Longjing tea appearance features are crucial for assessing tea quality. In order to intelligently evaluate the appearance characteristics of Longjing tea and quickly recognize the grades, a method combining image features and intelligent algorithms for appearance quality assessment was proposed. Images of the six grades of the standard Dafo Longjing tea were collected and their shape, color, and texture features were quantified and extracted to construct a database of tea appearance grade characteristics. The appearance features were fused and input into five machine learning models, namely, Decision Tree, Random Forest, K-Nearest Neighbor, Gaussian Bayesian, and Support Vector Machine, for grade recognition training. Three convolutional neural networks, VGG16, ResNet18 and DenseNet121 were compared to build a deep learning model for Longjing tea appearance evaluation. Then the model was optimized by optimizers and learning rate decay. The results show that the fusion of shape and texture data combined with Support Vector Machine was the optimal model for grade recognition, with an accuracy of 91.14% and an F1 score of 91.20%. The ResNet18 network structure was chosen to establish the optimal model for appearance evaluation. After optimization by Adadelta optimizer and CosineAnnealingLR learning rate decay, the recognition accuracies of Longjing tea’s flatness, straightness, tenderness, and color all improved, reaching 99.21%, 99.51%, 99.56%, and 99.68%, respectively. This study provided a theoretical foundation for the digital evaluation of the appearance quality of tea.
[1] Zhu J C, Zhu Y, Wang K, et al.Characterization of key aroma compounds and enantiomer distribution in Longjing tea[J]. Food Chemistry, 2021, 361: 130096. doi: 10.1016/j.foodchem.2021.130096.
[2] Guo Y H, Yang X T, Wang H L, et al.Study on the establishment of quality discrimination model of Longjing 43 green tea (Camellia sinensis (L.) Kuntze)[J]. Journal of Applied Research on Medicinal and Aromatic Plants, 2022, 31: 100389. doi: 10.1016/j.jarmap.2022.100389.
[3] Lu X H, Wang J, Lu G D, et al.Quality level identification of West Lake Longjing green tea using electronic nose[J]. Sensors and Actuators B: Chemical, 2019, 301: 127056. doi: 10.1016/j.snb.2019.127056.
[4] Gharibzahedi S M T, Barba F J, Zhou J, et al. Electronic sensor technologies in monitoring quality of tea: a review[J]. Biosensors, 2022, 12(5): 356. doi: 10.3390/bios12050356.
[5] Xu M, Wang J, Gu S.Rapid identification of tea quality by E-nose and computer vision combining with a synergetic data fusion strategy[J]. Journal of Food Engineering, 2019, 241: 10-17. doi: 10.1016/j.jfoodeng.2018.07.020.
[6] Yang J R, Wang J, Lu G D, et al.TeaNet: deep learning on near-infrared spectroscopy (NIR) data for the assurance of tea quality[J]. Computers and Electronics in Agriculture, 2021, 190: 106431. doi: 10.1016/j.compag.2021.106431.
[7] Hu Y, Yu H H, Song X B, et al.Comprehensive assessment of matcha qualities and visualization of constituents using hyperspectral imaging technology[J]. Food Research International, 2024, 196: 115110. doi: 10.1016/j.foodres.2024.115110.
[8] Li Y T, Sun J, Wu X H, et al.Grade identification of Tieguanyin tea using fluorescence hyperspectra and different statistical algorithms[J]. Journal of Food Science, 2019, 84(8): 2234-2241.
[9] Wang X R, Liu Y, Gong N, et al.Design of a tea strip-lining degree discrimination system based on appearance characteristics and near-infrared spectroscopy[J]. Journal of Food Composition and Analysis, 2024, 136: 106779. doi: 10.1016/j.jfca.2024.106779.
[10] Wang H J, Gu J N, Wang M R.A review on the application of computer vision and machine learning in the tea industry[J]. Frontiers in Sustainable Food Systems, 2023, 7: 1172543. doi: 10.3389/fsufs.2023.1172543.
[11] Liu F, Wang S D, Pang S C, et al.Detection and recognition of tea buds by integrating deep learning and image-processing algorithm[J]. Journal of Food Measurement and Characterization, 2024, 18(4): 2744-2761.
[12] Yan L, Pang L, Wang H, et al.Recognition of different Longjing fresh tea varieties using hyperspectral imaging technology and chemometrics[J]. Journal of Food Process Engineering, 2020, 43(4): e13378. doi: 10.1111/jfpe.13378.
[13] Zhang C, Wang J, Yan T, et al.An instance-based deep transfer learning method for quality identification of Longjing tea from multiple geographical origins[J]. Complex & Intelligent Systems, 2023, 9(3): 3409-3428.
[14] Jia W S, Ma Z H, Lan Y, et al.An identification of the growing area of Longjing tea based on the Fisher's discriminant analysis with the combination of principal components analysis[J]. Intelligent Automation & Soft Computing, 2013, 19(4): 545-553.
[15] Chen Y, Guo M Q, Chen K, et al.Predictive models for sensory score and physicochemical composition of Yuezhou Longjing tea using near-infrared spectroscopy and data fusion[J]. Talanta, 2024, 273: 125892. doi: 10.1016/j.talanta.2024.125892.
[16] Yu X L, Li J, Yang Y Q, et al.Comprehensive investigation on flavonoids metabolites of Longjing tea in different cultivars, geographical origins, and storage time[J]. Heliyon, 2023, 9(6): e17305. doi: 10.1016/j.heliyon.2023.e17305.
[17] Fang Z T, Yang W T, Li C Y, et al.Accumulation pattern of catechins and flavonol glycosides in different varieties and cultivars of tea plant in China[J]. Journal of Food Composition and Analysis, 2021, 97: 103772. doi: 10.1016/j.jfca.2020.103772.
[18] Li Q Q, Zhang C Y, Wang H W, et al.Machine learning technique combined with data fusion strategies: a tea grade discrimination platform[J]. Industrial Crops and Products, 2023, 203: 117127. doi: 10.1016/j.indcrop.2023.117127.
[19] Li Y T, He L Y, Jia J M, et al.High-efficiency tea shoot detection method via a compressed deep learning model[J]. International Journal of Agricultural and Biological Engineering, 2022, 15(3): 159-166.
[20] Zhu F L, Wang J, Zhang Y Q, et al.An improved 3D-SwinT-CNN network to evaluate the fermentation degree of black tea[J]. Food Control, 2025, 167: 110756. doi: 10.1016/j.foodcont.2024.110756.
[21] Zhu Y W, Chen S Y, Yin H Z, et al.Classification of oolong tea varieties based on computer vision and convolutional neural networks[J]. Journal of the Science of Food and Agriculture, 2024, 104(3): 1630-1637.
[22] Khalvati F, Wong A, Haider M A.Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models[J]. BMC Med Imaging, 2015, 15: 27. doi: 10.1186/s12880-015-0069-9.
[23] Jiang M F, Chen Z.Symmetry detection algorithm to classify the tea grades using artificial intelligence[J]. Microprocessors and Microsystems, 2021, 81: 103738. doi: 10.1016/j.micpro.2020.103738.
[24] Rahman M T, Ferdous S, Jenin M S, et al.Characterization of tea (Camellia sinensis) granules for quality grading using computer vision system[J]. Journal of Agriculture and Food Research, 2021, 6: 100210. doi: 10.1016/j.jafr.2021.100210.
[25] Gill G S, Kumar A, Agarwal R.Nondestructive grading of black tea based on physical parameters by texture analysis[J]. Biosystems Engineering, 2013, 116(2): 198-204.
[26] Laddi A, Prakash N R.Case studies in intelligent computing[M]. 1st ed. New York: Auerbach Publications, 2014: 535-546.
[27] 刘自强, 周铁军, 傅冬和, 等. 基于颜色和形状的鲜茶叶图像特征提取及在茶树品种识别中的应用[J]. 江苏农业科学, 2021, 49(12): 168-172.
Liu Z Q, Zhou T J, Fu D H, et al.Study on image feature extraction of fresh tea based on color and shape and its application in tea variety recognition[J]. Jiangsu Agricultural Sciences, 2021, 49(12): 168-172.
[28] 谢汉垒. 基于无损检测技术茶叶等级识别和拼配技术研究[D]. 合肥: 安徽农业大学, 2020.
Xie H L.Study on tea grade recognition and matching technology based on nondestructive testing technology [D]. Hefei: Anhui Agricultural University, 2020.
[29] 张金炎, 曹成茂, 李文宝, 等. 基于多特征融合的茶叶鲜叶等级识别的方法研究[J]. 安徽农业大学学报, 2021, 48(3): 480-487.
Zhang J Y, Cao C M, Li W B, et al.Study on the method of recognition of fresh leaf grade of tea based on multi-feature fusion[J]. Journal of Anhui Agricultural University, 2021, 48(3): 480-487.
[30] Gan N, Sun M F, Lu C Y, et al.High-speed identification system for fresh tea leaves based on phenotypic characteristics utilizing an improved genetic algorithm[J]. Journal of the Science of Food and Agriculture, 2022, 102(15): 6858-6867.
[31] Bakhshipour A, Zareiforoush H, Bagheri I.Application of decision trees and fuzzy inference system for quality classification and modeling of black and green tea based on visual features[J]. Journal of Food Measurement and Characterization 2020, 14(3): 1402-1416.
[32] Liu Y, Huang J L, Li M H, et al.Rapid identification of the green tea geographical origin and processing month based on near-infrared hyperspectral imaging combined with chemometrics[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 267: 120537. doi: 10.1016/j.saa.2021.120537.
[33] Jia J M, Zhou X F, Li Y, et al.Establishment of a rapid detection model for the sensory quality and components of Yuezhou Longjing tea using near-infrared spectroscopy[J]. LWT, 2022, 164: 113625. doi: 10.1016/j.lwt.2022.113625.
[34] Li C L, Guo H W, Zong B Z, et al.Rapid and non-destructive discrimination of special-grade flat green tea using near-infrared spectroscopy[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 206: 254-262. doi: 10.1016/j.saa.2018.07.085.
浙公网安备 33019902000101号