Search

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]

Fermentation is key to the quality of black tea, and traditional sensory evaluation methods are too slow and subjective for reliable, large-scale evaluation during fermentation. To address this problem, this study formulated a sensing system based on cobalt ions-doped carbon quantum dots emitting bright blue fluorescence. In evaluation experiments, this system was found to work stably for 90 min and accurately determine fermentation quality in real time. In fluorescence spectra results, fluorescence intensity decreased sharply with the concentrations of catechins, theaflavins, and gallic acid and this relationship was highly linear at concentrations from 0.01 to 50 μg/mL; R2 was >97% and the limit of detection was <0.046 μg/mL. A least-squares support vector machine model was established, and it had a 100% accuracy rate in discriminating between degrees of fermentation. Therefore, this quantum-dot-based system serves as an accurate and efficient means of measuring the fermentation quality of black tea. [Display omitted] • A testing technique for in-process black tea products with dynamic quality change. • Co-CQDs respond stably to key substances in black tea fermentation in real time. • The developed model's accuracy in determining the degree of fermentation is 100%. • Stable CQDs provide reliable performance during black tea fermentation. • Standard curves for catechins, theaflavins, and gallic acid were established. [ABSTRACT FROM AUTHOR]

Piling fermentation (PF) is the key to the formation of Pu-erh tea quality; however, the traditional PF process limits the digital and intelligent production of Pu-erh tea. To establish qualitative and quantitative prediction models for the PF degree of Pu-erh tea, hyperspectral imaging technology and chemometric analysis were utilized. A qualitative model that uses least-squares support-vector-machine effectively distinguished the PF degree with an accuracy of 98.63%. Moreover, the chemical contents of quality-affecting components, namely total catechin, free amino acids, and chlorophyll a , were accurately quantified using raw spectral data with residual prediction deviations of 11.26, 4.34, and 3.89, respectively. The spatial distribution of these components during PF was mapped through chemical imaging, and the PF was deemed complete when the model predicted that the total catechin, amino acid and chlorophyll a content were less than 0.48, 11.21 and 1.29 mg/g, respectively. These findings provide a theoretical foundation for digital processing. [Display omitted] • Hyperspectral image technology (HIS) is used for quality monitoring of Pu-erh tea. • The prediction of the degree of Pu-erh tea piling fermentation (PF) was achieved. • Quality components was accurately quantified by raw spectral data (RPD>3.0). • Spatial distribution of quality composition during PF was mapped by HSI. [ABSTRACT FROM AUTHOR]

Moist-heat action and microbial action are essential to the formation of Pu-erh tea's quality. To explore the impact of piling fermentation (PF) environment on Pu-erh tea quality, samples subjected to spontaneous PF (SPPF) and sterile PF (STPF) from the same batch of raw material were processed, and their sensory quality and metabolic profile dynamics were determined. Sensory evaluation indicated that infusions of the SPPF samples were mainly brownish-red, stale-mellow taste, and stale aroma, whereas infusions of the STPF samples were mainly orange-red, sweet-mellow taste, and woody aroma. Metabolomics analysis identified 465 key metabolites, including 33 microbial markers and 39 moist-heat activity markers. Enzyme and pathway analyses revealed that the production of microbial enzymes accelerates the degradation of flavonoids, flavonols, and lipids and also indicated an exclusive influence of microorganisms on the lipid metabolite pathway. This study elucidated the mechanism underlying the formation of Pu-erh tea's stale flavour. [Display omitted] • Investigating moisture-heat and microbial impact on Pu-erh tea quality. • Moist-heat action enhances woody aroma, sweet and mellow Pu-erh tea flavor. • Microbial create a stale aroma, and stale and mellow flavor profile in Pu-erh tea. • 33 microbial markers and 39 moist-heat markers were identified (from 108 markers). • Novel discovery: Microbes heavily impact lipid metabolic pathways. [ABSTRACT FROM AUTHOR]

[Display omitted] • IDA was composed of phenylboronic acids, pyrocatechol violet, and alizarin red S. • TP, TC, and EGCG were key quality indicators of black tea fermentation. • SVM model achieved accurate qualitative evaluation of fermentation degrees. • SCARS-SVR model achieved accurate prediction of TP, TC, and EGCG. • In-situ quality monitoring of black tea fermentation was realized. Herein, a new indicator-displacement array (IDA) sensor was developed for the quality evaluation of black tea fermentation. On the principle of the reversible covalent binding of phenylboronic acid and catechol, phenylboronic acids were selected as acceptors for targeted binding to polyphenols. Pyrocatechol violet and alizarin red S were used as indicators of the reaction. The IDA sensors have sensitive differential responses to fermented tea samples, achieving an assessment of the fermentation degree with accuracies of 80.39–88.00% by support vector machine (SVM). In addition, the key polyphenol components of the fermentation process were accurately predicted by the IDA and SVM regression with ratio of prediction to deviation values of 1.55–1.72, 2.03–2.21, and 2.03–2.08 for total polyphenols, total catechins, and epigallocatechin-3-O-gallate, respectively. In conclusion, the developed IDA sensor is capable of the in-situ quality monitoring of black tea fermentation, with the advantages being cost-effectiveness, sensitivity, and rapidity. [ABSTRACT FROM AUTHOR]

• Data of fermented tea samples was collected at-line by an industrial camera. • Catechins, theaflavins and chlorophylls were chosen as key quality indicators. • Correlations between color variables and quality indicators were established. • Spatial and temporal distribution of indicators was mapped and visualized. Fermentation is a key black tea processing step and makes an important contribution to quality formation. Current approaches to fermentation monitoring are costly or laboratory-based. Here, we first evaluated the potential of at-line computer vision for detecting fermentation quality in a tea factory. A self-built industrial camera was used to collect tea samples at various fermentation durations. The correlations of color variables that were extracted from the images with key quality indicators in the tea samples were verified. Subsequently, partial least-squares regression models based on the color variables showed high prediction accuracy with residual prediction deviation values of 4.13, 3.53, and 3.39 for catechins, theaflavins and chlorophylls, respectively. Finally, the spatial and temporal distributions of indicators during fermentation were mapped to visualize the fermentation quality. This study realized low-cost, at-line and real-time detection for black tea fermentation, which provides technical support for the industrial and intelligent production of black tea. [ABSTRACT FROM AUTHOR]

During the pile fermentation (PF) process, changes to the polyphenol composition directly affect the quality of Pu-erh tea. In this study, we have applied laboratory-made computer vision system (CVS) and miniature near-infrared spectroscopy (NIRS) to the at-line rapid detection of the PF degree of Pu-erh tea at an industrial scale. High-performance liquid chromatography was used for determining the content of catechins (EGCG, EGC ...) and gallic acid (GA). Based on the least-square support vector machine (LSSVM) qualitative model analysis, the texture features and color information extracted by CVS better predicted the degree of PF with a prediction set of 99.30% and calibration set of 100.00% compared to the spectral information extracted by NIRS. The best quantitative models for total catechins (TC), GA/TC, and red and green values of the tea infusion (R-TI, G-TI) were obtained with residual prediction deviations (RPD) of 4.76, 2.36, 5.18, and 4.71, respectively, based on CVS fusion data. And the optimal PF degree of Pu-erh tea was defined when the predicted values of TC, GA/TC, R-TI, and G-TI were in the ranges of 0.46 ± 0.08 mg/g, 19.04 ± 6.67, 74.81 ± 6.37, and 29.81 ± 2.46, respectively. In-situ quality monitoring of Pu-erh tea PF was realized. • CVS and NIRS were first applied to predict the quality changes of Pu-erh tea. • The CVS recognition rate was higher than NIRS up to 100% by LSSVM model. • TC, GA and tea infusion color were identified as quality prediction indicators. • The pile fermentation degree was defined based on quality prediction indicators. • "Color card" standards for different degree of pile fermentation were created. [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]

• NIR-HSI was used for quality monitoring of fermentation process of black tea. • Qualitative and quantitative models were developed to assess the quality. • Spatial distribution of catechins during fermentation was mapped by HSI. • Noncontact evaluation for intelligent processing of black tea was achieved. Fermentation is the most critical step in black tea processing and contributes to the taste and appearance of black tea. Conventionally, the degree of fermentation is evaluated through sensory reviews by experts. However, this method has low accuracy and is subject to reviewers' experience. In this study, the fermentation quality of black tea was qualitatively and quantitatively evaluated through near-infrared hyperspectral imaging (HSI). The spectral information of samples of four fermentation degrees was collected and preprocessed using standard normal variate. The developed qualitative model could discriminate fermentation degrees, with a correct classification rate of 83.33 % for the prediction set. The quantitative prediction model achieved excellent prediction accuracy for the catechin content, with a residual prediction deviation of 2.18. Finally, the spatial distribution of catechins during fermentation was mapped through chemical imaging. Our study confirmed the feasibility of HSI for monitoring the fermentation quality of black 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]

• Low-cost, portable instruments were used to evaluate the tea processing quality. • A satisfactory classification rate (89.19%) was achieved using data fusion. • Quantitative model showed high prediction performance for the theaflavin content. • Our results provide templates for at-line monitoring of tea processing quality. Intelligent identification of black tea fermentation quality is becoming a bottleneck to industrial automation. This study presents at-line rapid detection of black tea fermentation quality at industrial scale based on low-cost micro-near-infrared spectroscopy (NIRS) and laboratory-made computer vision system (CVS). High-performance liquid chromatography and a spectrophotometer were used for determining the content of catechins and theaflavins, and the color of tea samples, respectively. Hierarchical cluster analysis combined with sensory evaluation was used to group samples through different fermentation degrees. A principal component analysis–support vector machine (SVM) model was developed to discriminate the black tea fermentation degree using color, spectral, and data fusion information; high accuracy (calibration = 95.89%, prediction = 89.19%) was achieved using mid-level data fusion. In addition, SVM model for theaflavins content prediction was established. The results indicated that the micro-NIRS combined with CVS proved a portable and low-cost tool for evaluating the black tea fermentation quality. [ABSTRACT FROM AUTHOR]

Fermentation is the most crucial step in black tea processing. In this study, we used a combination of Fourier transform near-infrared spectroscopy (FT-NIR) and computer vision system (CVS) for comprehensively evaluating the black tea fermentation degree. 110 samples of black tea at different fermentation degrees were collected in this research. The tea polyphenols (TP) content was measured using a UV–Vis spectrometer, and TP degradation during black tea fermentation was measured for classifying the degree of fermentation. Two mid-level strategies were used to analyze the fusion signals of FT-NIR and CVS. K-nearest neighbors, linear discriminant analysis, and a support vector machine (SVM) were applied for classification modeling. The advantages of FT-NIR and CVS were integrated based on mid-level fusion, and the results obtained were better than those obtained using independent methods for evaluating black tea fermentation. The mid-level fusion strategy that combined FT-NIR and CVS for principal component analysis feature extraction was the most effective in the SVM model. Classification accuracies of calibration and prediction sets were each 100%. Therefore, in this study, it was demonstrated that a combination of FT-NIR and CVS at mid-level fusion strategy can be used as a method to rapidly evaluate the black tea fermentation degree. • Tea polyphenols degradation data utilized in fermentation degree evaluation. • The fermentation degrees of black tea were jointly evaluated by FT-NIR and CVS. • Two different feature extraction methods were compared at mid-level fusion. • The efficiency of independent decision and fusion strategies were compared. • Obtained 100% accuracy by combining PCA feature extraction of FT-NIR and CVS. [ABSTRACT FROM AUTHOR]