Small target tea bud detection based on improved YOLOv5 in complex background.

Tea bud detection is the first step in the precise picking of famous teas. Accurate and fast tea bud detection is crucial for achieving intelligent tea bud picking. However, existing detection methods still exhibit limitations in both detection accuracy and speed due to the intricate background of tea buds and their small size. This study uses YOLOv5 as the initial network and utilizes attention mechanism to obtain more detailed information about tea buds, reducing false detections and missed detections caused by different sizes of tea buds; The addition of Spatial Pyramid Pooling Fast (SPPF) in front of the head to better utilize the attention module's ability to fuse information; Introducing the lightweight convolutional method Group Shuffle Convolution (GSConv) to ensure model efficiency without compromising accuracy; The Mean-Positional-Distance Intersection over Union (MPDIoU) can effectively accelerate model convergence and reduce the training time of the model. The experimental results demonstrate that our proposed method achieves precision (P), recall rate (R) and mean average precision (mAP) of 93.38%, 89.68%, and 95.73%, respectively. Compared with the baseline network, our proposed model's P, R, and mAP have been improved by 3.26%, 11.43%, and 7.68%, respectively. Meanwhile, comparative analyses with other deep learning methods using the same dataset underscore the efficacy of our approach in terms of P, R, mAP, and model size. This method can accurately detect the tea bud area and provide theoretical research and technical support for subsequent tea picking.

Long-range infrared absorption spectroscopy and fast mass spectrometry for rapid online measurements of volatile organic compounds from black tea fermentation.

Fermentation is the key process to determine the quality of black tea. Traditional physical and chemical analyses are time consuming, it cannot meet the needs of online monitoring. The existing rapid testing techniques cannot determine the specific volatile organic compounds (VOCs) produced at different stages of fermentation, resulting in poor model transferability; therefore, the current degree of black tea fermentation mainly relies on the sensory judgment of tea makers. This study used proton transfer reaction mass spectrometry (PTR-MS) and fourier transform infrared spectroscopy (FTIR) combined with different injection methods to collect VOCs of the samples, the rule of change of specific VOCs was clarified, and the extreme learning machine (ELM) model was established after principal component analysis (PCA), the prediction accuracy reached 95% and 100%, respectively. Finally, different application scenarios of the two technologies in the actual production of black tea are discussed based on their respective advantages.

Quality Detection and Grading of Rose Tea Based on a Lightweight Model.

Rose tea is a type of flower tea in China's reprocessed tea category, which is divided into seven grades, including super flower, primary flower, flower bud, flower heart, yellow flower, scattered flower, and waste flower. Grading rose tea into distinct quality levels is a practice that is essential to boosting their competitive advantage. Manual grading is inefficient. We provide a lightweight model to advance rose tea grading automation. Firstly, four kinds of attention mechanisms were introduced into the backbone and compared. According to the experimental results, the Convolutional Block Attention Module (CBAM) was chosen in the end due to its ultimate capacity to enhance the overall detection performance of the model. Second, the lightweight module C2fGhost was utilized to change the original C2f module in the neck to lighten the network while maintaining detection performance. Finally, we used the SIoU loss in place of the CIoU loss to improve the boundary regression performance of the model. The results showed that the mAP, precision (P), recall (R), FPS, GFLOPs, and Params values of the proposed model were 86.16%, 89.77%, 83.01%, 166.58, 7.978, and 2.746 M, respectively. Compared with the original model, the mAP, P, and R values increased by 0.67%, 0.73%, and 0.64%, the GFLOPs and Params decreased by 0.88 and 0.411 M, respectively, and the speed was comparable. The model proposed in this study also performed better than other advanced detection models. It provides theoretical research and technical support for the intelligent grading of roses.

Predictive models for sensory score and physicochemical composition of Yuezhou Longjing tea using near-infrared spectroscopy and data fusion.

In this study, NIR quantitative prediction model was established for sensory score and physicochemical components of different varieties and quality grades of Yuezhou Longjing tea. Firstly, L, a, b color factors and diffuse reflection spectral data are collected for each sample. Subsequently, the original spectrum is preprocessed. Three techniques for selecting variables, CARS, BOSS, and SPA, were utilized to extract optimal feature bands. Finally, the spectral data extracted from feature bands were fused with L, a and b color factors to build SVR and PLSR prediction models. enabling the rapid non-destructive discrimination of different varieties and grades of Yuezhou Longjing tea. The outcomes demonstrated that BOSS was the best variable selection technique for sensory score and the distinctive caffeine wavelengths, CARS, however, was the best variable selection technique for catechins distinctive wavelengths. Additionally, the middle-level data fusion-based non-linear prediction models greatly outperformed the linear prediction models. For the prediction models of sensory score, catechins, and caffeine, the relative percent deviation (RPD) values were 2.8, 1.6, and 2.6, respectively, suggesting the good predictive ability of the models. In conclusion, evaluating the quality of the five Yuezhou Longjing tea varieties using near-infrared spectroscopy and data fusion have proved as feasible.

Research on the Detection Method of Organic Matter in Tea Garden Soil Based on Image Information and Hyperspectral Data Fusion.

Soil organic matter is an important component that reflects soil fertility and promotes plant growth. The soil of typical Chinese tea plantations was used as the research object in this work, and by combining soil hyperspectral data and image texture characteristics, a quantitative prediction model of soil organic matter based on machine vision and hyperspectral imaging technology was built. Three methods, standard normalized variate (SNV), multisource scattering correction (MSC), and smoothing, were first used to preprocess the spectra. After that, random frog (RF), variable combination population analysis (VCPA), and variable combination population analysis and iterative retained information variable (VCPA-IRIV) algorithms were used to extract the characteristic bands. Finally, the quantitative prediction model of nonlinear support vector regression (SVR) and linear partial least squares regression (PLSR) for soil organic matter was established by combining nine color features and five texture features of hyperspectral images. The outcomes demonstrate that, in comparison to single spectral data, fusion data may greatly increase the performance of the prediction model, with MSC + VCPA-IRIV + SVR (R2C = 0.995, R2P = 0.986, RPD = 8.155) being the optimal approach combination. This work offers excellent justification for more investigation into nondestructive methods for determining the amount of organic matter in soil.

NIR Spectral Inversion of Soil Physicochemical Properties in Tea Plantations under Different Particle Size States.

Soil fertility is vital for the growth of tea plants. The physicochemical properties of soil play a key role in the evaluation of soil fertility. Thus, realizing the rapid and accurate detection of soil physicochemical properties is of great significance for promoting the development of precision agriculture in tea plantations. In recent years, spectral data have become an important tool for the non-destructive testing of soil physicochemical properties. In this study, a support vector regression (SVR) model was constructed to model the hydrolyzed nitrogen, available potassium, and effective phosphorus in tea plantation soils of different grain sizes. Then, the successful projections algorithm (SPA) and least-angle regression (LAR) and bootstrapping soft shrinkage (BOSS) variable importance screening methods were used to optimize the variables in the soil physicochemical properties. The findings demonstrated that soil particle sizes of 0.25-0.5 mm produced the best predictions for all three physicochemical properties. After further using the dimensionality reduction approach, the LAR algorithm (R2C = 0.979, R2P = 0.976, RPD = 6.613) performed optimally in the prediction model for hydrolytic nitrogen at a soil particle size of 0.25~0.5. The models using data dimensionality reduction and those that used the BOSS method to estimate available potassium (R2C = 0.977, R2P = 0.981, RPD = 7.222) and effective phosphorus (R2C = 0.969, R2P = 0.964, RPD = 5.163) had the best accuracy. In order to offer a reference for the accurate detection of soil physicochemical properties in tea plantations, this study investigated the modeling effect of each physicochemical property under various soil particle sizes and integrated the regression model with various downscaling strategies.

A tea bud segmentation, detection and picking point localization based on the MDY7-3PTB model.

Introduction: The identification and localization of tea picking points is a prerequisite for achieving automatic picking of famous tea. However, due to the similarity in color between tea buds and young leaves and old leaves, it is difficult for the human eye to accurately identify them. Methods: To address the problem of segmentation, detection, and localization of tea picking points in the complex environment of mechanical picking of famous tea, this paper proposes a new model called the MDY7-3PTB model, which combines the high-precision segmentation capability of DeepLabv3+ and the rapid detection capability of YOLOv7. This model achieves the process of segmentation first, followed by detection and finally localization of tea buds, resulting in accurate identification of the tea bud picking point. This model replaced the DeepLabv3+ feature extraction network with the more lightweight MobileNetV2 network to improve the model computation speed. In addition, multiple attention mechanisms (CBAM) were fused into the feature extraction and ASPP modules to further optimize model performance. Moreover, to address the problem of class imbalance in the dataset, the Focal Loss function was used to correct data imbalance and improve segmentation, detection, and positioning accuracy. Results and discussion: The MDY7-3PTB model achieved a mean intersection over union (mIoU) of 86.61%, a mean pixel accuracy (mPA) of 93.01%, and a mean recall (mRecall) of 91.78% on the tea bud segmentation dataset, which performed better than usual segmentation models such as PSPNet, Unet, and DeeplabV3+. In terms of tea bud picking point recognition and positioning, the model achieved a mean average precision (mAP) of 93.52%, a weighted average of precision and recall (F1 score) of 93.17%, a precision of 97.27%, and a recall of 89.41%. This model showed significant improvements in all aspects compared to existing mainstream YOLO series detection models, with strong versatility and robustness. This method eliminates the influence of the background and directly detects the tea bud picking points with almost no missed detections, providing accurate two-dimensional coordinates for the tea bud picking points, with a positioning precision of 96.41%. This provides a strong theoretical basis for future tea bud picking.

Monitoring the major taste components during black tea fermentation using multielement fusion information in decision level.

Hitherto, the intelligent detection of black tea fermentation quality is still a thought-provoking problem because of one-side sample information and poor model performance. This study proposed a novel method for the prediction of major chemical components including total catechins, soluble sugar and caffeine using hyperspectral imaging technology and electrical properties. The multielement fusion information were used to establish quantitative prediction models. The performance of model using multielement fusion information was better than that of model using single information. Subsequently, the stacking combination model using fusion data combined with feature selection algorithms for evaluating the fermentation quality of black tea. Our proposed strategy achieved better performance than classical linear and nonlinear algorithms, with the correlation coefficient of the prediction set (Rp) for total catechins, soluble sugar and caffeine being 0.9978, 0.9973 and 0.9560, respectively. The results demonstrated that our proposed strategy could effectively evaluate the fermentation quality of black tea.

Detection of volatile organic compounds in adulterated tea using Fourier transform infrared spectroscopy and Proton-transfer-reaction mass spectrometry.

Aroma is a key factor used to evaluate tea quality. Illegal traders usually add essence to expired or substandard tea to improve its aroma so as to gain more profit. Traditional physical and chemical testing methods are time-consuming and costly. Furthermore, rapid detection techniques, such as near-infrared spectroscopy and machine vision, can only be used to detect adulterated powdered solid essences in tea. In this study, proton-transfer reaction mass spectrometry (PTR-MS) and Fourier-transform infrared spectroscopy (FTIR) were employed to detect volatile organic compounds (VOCs) in samples, and rapid detection of different tea adulterated liquid essence was achieved. The prediction accuracies of PTR-MS and FTIR reached over 0.941 and 0.957, respectively, and the minimum detection limits were lower than the actual used values in both. In this study, the different application scenarios of the two technologies are discussed based on their performance characteristics.

A Tea Buds Counting Method Based on YOLOv5 and Kalman Filter Tracking Algorithm.

The tea yield estimation provides information support for the harvest time and amount and serves as a decision-making basis for farmer management and picking. However, the manual counting of tea buds is troublesome and inefficient. To improve the efficiency of tea yield estimation, this study presents a deep-learning-based approach for efficiently estimating tea yield by counting tea buds in the field using an enhanced YOLOv5 model with the Squeeze and Excitation Network. This method combines the Hungarian matching and Kalman filtering algorithms to achieve accurate and reliable tea bud counting. The effectiveness of the proposed model was demonstrated by its mean average precision of 91.88% on the test dataset, indicating that it is highly accurate at detecting tea buds. The model application to the tea bud counting trials reveals that the counting results from test videos are highly correlated with the manual counting results (R 2 = 0.98), indicating that the counting method has high accuracy and effectiveness. In conclusion, the proposed method can realize tea bud detection and counting in natural light and provides data and technical support for rapid tea bud acquisition.

Moisture content monitoring in withering leaves during black tea processing based on electronic eye and near infrared spectroscopy.

Monitoring the moisture content of withering leaves in black tea manufacturing remains a difficult task because the external and internal information of withering leaves cannot be simultaneously obtained. In this study, the spectral data and the color/texture information of withering leaves were obtained using near infrared spectroscopy (NIRS) and electronic eye (E-eye), respectively, and then fused to predict the moisture content. Subsequently, the low- and middle-level fusion strategy combined with support vector regression (SVR) was applied to detect the moisture level of withering leaves. In the middle-level fusion strategy, the principal component analysis (PCA) and random frog (RF) were employed to compress the variables and select effective information, respectively. The middle-level-RF (cutoff line = 0.8) displayed the best performance because this model used fewer variables and still achieved a satisfactory result, with 0.9883 and 5.5596 for the correlation coefficient of the prediction set (Rp) and relative percent deviation (RPD), respectively. Hence, our study demonstrated that the proposed data fusion strategy could accurately predict the moisture content during the withering process.

Research on moisture content detection method during green tea processing based on machine vision and near-infrared spectroscopy technology.

Moisture content is an important indicator that affects green tea processing. In this study, taking Chuyeqi tea as the research object, a quantitative prediction model of the changes in moisture content during the processing of green tea was constructed based on machine vision and near-infrared spectroscopy technology. First, collect the spectrum and image information in the process of spreading, fixation, first-drying, carding, and second-drying. The competitive adaptive reweighted sampling (CARS) method is then used to extract the characteristic wavelengths in the spectrum, and the image's 9 color features and 6 texture features are combined to establish linear PLSR and nonlinear SVR prediction models by fusing the data information from the two sensors. The results show that, when compared to single data, the PLSR and SVR models based on low-level data fusion do not effectively improve the model's prediction accuracy, but rather produce poor prediction results. In contrast, the PLSR and SVR models established by middle-level data fusion have improved the prediction accuracy of moisture content in green tea processing. Among them, the established SVR model has the best effect. The correlation coefficient of the calibration set (Rc) and the root mean square error of calibration (RMSEC) are 0.9804 and 0.0425, respectively, the correlation coefficient of the prediction set (Rp) and the root mean square error of prediction (RMSEP) are 0.9777 and 0.0490 respectively, and the relative percent deviation is 4.5002. The results show that the middle data fusion based on machine vision and near-infrared spectroscopy technology can effectively predict the moisture content in the processing of green tea, which has important guiding significance for overcoming the low prediction accuracy of a single sensor.

Robustness and accuracy evaluation of moisture prediction model for black tea withering process using hyperspectral imaging.

The rapid and non-destructive detection of moisture in withering leaves is an unsolved problem because the leaves are stacked together and have random orientation. To address this issue, this study aimed to establish more robust and accurate models. The performance of front side, back side and multi-region models were compared, and the front side model showed the worst transferability. Therefore, five effective wavelength (EW) selection algorithms were combined with a successive projection algorithm (SPA) to select EWs. It was found that the shuffled frog leaping algorithm (SFLA) combined with SPA was the best method for the front side model for moisture analyses. Based on the selected EWs, the extreme learning machine (ELM) became the model with the best self-verification result. Subsequently, moisture distribution maps of withering leaves were successfully generated. Considering the processing demand of withering leaves, local region models developed based on partial least squares and the SFLA-SPA method were applied to predict the moisture of withering leaves in the local and stacked region. The results showed that the RPD, Rcv and Rp values were above 1.6, 0.870 and 0.897, respectively. These results provide a useful reference for the non-destructive detection of moisture in withering leaves.

Black tea aroma formation during the fermentation period.

The present study aimed to systematically investigate black tea aroma formation during the fermentation period. In total, 158 volatile compounds were identified. Of these, most amino acid-derived volatiles (AADVs) and carotenoid-derived volatiles (CDVs) showed significant increases, while fatty acid-derived volatiles (FADVs) and volatile terpenoids (VTs) displayed diverse changes during the fermentation period. During this time, fatty acids, amino acids, carotenoids, and glycosidically bound volatiles (GBVs, especially primeverosides) were found to degrade to form aroma components. Further, equivalent quantification of aroma showed that the intensity of green scent was notably decreased, while the intensities of sweet and floral/fruity scents were greatly increased and gradually dominated the aroma of tea leaves. AADVs and CDVs were shown to make greater contributions to the formation of sweet and floral/fruity scents than VTs. Our study provides a detailed characterization of the formation of sweet and floral/fruity aromas in black tea during the fermentation period.

Nondestructive Testing and Visualization of Catechin Content in Black Tea Fermentation Using Hyperspectral Imaging.

Catechin is a major reactive substance involved in black tea fermentation. It has a determinant effect on the final quality and taste of made teas. In this study, we applied hyperspectral technology with the chemometrics method and used different pretreatment and variable filtering algorithms to reduce noise interference. After reduction of the spectral data dimensions by principal component analysis (PCA), an optimal prediction model for catechin content was constructed, followed by visual analysis of catechin content when fermenting leaves for different periods of time. The results showed that zero mean normalization (Z-score), multiplicative scatter correction (MSC), and standard normal variate (SNV) can effectively improve model accuracy; while the shuffled frog leaping algorithm (SFLA), the variable combination population analysis genetic algorithm (VCPA-GA), and variable combination population analysis iteratively retaining informative variables (VCPA-IRIV) can significantly reduce spectral data and enhance the calculation speed of the model. We found that nonlinear models performed better than linear ones. The prediction accuracy for the total amount of catechins and for epicatechin gallate (ECG) of the extreme learning machine (ELM), based on optimal variables, reached 0.989 and 0.994, respectively, and the prediction accuracy for EGC, C, EC, and EGCG of the content support vector regression (SVR) models reached 0.972, 0.993, 0.990, and 0.994, respectively. The optimal model offers accurate prediction, and visual analysis can determine the distribution of the catechin content when fermenting leaves for different fermentation periods. The findings provide significant reference material for intelligent digital assessment of black tea during processing.

Rapid characterization of the volatile profiles in Pu-erh tea by gas phase electronic nose and microchamber/thermal extractor combined with TD-GC-MS.

Aroma plays an important role in the quality of Pu-erh tea. However, the quality evaluation of Pu-erh tea aroma is heavily relied on the experience of sensory evaluation, and the theoretical research is relatively scarce. In the present work, the volatile compounds in Pu-erh tea were characterized by using gas phase electronic nose (e-nose) and microchamber/thermal extractor (µ-CTE) combined with thermal desorption coupled to gas chromatography-mass spectrometry (TD-GC-MS). A satisfactory discrimination model (R2 Y = 0.95, Q2  = 0.807) was obtained by using orthogonal partial least squares discriminant analysis (OPLS-DA) based on the odor fingerprint of different brands of Pu-erh tea. In addition, based on the double criterion of multivariate analysis with VIP >1.0 and univariate analysis with p ≤ 0.001, 39 volatile components were identified to contribute greatly to the discrimination of five brands of Pu-erh tea. The results suggested that gas phase e-nose and µ-CTE combined with TD-GC/MS were simple, rapid techniques to characterize the volatile compounds in Pu-erh tea and were allowed to effectively distinguish different brands of Pu-erh tea, which would provide an important reference on the quality assessment of Pu-erh tea. PRACTICAL APPLICATION: This work demonstrates that the volatile compounds in Pu-erh tea are simply and rapidly characterized by using µ-CTE/TD-GC/MS and gas phase e-nose, allowing to effectively distinguish different brands of Pu-erh tea, which can provide an important reference for the quality assessment and authentication of Pu-erh tea.

Investigation on green tea lipids and their metabolic variations during manufacturing by nontargeted lipidomics.

Lipids are hydrophobic metabolites implicated in tea flavor quality. Understanding their transformations during tea manufacture is of particular interest. To date, the detailed lipid composition and variations during green tea manufacture are largely unknown. Herein, we performed a comprehensive characterization of the dynamic changes of lipids during green tea manufacture, by applying nontargeted lipidomics using ultrahigh performance liquid chromatography-quadrupole-Orbitrap mass spectrometry (UHPLC-Q-Exactive/MS) combined with chemometric tools. Totally, 283 lipid species were detected, covering 20 subclasses. Significant lipidomic variations were observed during green tea manufacture, especially in the fixation stage, mainly associated with chlorophyll decomposition, phosphatidic acids (PAs) reduction and glycolipids degradation, which potentially contribute to tea color and aroma quality. Specifically, the most prominent decrease of PAs content during green tea manufacture was identified for the first time. This study provides insights into the lipid metabolic fates upon green tea manufacture, and their roles in green tea sensory quality.

Aroma dynamic characteristics during the process of variable-temperature final firing of Congou black tea by electronic nose and comprehensive two-dimensional gas chromatography coupled to time-of-flight mass spectrometry.

The drying technology is crucial to the quality of Congou black tea. In this study, the aroma dynamic characteristics during the variable-temperature final firing of Congou black tea was investigated by electronic nose (e-nose) and comprehensive two-dimensional gas chromatography coupled to time-of-flight mass spectrometry (GC × GC-TOFMS). Varying drying temperatures and time obtained distinctly different types of aroma characteristics such as faint scent, floral aroma, and sweet fragrance. GC × GC-TOFMS identified a total of 243 volatile compounds. Clear discrimination among different variable-temperature final firing samples was achieved by using partial least squares discriminant analysis (R2Y = 0.95, Q2 = 0.727). Based on a dual criterion of variable importance in the projection value (VIP > 1.0) and one-way ANOVA (p < 0.05), ninety-one specific volatile biomarkers were identified, including 2,6-dimethyl-2,6-octadiene and 2,5-diethylpyrazine with VIP > 1.5. In addition, for the overall odor perception, e-nose was able to distinguish the subtle difference during the variable-temperature final firing process.

Quantitation of pyrazines in roasted green tea by infrared-assisted extraction coupled to headspace solid-phase microextraction in combination with GC-QqQ-MS/MS.

Pyrazines play an important role in the characteristic flavor of roasted green tea due to powerful strong odours and low sensory thresholds. It is important to analyze these compounds reliably and rapidly in roasted green tea. In this study, infrared-assisted extraction coupled to headspace solid-phase microextraction (IRAE-HS-SPME) and gas chromatography-triple quadrupole-tandem mass spectrometry (GC-QqQ-MS/MS) were developed and validated to determine the pyrazines in roasted green tea. Good linear correlation coefficients (0.9955-0.9996) were obtained over the concentration ranges of 10-5000 ng/mL. The limits of detection (LODs) and limits of quantification (LOQs) for the pyrazines were in the range of 1.46-3.27 ng/mL and 4.89-10.90 ng/mL, respectively. The average recoveries varied from 84% to 119%. The method was used to analyze the pyrazines in roasted green tea manufactured by different final firing methods, the results revealed that microwave final firing method had maximum contents of pyrazines, and significantly improved the aroma quality. In addition, there were great disparities of pyrazines in flatten-shaped green tea and strip-shaped green tea according to the appearance. The result is expected to better understand the role of pyrazines related to aroma quality of roasted green tea and improve processing technology.

Rapid Sensing of Key Quality Components in Black Tea Fermentation Using Electrical Characteristics Coupled to Variables Selection Algorithms.

Based on the electrical characteristic detection technology, the quantitative prediction models of sensory score and physical and chemical quality Index (theaflavins, thearubigins, and theabrownins) were established by using the fermented products of Congou black tea as the research object. The variation law of electrical parameters during the process of fermentation and the effects of different standardized pretreatment methods and variable optimization methods on the models were discussed. The results showed that the electrical parameters vary regularly with the test frequency and fermentation time, and the substances that hinder the charge transfer increase gradually during the fermentation process. The Zero-mean normalization (Zscore) preprocessing method had the best noise reduction effect, and the prediction set correlation coefficient (Rp) value of the original data could be increased from 0.172 to 0.842. The mixed variable optimization method (MCUVE-CARS) of Monte Carlo uninformed variable elimination (MC UVE) and competitive adaptive reweighted sampling (CARS) was proved that the characteristic electrical parameters were the loss factor (D) and reactance (X) of the low range. Based on the characteristic variables screened by MCUVE-CARS, the quantitative prediction models for each fermentation quality indicator were established. The Rp values of the sensory score, theaflavin, thearubigin and theabrownins of the predicted models were 0.924, 0.811, 0.85 and 0.938 respectively. The relative percent deviation (RPD) values of the sensory score, theaflavins, thearubigins and theabrownins of the predicted models were 2.593, 1.517, 1,851 and 2.920 respectively, and it showed that these models have good performance and could realize quantitative characterization of key fermentation quality indexes.