Search

The appearance of tea leaves is the most intuitive factor in assessing their quality and is an important indicator of the price. The study utilizes machine vision and hyperspectral image technology to develop a rapid method for assessing the appearance quality of seven grades of Dianhong Congou black tea samples based on shape, color, texture, and feature fusion. Using the shape metrics of length, width, perimeter, narrowness, area, and rectangularity, 88 texture values, and nine color values as features, the effectiveness of intelligent recognition algorithms such as support vector machine, random forest, and least squares support vector machine (LSSVM) in classifying single features (shape, color, and texture) and fused data models of the categories of Dianhong tea samples was explored. The results showed that the accuracy of the feature fusion-based appearance quality evaluation models was all higher than the modeling results of the corresponding single features, and the accuracy of the LSSVM model based on the fused data was 100%. This study showed that feature data fusion reflects the external information of tea leaves more comprehensively and that intelligent classification algorithms combined with image analysis techniques were an effective strategy for the identification of regional black tea. [ABSTRACT FROM AUTHOR]

The taste of tea is one of the key indicators in the evaluation of its quality and is a key factor in its grading and market pricing. To objectively and digitally evaluate the taste quality of tea leaves, miniature near-infrared (NIR) spectroscopy and electronic tongue (ET) sensors are considered effective sensor signals for the characterization of the taste quality of tea leaves. This study used micro-NIR spectroscopy and ET sensors in combination with data fusion strategies and chemometric tools for the taste quality assessment and prediction of multiple grades of black tea. Using NIR features and ET sensor signals as fused information, the data optimization based on grey wolf optimization, ant colony optimization (ACO), particle swarm optimization, and non-dominated sorting genetic algorithm II were employed as modeling features, combined with support vector machine (SVM), extreme learning machine and K-nearest neighbor algorithm to build the classification models. The results obtained showed that the ACO−SVM model had the highest classification accuracy with a discriminant rate of 93.56%. The overall results reveal that it is feasible to qualitatively distinguish black tea grades and categories by NIR spectroscopy and ET techniques. [ABSTRACT FROM AUTHOR]

Summary: Food fraud causes significant economic losses for the industry and generates distrust between the consumers and traders. Tea is one of the most valued beverages throughout the world, being vulnerable to economically motivated cheat. The objective of the study was to develop the potential of hyperspectral imaging (HSI) allying multivariate analysis and data fusion to identify the authenticity of Keemun black tea quality categories. Data fusion that integrated of texture characteristics based on grey level co‐occurrence matrix and visible and near‐infrared spectral features via competitive adaptive reweighted sampling (CARS) was as the target data for modelling. Support vector machine (SVM) and random forest (RF) were utilised for the classification of tea samples of seven grades. The RF model using fused data gave the best performance with the correct discriminant rate of 92.70% for the prediction set. This study demonstrated that HSI coupled with RF was effective in identifying tea sample rank. [ABSTRACT FROM AUTHOR]

BACKGROUND Tea (Camellia sinensis L) is a highly nutritious beverage with commercial value globally. However, it is at risk of economic fraud. This study aims to develop a powerful evaluation method to distinguish Chinese official Dianhong tea from various other categories, employing hyperspectral imaging (HSI) technology and chemometric algorithms. RESULTS: Two matrix statistical algorithms encompassing a gray‐level co‐occurrence matrix (GLCM) and a gradient co‐occurrence matrix (GLGCM) are used to extract HSI texture data. Three novel spectral variable screening methods are utilized to select wavenumbers of near‐infrared (NIR) spectra: iteratively retaining informative variables (IRIV), interval random frog, and variable combination population analysis. Feature fusion of image texture characteristics and spectra data are the eigenvectors for model building. Authentic classification models are constructed using the extreme learning machine approach and the least squares support vector machine (LSSVM) approach, coupling them with features from wavelength extraction techniques for assessing the quality of Dianhong black tea. The results demonstrate that the LSSVM model using fused data (IRIV + GLGCM) provides the best results and achieves a predictive precision of 99.57%. CONCLUSION: This study confirms that HSI coupled with LSSVM is effective in differentiating authentic Dianhong black tea samples. © 2020 Society of Chemical Industry [ABSTRACT FROM AUTHOR]

The evaluation of Chinese dianhong black tea (CDBT) grades was an important indicator to ensure its quality. A handheld spectroscopy system combined with chemometrics was utilized to assess CDBT from eight grades. Both variables selection methods, namely genetic algorithm (GA) and successive projections algorithm (SPA), were employed to acquire the feature variables of each sample spectrum. A partial least‐squares discriminant analysis (PLS‐DA) and support vector machine (SVM) algorithms were applied for the establishment of the grading discrimination models based on near‐infrared spectroscopy (NIRS). Comparisons of the portable and benchtop NIRS systems were implemented to obtain the optimal discriminant models. Experimental results showed that GA‐SVM models by the handheld sensors yielded the best predictive performance with the correct discriminant rate (CDR) of 98.75% and 100% in the training set and prediction set, respectively. This study demonstrated that the handheld system combined with a suitable chemometric and feature information selection method could successfully be used for the rapid and efficient discrimination of CDBT rankings. It was promising to establish a specific economical portable NIRS sensor for in situ quality assurance of CDBT grades. [ABSTRACT FROM AUTHOR]

A total 206 samples of green, yellow, white, black, and Oolong teas were utilized to acquire hyperspectral imaging, and five tea categories were identified based on visible and near-infrared (NIR) hyperspectral imaging, combined with classification pattern recognition. The characteristic spectra were extracted from the region of interest (ROI), and the standard normal variate (SNV) method was preprocessed to reduce background noise. Four dominant wavelengths (589, 635, 670, and 783 nm) were selected by principal component analysis (PCA) as spectral features. Textural features were extracted by the Grey-level co-occurrence matrix (GLCM) from images at selected dominant wavelengths. Linear discriminant analysis (LDA), library support vector machine (Lib-SVM), and extreme learning machine (ELM) classification models were established based on full spectra, spectral features, textural features, and data fusion, respectively. Lib-SVM was the best model with the input data fusion, and the correct classification rate (CCR) achieved 98.39%. The results implied that visible and NIR hyperspectral imaging combined with Lib-SVM has the capability of rapidly and non-destructively classifying tea categories. [ABSTRACT FROM AUTHOR]

The main objectives of the study are to understand and explore critical feature wavelengths of the obtained near-infrared (NIR) data relating to dianhong black tea quality categories, we propose a multi-variable selection strategy based on the variable space optimization from big to small which is the kernel idea of a variable combination of the improved genetic algorithm (IGA) and particle swarm optimization (PSO) in this study. A rapid description based on the NIR technology is implemented to assess black tea tenderness and rankings. First, 700 standard samples from dianhong black tea of seven quality classes are scanned using a NIR system. The raw spectra acquired are preprocessed by Savitzky-Golay (SG) filtering coupled with standard normal variate transformation (SNV). Then, the multi-variable selection algorithm (IGA-PSO) is applied to compare with the single method (the IGA and PSO) and search the optimal characteristic wavelengths. Finally, the identification models are developed using a decision tree (DT), partial least-squares discriminant analysis (PLS-DA), and support vector machine (SVM) based on different kernel functions combined with the effective features from the above variables screening paths for the discrimination of black tea quality. The results show that the IGA-PSO-SVM model with a radial basis function achieves the best predictive results with the correct discriminant rate (CDR) of 95.28% based on selected four characteristic variables in the prediction process. The overall results demonstrate that NIR combined with a multi-variable selection method can constitute a potential tool to understand the most important features involved in the evaluation of dianhong black tea quality helping the instrument manufacturers to achieve the development of low-cost and handheld NIR sensors. Unlabelled Image • Rapid description of black tea quality based on multi-variable selection strategy • Feature information was selected by the GA, IGA and PSO. • Classification models for black tea categories developed using DT, PLS-DA and SVM • The SVM discriminator is implemented with four different kernel functions. • The IGA-PSO-SVM model obtained better predictive results based on four feature wavelengths. [ABSTRACT FROM AUTHOR]

• Assessing tea rank by Vis-NIR spectra and a hybrid variable selection strategy. • Feature data are selected by the GA, IRIV, VCPA, VCPA-GA, and VCPA-IRIV. • Authentication models for tea ranks are created using LSSVM, RF, and BPNN. • The VCPA-IRIV-LSSVM model obtains superior performance. Tea is one of the most consumed and popular beverages around the world. Authenticating tea quality is essential to resist counterfeit goods and prevent fraud. This study innovatively aims to use a visible-near infrared (Vis-NIR) sensor combined with a variable combination population analysis (VCPA)-based hybrid variable selection algorithm to realize the authentication of tea quality. First, the spectra of 700 tea samples from seven different grades are acquired using a Vis-NIR sensor. Second, the raw spectra acquired are preprocessed by Savitzky-Golay convolution smoothing combined with first derivative (SG1), standard normal variate transformation (SNV), and multiplicative scatter correction (MSC), and the best pretreating technique is determined by support vector machine (SVM) algorithm. Third, the VCPA-based hybrid method optimizes the variable space of the optimal pretreated spectra data in the first step, and a genetic algorithm (GA) and iteratively retaining informative variables (IRIV) are utilized to execute further optimization and shrink the variable in the second step. Finally, authentication models of tea quality are constructed employing least squares support vector machine (LSSVM), random forest (RF), and back propagation neural network (BPNN) approaches based on the selected variables. The results show that the VCPA-IRIV-LSSVM model obtains the best predictive performance with an accuracy of 97.40% in the predictive process. Our findings demonstrate that it is feasible to apply the inexpensive vis-NIR sensor to assess quality attributes in tea. Also, the VCPA-based hybrid method can search the combination of the optimal wavelength and improve the identification accuracy and robustness of the model and can assist sensor manufacturers in developing a cheap and user-friendly smartphone-coupled micro spectroscopic sensor for authentication of tea quality. [ABSTRACT FROM AUTHOR]

[Display omitted] • Digital diagnosis of Dianhong black tea quality using pocket-sized NIR. • Optimizing features by the PSO, ACO, SA, and GWO. • Recognition models for black tea categories were developed using ELM, PLS-DA, and SVM combined with the selected features. • The GWO-SVM model achieves the expected predictive performance. This paper investigates the feasibility of combining portable near-infrared (NIR) spectroscopy with chemometric algorithms to improve the quality prediction performance of Dianhong black tea. This study presented a pocket-sized NIR device (defined as NIR-S-R2) for the simultaneous identification of multiple categories of Dianhong black tea. Firstly, the spectral information of 700 multi-category Dianhong tea samples was sensed by the NIR-S-R2 system and high-quality analytical spectra of the samples were obtained by comparing multiple spectral pre-processing algorithms. Then, based on the best pre-processed spectral data, four characteristic wavelength evolution algorithms, namely particle swarm optimization, ant colony optimization, simulated annealing, and grey wolf optimization (GWO), were employed to obtain the characteristic spectral variables. Finally, extreme learning machine, partial least squares discriminant analysis, and support vector machine (SVM) methods were adopted to develop recognition models for seven categories of Dianhong black tea based on the selected features. The results showed that the GWO-SVM model had the best predictive capability, with a prediction accuracy of 91.42%. At suitable spectral wavelengths, the NIR-S-R2 system combined with chemometrics offers good discriminatory accuracy and potential for the application of extended detection. [ABSTRACT FROM AUTHOR]

• A novel solution phase CSA was used for monitoring black tea fermentation. • UV-visible spectroscopy was employed to obtain CSA features in real time. • The accuracy of CARS-SVM model for discriminating fermentation degree was 100%. • Accurate prediction models for catechins and theaflavins were obtained. Rapid monitoring of fermentation quality has been the key to realizing the intelligent processing of black tea. In our study, mixing ratios, sensing array components and reaction times were optimized before an optimal solution phase colorimetric sensor array was constructed. The characteristic spectral information of the array was obtained by UV–visible spectroscopy and subsequently combined with machine learning algorithms to construct a black tea fermentation quality evaluation model. The competitive adaptive reweighting algorithms (CARS)-support vector machine model discriminated the black tea fermentation degree with 100% accuracy. For quantification of catechins and four theaflavins (TF, TFDG, TF-3-G, and TF-3′-G), the correlation coefficients of the CARS least square support vector machine model prediction set were 0.91, 0.86, 0.76, 0.72 and 0.79, respectively. The results obtained within 2 min enabled accurate monitoring of the fermentation quality of black tea, which provides a new method and idea for intelligent black tea processing. [ABSTRACT FROM AUTHOR]

[Display omitted] • Six from fifteen pH indicators sensitive to the gas of withered leaves were selected. • An effective gas sensor array including six selected pH indicators was prepared. • Sensor array combining with hyperspectral imaging were used for withering evaluation. • PCA effectively reduced dimensionality of HSI data and improved model's accuracy. • Developed LS-SVM model can accurately determine withering degree of black tea. Withering is one of the most critical steps in the processing of black tea. The degree of withering affects the aroma quality of the finished tea. In this study, we used a pH indicator-based colorimetric sensor array in combination with hyperspectral imaging to intelligently evaluate the withering degree. After analyzing the difference between images taken before and after the reaction of pH indicators with withered leaves, six pH indicators were selected to build a sensor array. Then, the hyperspectral image of each pH indicator was obtained at wavelengths between 400 and 1000 nm. Nonlinear support vector machine (SVM) and least-squares (LS) SVM models were established to determine the degree of withering. Results revealed that the spectral information from single pH indicator failed to accurately evaluate the withering degree. The LS-SVM model achieved satisfactory discriminant results with the low-level data fusion of six pH indicators followed by principal component analysis for dimensionality reduction. The optimal model yielded accuracies of 93.75% and 90.00% for the calibration and prediction sets, respectively. The results indicated that colorimetric sensor array in combination with hyperspectral imaging can effectively determine the withering degree, thus providing a novel method for the intelligent processing of food and tea. [ABSTRACT FROM AUTHOR]

[Display omitted] • A novel spectral-based gas monitoring method was proposed. • Image and spectral feature information of CSA were extracted and compared. • An N-TPP-based CSA was firstly applied in black tea fermentation monitoring. The rapid and scientific method for monitoring the quality of black tea fermentation is of great significance to the quality control of black tea production. This study proposed a novel method for evaluating the fermentation quality of black tea by using hyperspectral imaging technology with self-assembled nanoporphyrin (N-TPP) dyes, which were used as aroma capture probes in the black tea fermentation process. Scanning electron microscopy and ultraviolet–visible spectroscopy were performed to characterize the N-TPP. Then, the results of the colorimetric sensor array (conventional camera color method) and the proposed hyperspectral methods were compared. Finally, the hyperspectral information of N-TPP with higher sensitivity was collected, and the qualitative models of evaluating black tea fermentation quality were established using support vector machine (SVM), extreme learning machine, and linear discriminant analysis. Among these models, the SVM model exhibited the highest discriminant accuracy. The accuracy of the SVM model based on the hyperspectral information of the self-assembled N-TPP array was 98.85 %, which was considerably higher than that (68.97 %) of the SVM model based on the color information of the porphyrin array. The results revealed that the proposed method can effectively improve the monitoring accuracy of black tea fermentation quality. [ABSTRACT FROM AUTHOR]

Withering of leaves is an important step in the processing of black tea and determines the taste and aroma of the tea. Currently, the withering degree of the leaves is mainly determined via sensory evaluation by the tea maker, and this is time-consuming and laborious. In this study, near-infrared spectroscopy, electronic eye, and colorimetric sensing array technologies were combined to evaluate the extent of withering. A low-cost micro-spectrometer, a self-built machine vision system, and a homemade colorimetric array were used to capture relevant information regarding the withered tea leaf samples in situ. Additionally, low- and middle-level data fusion strategies were modeled and compared using a support vector machine (SVM). The SVM model, which combined the information obtained using the three technologies, performed substantially better than a single technology. Low-level fusion achieved acceptable discriminant performance, with an accuracy of 90.00% for both the SVM and principal component analysis–SVM models for the prediction set. The middle-level fusion strategy achieved better performance than the low-level fusion strategy, with an optimal discriminant accuracy of 97.50% for SVM model. Hence, this study demonstrated that in situ and low-cost quality assessment and intelligent control of the withering process of black tea leaves are possible. [Display omitted] • E-nose, E-eye and NIRS were jointly used to monitor withering degree of black tea. • Low- and middle-level data fusion were critically used and compared. • Performance of data fusion in middle-level outperformed that of independent data. • It provides a low-cost, in situ method for quality monitoring of tea processing. [ABSTRACT FROM AUTHOR]

• Assessing black tea quality by Vis-NIR spectra. • Selecting spectral features by the Si-PLS, CARS, iVISSA, and VISSA. • Chemometric models for black tea quality developed using SVM-based kernel methods. • The CARS-linear kernel SVM model shows promising results. Current evaluation systems for tea quality assessment are difficult to use and unstable. A rapid and cheap assessment method is required to distinguish the quality levels of tea. In this study, a visible-near-infrared (Vis–NIR) spectrometer and support vector machine (SVM)-based kernels were used for the qualitative categorization of black tea. First, a Vis–NIR system was used to acquire the spectral data of seven levels of tea samples. The obtained spectra were preprocessed using the Savitzky–Golay smoothing combined with the first derivative and standard normal variate transformation. Then, four characteristic wavelength selection algorithms, namely synergy interval partial least square, competitive adaptive reweighted sampling (CARS), the variable iterative space shrinkage approach (VISSA), and the interval VISSA, were used to obtain preprocessed spectral features. Finally, the SVM was used with four kernel functions, namely the linear, Gaussian, quadratic, and cubic functions, to develop models based on the variables obtained from the selected features for tea quality classification. The results revealed that the CARS–linear kernel SVM model exhibited the best results, with a correct identification rate of 91.85 % in the validation process. Our findings demonstrate that Vis-NIR spectroscopy can be a rapid, inexpensive, efficient, and alternative method for predicting the quality of black tea. [ABSTRACT FROM AUTHOR]

• Estimation of Congou black tea quality by an artificial lipid membrane taste sensor. • Optimizing taste features using ant colony optimization. • Multivariate analyses of quality categories and taste characteristics are performed. • The ACO-LS-SVM model achieves the desired predictive performance. The taste attribute is an important indicator to estimate the quality and rank of black tea. It is crucial to prevent fraud and avoid economic losses. This study creatively proposed the assessment of Congou black tea quality based on an electronic tongue system combined with the ant colony optimization (ACO) algorithm and stoichiometry. Firstly, the electronic tongue could effectively present the taste quality of black tea, capturing characteristic potential signals from 700 samples of seven different qualities and converting the signals into nine relative characteristic taste values. Then, the taste indicators from different artificial lipid membrane sensors were optimized using the ACO method. Finally, the discriminant models based on the extreme learning machine, support vector machine, partial least-squares discriminant analysis, and least squares-support vector machine (LS-SVM) were developed using the optimized taste characteristics for the assessment of black tea quality. Results indicated that the LS-SVM model, which was created using the five taste features, could obtain better predictive outcomes based on the generalization performance of the model. In the prediction set, the correct discriminant rate was 99.14%. The overall results demonstrate that the electronic tongue sensor array has potential application prospects for the assessment of Congou black tea products in the actual production process. [ABSTRACT FROM AUTHOR]

• Smartphone-based micro NIRS was used to collect spectrum of green tea samples. • A multilayer algorithmic model was designed to explain the obtained spectral data. • Simplified models were established by using three wavelength selection algorithms. • A low-cost and in-situ method was proposed to detect adulteration in green tea. Green tea adulterated with sugar and glutinous rice flour has an increased sensitivity to water, which affects the safety of the tea. A total of 475 samples of pure tea, sugar-adulterated tea, and glutinous-rice-flour-adulterated tea were prepared and scanned using micro near infrared spectroscopy (NIRS). The collected NIRS data were qualitatively and quantitatively detected by a multi-layer algorithm model. Principal component analysis indicated that the three sample groups had an obvious separation trend. The discriminate rate of the optimal qualitative model, namely support vector machine, was 97.47% for the prediction set. A total of three wavelength selection methods were used to improve the performances of partial least squares regression and support vector machine regression (SVR) models. The nonlinear SVR models based on characteristic wavelengths selected by iteratively retaining informative variables algorithm provided satisfactory results for the identification of sugar and glutinous rice flour adulteration. The correlation coefficients for prediction (Rp) were >0.94, and the residual prediction deviation were >3. The results indicated that smartphone-based micro NIRS can be effectively used to qualitatively and quantitatively analyze adulterants in green tea. [ABSTRACT FROM AUTHOR]

• Evaluating tea quality using a lab-made computer vision and morphological features. • Identification models for tea quality are created using non-linear chemometrics. • The LS-SVM and SVM are implemented with three different kernels. • The polynomial kernel LS-SVM model yields satisfactory results with an accuracy of 100%. The feature of external shape in tea is a vital quality index that determines the rank quality of tea. The potential of a lab-made computer vision system (CVS) coupled with morphological features and chemometric tools is investigated for evaluating Congou black tea quality. First, Raw images of 700 tea samples from seven different quality grades are acquired using the CVS. The original images collected are processed by graying, binarization, and median de-noising. Then, six morphological parameters (viz. width, length, area, perimeter, length-width ratio, and rectangularity) from the samples are extracted by the shape segmentation of each tea leaf image, and the corresponding feature histogram is obtained. Finally, support vector machine (SVM) and least squares-support vector machine (LS-SVM) are utilized to build identification models based on the histogram distribution characteristic vectors. Three kernel methods (linear kernel, polynomial kernel, and radial basis function kernel) are compared for monitoring tea quality. The results show that the optimal LS-SVM model has a 12% higher correct discrimination rate (CDR) than the SVM model. The polynomial kernel LS-SVM model yields satisfactory classification results with the CDR of 100% based on selected six shape features in the calibration and prediction sets. This work demonstrates that it is feasible to discriminate Congou black tea quality using CVS technology along with morphological features and nonlinear chemometric methods. A new perspective on the sizes of morphological characteristics is proposed as an identifier of Congou black tea quality. [ABSTRACT FROM AUTHOR]

Tea storage period is difficult to be assessed by traditional sensory and chemical analysis methods. In this research, hyperspectral imaging (HSI) covering the spectral range of 400–1000 nm was combined with chemometric methods to predict the storage period of green tea samples. Tea samples were incubated under two storage temperatures of 4 °C (Sample set 1) and 25 °C (Sample set 2) for 360 days. The reflectance spectra were acquired every 90 days. Based on the preprocessed full spectra, partial least squares-discriminant analysis (PLS-DA)- and support vector machine (SVM)-based models had acceptable outputs for the two sample sets with an accuracy of over 90%. In addition, regression coefficients (RCs) of PLS-based models, second derivative (2-Der), and successive projections algorithm (SPA) were applied to select the optimal wavelengths. Satisfactory results were achieved by SVM-based models on the basis of optimal wavelengths. The SPA-SVM- and 2-Der-SVM-based models had the best performance to discriminate the storage period of the two sample sets with the prediction accuracies of 98% and 98%, respectively. The results demonstrated that HSI could be used to evaluate the storage period of green tea, providing an alternative for a real-time monitoring of tea quality. [ABSTRACT FROM AUTHOR]