Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 29;13(11):1708.
doi: 10.3390/foods13111708.

Online System for Monitoring the Degree of Fermentation of Oolong Tea Using Integrated Visible-Near-Infrared Spectroscopy and Image-Processing Technologies

Pengfei Zheng  1 , Selorm Yao-Say Solomon Adade  1 , Yanna Rong  1 , Songguang Zhao  1 , Zhang Han  1   2 , Yuting Gong  2 , Xuanyu Chen  1 , Jinghao Yu  1 , Chunchi Huang  2 , Hao Lin  1
Affiliations

Online System for Monitoring the Degree of Fermentation of Oolong Tea Using Integrated Visible-Near-Infrared Spectroscopy and Image-Processing Technologies

Pengfei Zheng et al. Foods. .

Abstract

During the fermentation process of Oolong tea, significant changes occur in both its external characteristics and its internal components. This study aims to determine the fermentation degree of Oolong tea using visible-near-infrared spectroscopy (vis-VIS-NIR) and image processing. The preprocessed vis-VIS-NIR spectral data are fused with image features after sequential projection algorithm (SPA) feature selection. Subsequently, traditional machine learning and deep learning classification models are compared, with the support vector machine (SVM) and convolutional neural network (CNN) models yielding the highest prediction rates among traditional machine learning models and deep learning models with 97.14% and 95.15% in the prediction set, respectively. The results indicate that VIS-NIR combined with image processing possesses the capability for rapid non-destructive online determination of the fermentation degree of Oolong tea. Additionally, the predictive rate of traditional machine learning models exceeds that of deep learning models in this study. This study provides a theoretical basis for the fermentation of Oolong tea.

Keywords: Oolong tea; data fusion; fermentation; machine learning; prediction.

PubMed Disclaimer

Conflict of interest statement

Authors Zhang Han, Yuting Gong, and Chunchi Huang are employed by Chi Chun Machinery (Xiamen) Co., Ltd. Author Zhang Han participated in the investigation. Author Yuting Gong participated in the formal analysis. Author Chunchi Huang participated in the data curation of this study. The company provided materials and equipment but did not provide financial support. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
The process diagram of Oolong tea fermentation degree determination based on VIS-NIR and image-processing data fusion technology.
Figure 2
Figure 2
Sampling flow diagram.
Figure 3
Figure 3
(a) Changes in the area of the red part of the leaf; (b) RGB, HSV, and Lab changing trends; (c) varying trends of texture feature values extracted from the gray co—occurrence matrix.
Figure 4
Figure 4
The distribution of the extracted characteristic variables throughout the spectrum: (a) CARS; (b) SPA; (c) VCPA; (d) VCPA-IRIV.
Figure 5
Figure 5
Diagrams of the three traditional machine learning modeling processes: (a) LDA, (b) SVM, (c,d) BPANN.
Figure 6
Figure 6
(a) Confusion matrix of the CNN model, (b) loss function of the CNN model, (c) confusion matrix of the MLP model, (d) loss function of the MLP model.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Ng K.-W., Cao Z.-J., Chen H.-B., Zhao Z.-Z., Zhu L., Yi T. Oolong tea: A critical review of processing methods, chemical composition, health effects, and risk. Crit. Rev. Food Sci. Nutr. 2017;58:2957–2980. doi: 10.1080/10408398.2017.1347556. - DOI - PubMed
    1. Lin Y., Yu W., Zhou L., Fan X., Wang F., Wang P., Fang W., Cai C., Ye N. Genetic diversity of oolong tea (Camellia sinensis) germplasms based on the nanofluidic array of single-nucleotide polymorphism (SNP) markers. Tree Genet. Genomes. 2019;16:3. doi: 10.1007/s11295-019-1392-z. - DOI
    1. Xu Y.-Q., Liu P.-P., Shi J., Gao Y., Wang Q.-S., Yin J.-F. Quality development and main chemical components of Tieguanyin oolong teas processed from different parts of fresh shoots. Food Chem. 2018;249:176–183. doi: 10.1016/j.foodchem.2018.01.019. - DOI - PubMed
    1. Theppakorn T. Stability and chemical changes of phenolic compounds during Oolong tea processing. Int. Food Res. J. 2016;23:564.
    1. Li L., Wang Y., Cui Q., Liu Y., Ning J., Zhang Z. Qualitative and quantitative quality evaluation of black tea fermentation through noncontact chemical imaging. J. Food Compos. Anal. 2022;106:104300. doi: 10.1016/j.jfca.2021.104300. - DOI

LinkOut - more resources