to satisfactory classification results. Follow-up researches of food varieties and geographical origins traceability and development of real-time detection equipment are still in demand.

Detection of Insect Damage in Green Coffee Beans Using VIS-NIR Hyperspectral Imaging

The defective beans of coffee are categorized into black beans, fermented beans, moldy beans, insect damaged beans, parchment beans, and broken beans, and insect damaged beans are the most frequently seen type. In the past, coffee beans were manually screened and eye strain would induce misrecognition. This paper used a push-broom visible-near infrared (VIS-NIR) hyperspectral sensor to obtain the images of coffee beans, and further developed a hyperspectral insect damage detection algorithm (HIDDA), which can automatically detect insect damaged beans using only a few bands and one spectral signature. First, by taking advantage of the constrained energy minimization (CEM) developed band selection methods, constrained energy minimization-constrained band dependence minimization (CEM-BDM), minimum variance band prioritization (MinV-BP), maximal variance-based bp (MaxV-BP), sequential forward CTBS (SF-CTBS), sequential backward CTBS (SB-CTBS), and principal component analysis (PCA) were used to select the bands, and then two classifier methods were further proposed. One combined CEM with support vector machine (SVM) for classification, while the other used convolutional neural networks (CNN) and deep learning for classification where six band selection methods were then analyzed. The experiments collected 1139 beans and 20 images, and the results demonstrated that only three bands are really need to achieve 95% of accuracy and 90% of kappa coefficient. These findings show that 850–950 nm is an important wavelength range for accurately identifying insect damaged beans, and HIDDA can indeed detect insect damaged beans with only one spectral signature, which will provide an advantage in the process of practical application and commercialization in the future.

Detection of adulteration in food based on nondestructive analysis techniques: a review

In recent years, people pay more and more attention to food quality and safety, which are significantly relating to human health. Food adulteration is a world-wide concerned issue relating to food quality and safety, and it is difficult to be detected. Modern detection techniques (high performance liquid chromatography, gas chromatography-mass spectrometer, etc.) can accurately identify the types and concentrations of adulterants in different food types. However, the characteristics as expensive, low efficient and complex sample preparation and operation limit the use of these techniques. The rapid, nondestructive and accurate detection techniques of food adulteration is of great and urgent demand. This paper introduced the principles, advantages and disadvantages of the nondestructive analysis techniques and reviewed the applications of these techniques in food adulteration screen in recent years. Differences among these techniques, differences on data interpretation and future prospects were also discussed.

Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging

Black goji berry (Lycium ruthenicum Murr.) has great commercial and nutritional values. Near-infrared hyperspectral imaging (NIR-HSI) was used to determine total phenolics, total flavonoids and total anthocyanins in dry black goji berries. Convolutional neural networks (CNN) were designed and developed to predict the chemical compositions. These CNN models and deep autoencoder were used as supervised and unsupervised feature extraction methods, respectively. Partial least squares (PLS) and least-squares support vector machine (LS-SVM) as modelling methods, successive projections algorithm and competitive adaptive reweighted sampling (CARS) as wavelength selection methods, and principal component analysis (PCA) and wavelet transform (WT) as feature extraction methods were studied as conventional approaches for comparison. Deep learning approaches as modelling methods and feature extraction methods obtained good and equivalent performances to the conventional methods. The results illustrated that deep learning had great potential as modelling and feature extraction methods for chemical compositions determination in NIR-HSI.

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.

Investigation on Data Fusion of Multisource Spectral Data for Rice Leaf Diseases Identification Using Machine Learning Methods

Rice diseases are major threats to rice yield and quality. Rapid and accurate detection of rice diseases is of great importance for precise disease prevention and treatment. Various spectroscopic techniques have been used to detect plant diseases. To rapidly and accurately detect three different rice diseases [leaf blight (Xanthomonas oryzae pv. Oryzae), rice blast (Pyricularia oryzae), and rice sheath blight (Rhizoctonia solani)], three spectroscopic techniques were applied, including visible/near-infrared hyperspectral imaging (HSI) spectra, mid-infrared spectroscopy (MIR), and laser-induced breakdown spectroscopy (LIBS). Three different levels of data fusion (raw data fusion, feature fusion, and decision fusion) fusing three different types of spectral features were adopted to categorize the diseases of rice. Principal component analysis (PCA) and autoencoder (AE) were used to extract features. Identification models based on each technique and different fusion levels were built using support vector machine (SVM), logistic regression (LR), and convolution neural network (CNN) models. Models based on HSI performed better than those based on MIR and LIBS, with the accuracy over 93% for the test set based on PCA features of HSI spectra. The performance of rice disease identification varied with different levels of fusion. The results showed that feature fusion and decision fusion could enhance identification performance. The overall results illustrated that the three techniques could be used to identify rice diseases, and data fusion strategies have great potential to be used for rice disease detection.

Application of Near-Infrared Hyperspectral Imaging with Machine Learning Methods to Identify Geographical Origins of Dry Narrow-Leaved Oleaster (Elaeagnus angustifolia) Fruits

Narrow-leaved oleaster (Elaeagnus angustifolia) fruit is a kind of natural product used as food and traditional medicine. Narrow-leaved oleaster fruits from different geographical origins vary in chemical and physical properties and differ in their nutritional and commercial values. In this study, near-infrared hyperspectral imaging covering the spectral range of 874–1734 nm was used to identify the geographical origins of dry narrow-leaved oleaster fruits with machine learning methods. Average spectra of each single narrow-leaved oleaster fruit were extracted. Second derivative spectra were used to identify effective wavelengths. Partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were used to build discriminant models for geographical origin identification using full spectra and effective wavelengths. In addition, deep convolutional neural network (CNN) models were built using full spectra and effective wavelengths. Good classification performances were obtained by these three models using full spectra and effective wavelengths, with classification accuracy of the calibration, validation, and prediction set all over 90%. Models using effective wavelengths obtained close results to models using full spectra. The performances of the PLS-DA, SVM, and CNN models were close. The overall results illustrated that near-infrared hyperspectral imaging coupled with machine learning could be used to trace geographical origins of dry narrow-leaved oleaster fruits.

Rapid Classification of Wheat Grain Varieties Using Hyperspectral Imaging and Chemometrics

The classification of wheat grain varieties is of great value because its high purity is the yield and quality guarantee. In this study, hyperspectral imaging combined with the chemometric methods was applied to explore and implement the varieties classification of wheat seeds. The hyperspectral images of all the samples covering 874–1734 nm bands were collected. Exploratory analysis was first carried out while using principal component analysis (PCA) and linear discrimination analysis (LDA). Spectral preprocessing methods including standard normal variate (SNV), multiplicative scatter correction (MSC), and wavelet transform (WT) were introduced, and their effects on discriminant models were studied to eliminate the interference of instrumental and environmental factors. PCA loading, successive projections algorithm (SPA), and random frog (RF) were applied to extract feature wavelengths for redundancy elimination owing to the possibility of existing redundant spectral information. Classification models were developed based on full wavelengths and feature wavelengths using LDA, support vector machine (SVM), and extreme learning machine (ELM). This optimal model was finally utilized to generate visualization map to observe the classification performance intuitively. When comparing with other models, ELM based on full wavelengths achieved the best accuracy up to 91.3%. The overall results suggested that hyperspectral imaging was a potential tool for the rapid and accurate identification of wheat varieties, which could be conducted in large-scale seeds classification and quality detection in modern seed industry.

Identification of Soybean Varieties Using Hyperspectral Imaging Coupled with Convolutional Neural Network

Soybean variety is connected to stress resistance ability, as well as nutritional and commercial value. Near-infrared hyperspectral imaging was applied to classify three varieties of soybeans (Zhonghuang37, Zhonghuang41, and Zhonghuang55). Pixel-wise spectra were extracted and preprocessed, and average spectra were also obtained. Convolutional neural networks (CNN) using the average spectra and pixel-wise spectra of different numbers of soybeans were built. Pixel-wise CNN models obtained good performance predicting pixel-wise spectra and average spectra. With the increase of soybean numbers, performances were improved, with the classification accuracy of each variety over 90%. Traditionally, the number of samples used for modeling is large. It is time-consuming and requires labor to obtain hyperspectral data from large batches of samples. To explore the possibility of achieving decent identification results with few samples, a majority vote was also applied to the pixel-wise CNN models to identify a single soybean variety. Prediction maps were obtained to present the classification results intuitively. Models using pixel-wise spectra of 60 soybeans showed equivalent performance to those using the average spectra of 810 soybeans, illustrating the possibility of discriminating soybean varieties using few samples by acquiring pixel-wise spectra.

Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.

Identifying Freshness of Spinach Leaves Stored at Different Temperatures Using Hyperspectral Imaging

Spinach is prone to spoilage in the course of preservation. Spinach leaves stored at different temperatures for different durations will have varying degrees of freshness. In order to monitor the freshness of spinach leaves during storage, a rapid and non-destructive method—hyperspectral imaging technology—was applied in this study. Visible near-infrared reflectance (Vis-NIR) (380–1030 nm) and near-infrared reflectance (NIR) (874–1734 nm) hyperspectral imaging systems were used. Spinach leaves preserved at different temperatures with different durations (0, 3, 6, 9 days at 4 °C and 0, 1, 2 days at 20 °C) were studied. Principal component analysis (PCA) was adopted as a qualitative analysis method. The second-order derivative spectra were utilized to select effective wavelengths. Partial least squares discriminant analysis (PLS-DA), support vector machine (SVM), and extreme learning machine (ELM) were used to build models based on full spectra and effective wavelengths. All three models achieved good results, with accuracies above 92% for both Vis-NIR spectra and NIR spectra. ELM obtained the best results, with all accuracies reaching 100%. The overall results indicate the possibility of the freshness identification of spinach preserved at different temperatures for different durations using two kinds of hyperspectral imaging systems.

Nondestructive Determination and Visualization of Quality Attributes in Fresh and Dry Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging

Rapid and nondestructive determination of quality attributes in fresh and dry Chrysanthemum morifolium is of great importance for quality sorting and monitoring during harvest and trade. Near-infrared hyperspectral imaging covering the spectral range of 874–1734 nm was used to detect chlorogenic acid, luteolin-7-O-glucoside, and 3,5-O-dicaffeoylquinic acid content in Chrysanthemum morifolium. Fresh and dry Chrysanthemum morifolium flowers were studied for harvest and trade. Pixelwise spectra were preprocessed by wavelet transform (WT) and area normalization, and calculated as average spectrum. Successive projections algorithm (SPA) was used to select optimal wavelengths. Partial least squares (PLS), extreme learning machine (ELM), and least-squares support vector machine (LS-SVM) were used to build calibration models based on full spectra and optimal wavelengths. Calibration models of fresh and dry flowers obtained good results. Calibration models for chlorogenic acid in fresh flowers obtained best performances, with coefficient of determination (R2) over 0.85 and residual predictive deviation (RPD) over 2.50. Visualization maps of chlorogenic acid, luteolin-7-O-glucoside, and 3,5-O-dicaffeoylquinic acid in single fresh and dry flowers were obtained. The overall results showed that hyperspectral imaging was feasible to determine chlorogenic acid, luteolin-7-O-glucoside, and 3,5-O-dicaffeoylquinic acid. Much more work should be done in the future to improve the prediction performance.

Variety identification of oat seeds using hyperspectral imaging: investigating the representation ability of deep convolutional neural network

Variety identification of seeds is critical for assessing variety purity and ensuring crop yield. In this paper, a novel method based on hyperspectral imaging (HSI) and deep convolutional neural network (DCNN) was proposed to discriminate the varieties of oat seeds. The representation ability of DCNN was also investigated. The hyperspectral images with a spectral range of 874–1734 nm were primarily processed by principal component analysis (PCA) for exploratory visual distinguishing. Then a DCNN trained in an end-to-end manner was developed. The deep spectral features automatically learnt by DCNN were extracted and combined with traditional classifiers (logistic regression (LR), support vector machine with RBF kernel (RBF_SVM) and linear kernel (LINEAR_SVM)) to construct discriminant models. Contrast models were built based on the traditional classifiers using full wavelengths and optimal wavelengths selected by the second derivative (2nd derivative) method. The comparison results showed that all DCNN-based models outperformed the contrast models. DCNN trained in an end-to-end manner achieved the highest accuracy of 99.19% on the testing set, which was finally employed to visualize the variety classification. The results demonstrated that the deep spectral features with outstanding representation ability enabled HSI together with DCNN to be a reliable tool for rapid and accurate variety identification, which would help to develop an on-line system for quality detection of oat seeds as well as other grain seeds.

The excellent representation ability of deep spectral features enables hyperspectral imaging combined with deep convolutional neural network to be a powerful tool for large-scale seeds detection in modern seed industry.

Large-aperture UV (250~400 nm) imaging spectrometer based on a solid Sagnac interferometer

Developing an ultraviolet (UV) imaging spectrometer is challenging due to a low level of incident power of photon flux, large chromatic aberration, and relatively low quantum efficiency of imaging sensor in UV waveband. In this paper, a large-aperture UV (250~400 nm) Fourier transform imaging spectrometer is presented for close-range hyperspectral sensing with high spatial resolution and decent spectral resolution. An advanced design based on a modified solid Sagnac interferometer working in UV waveband of 250~400 nm is introduced to improve the interferometric stability. A large-aperture and a reflective-transmissive filtering system are used to increase the spectral purity of the incident UV radiation, and air-spaced achromatic doublets are designed to address the chromatic aberration. The finished spectrometer has a spatial resolution of 23.44 μm on the target plane, a wavelengths resolution of 1.59 nm at 250 nm, and can provide approximately 59 wavelength samples over the waveband of 250~400 nm. The proposed imaging spectrometer acquires a hyperspectral data cube through push-broom scanning in a few minutes. Examples of UV hyperspectral imaging are demonstrated with a sample of resolution test chart, and a cotton sample with vitamin C (VC) and vitamin B6 (VB6) traces. Based on the analysis of spectra, monochromatic images, and k-Means clustering results, it can be concluded that the spectrometer is capable of UV hyperspectral imaging with excellent spectral accuracy, spatial performance, compactness, and robustness. The potential applications of the proposed instrument include materials analysis and traces detection with UV spectral characteristics.

Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging

Different varieties of raisins have different nutritional properties and vary in commercial value. An identification method of raisin varieties using hyperspectral imaging was explored. Hyperspectral images of two different varieties of raisins (Wuhebai and Xiangfei) at spectral range of 874–1734 nm were acquired, and each variety contained three grades. Pixel-wise spectra were extracted and preprocessed by wavelet transform and standard normal variate, and object-wise spectra (sample average spectra) were calculated. Principal component analysis (PCA) and independent component analysis (ICA) of object-wise spectra and pixel-wise spectra were conducted to select effective wavelengths. Pixel-wise PCA scores images indicated differences between two varieties and among different grades. SVM (Support Vector Machine), k-NN (k-nearest Neighbors Algorithm), and RBFNN (Radial Basis Function Neural Network) models were built to discriminate two varieties of raisins. Results indicated that both SVM and RBFNN models based on object-wise spectra using optimal wavelengths selected by PCA could be used for raisin variety identification. The visualization maps verified the effectiveness of using hyperspectral imaging to identify raisin varieties.

Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network

Rapid and accurate discrimination of Chrysanthemum varieties is very important for producers, consumers and market regulators. The feasibility of using hyperspectral imaging combined with deep convolutional neural network (DCNN) algorithm to identify Chrysanthemum varieties was studied in this paper. Hyperspectral images in the spectral range of 874–1734 nm were collected for 11,038 samples of seven varieties. Principal component analysis (PCA) was introduced for qualitative analysis. Score images of the first five PCs were used to explore the differences between different varieties. Second derivative (2nd derivative) method was employed to select optimal wavelengths. Support vector machine (SVM), logistic regression (LR), and DCNN were used to construct discriminant models using full wavelengths and optimal wavelengths. The results showed that all models based on full wavelengths achieved better performance than those based on optimal wavelengths. DCNN based on full wavelengths obtained the best results with an accuracy close to 100% on both training set and testing set. This optimal model was utilized to visualize the classification results. The overall results indicated that hyperspectral imaging combined with DCNN was a very powerful tool for rapid and accurate discrimination of Chrysanthemum varieties. The proposed method exhibited important potential for developing an online Chrysanthemum evaluation system.

Determination of Total Polysaccharides and Total Flavonoids in Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging and Multivariate Analysis

The rapid and nondestructive determination of active compositions in Chrysanthemum morifolium (Hangbaiju) is of great value for producers and consumers. Hyperspectral imaging as a rapid and nondestructive technique was used to determine total polysaccharides and total flavonoids content in Chrysanthemum morifolium. Hyperspectral images of different sizes of Chrysanthemum morifolium flowers were acquired. Pixel-wise spectra within all samples were preprocessed by wavelet transform (WT) followed by standard normal variate (SNV). Partial least squares (PLS) and least squares-support vector machine (LS-SVM) were used to build prediction models using sample average spectra calculated by preprocessed pixel-wise spectra. The LS-SVM model performed better than the PLS models, with the determination of the coefficient of calibration (R²c) and prediction (R²p) being over 0.90 and the residual predictive deviation (RPD) being over 3 for total polysaccharides and total flavonoids content prediction. Prediction maps of total polysaccharides and total flavonoids content in Chrysanthemum morifolium flowers were successfully obtained by LS-SVM models, which exhibited the best performances. The overall results showed that hyperspectral imaging was a promising technique for the rapid and accurate determination of active ingredients in Chrysanthemum morifolium, indicating the great potential to develop an online system for the quality determination of Chrysanthemum morifolium.

Detection of Oil Chestnuts Infected by Blue Mold Using Near-Infrared Hyperspectral Imaging Combined with Artificial Neural Networks

Mildew damage is a major reason for chestnut poor quality and yield loss. In this study, a near-infrared hyperspectral imaging system in the 874⁻1734 nm spectral range was applied to detect the mildew damage to chestnuts caused by blue mold. Principal component analysis (PCA) scored images were firstly employed to qualitatively and intuitively distinguish moldy chestnuts from healthy chestnuts. Spectral data were extracted from the hyperspectral images. A successive projections algorithm (SPA) was used to select 12 optimal wavelengths. Artificial neural networks, including back propagation neural network (BPNN), evolutionary neural network (ENN), extreme learning machine (ELM), general regression neural network (GRNN) and radial basis neural network (RBNN) were used to build models using the full spectra and optimal wavelengths to distinguish moldy chestnuts. BPNN and ENN models using full spectra and optimal wavelengths obtained satisfactory performances, with classification accuracies all surpassing 99%. The results indicate the potential for the rapid and non-destructive detection of moldy chestnuts by hyperspectral imaging, which would help to develop online detection system for healthy and blue mold infected chestnuts.