Original Articles Open access

Distinguishing tea stalks of Wuyuan green tea using hyperspectral imaging analysis and convolutional neural network

Authors

Published
16 February 2024
Section
Original Articles
DOI
10.4081/jae.2024.1560

Abstract

A well-known agricultural product in China, Wuyuan green tea is safeguarded by national geographical indications. In addition, the processed green tea must be free of contaminants like stones and tea stalks. Nevertheless, due to their similar colors, photoelectric sorting and 2D image recognition technologies are unable to distinguish tea stalks from Wuyuan green tea. In order to address the issue of incorrect sorting brought on by similar color matching, this paper uses hyperspectral imaging technology. Using a 400–1000 nm visible and near-infrared camera, green tea with tea stalks was photographed. Furthermore, the hyperspectral image that was gathered was reduced in dimension using principal component analysis. Additionally, tea stalks were successfully identified in hyperspectral images using the convolutional neural network, which can automatically learn the corresponding features and do away with the laborious feature extraction procedure. According to the experiment’s findings, tea stalks can be recognized with an accuracy of 98.53%. The technique can meet the real production requirements and has a high recognition rate. The selection rate is as high as 97.05% following field testing.

Keywords

References

  1. Chen P., Wu T. Detection of impurities in tea using Hough transform after removing shadows[J]. Mechanical Engineering and Automation, 2014(05): 63-65.
  2. Chen S., Zhang C. A fast image sorting method of tea stalk color sorter[J]. Journal of Hefei Univer-sity(Natural Science Edition), 2013, 23(04): 36-41.
  3. Celik T. Unsupervised change detection in satellite images using principal component analysis and k-means clustering[J]. IEEE geoscience and remote sensing letters, 2009, 6(4): 772-776. DOI: https://doi.org/10.1109/LGRS.2009.2025059
  4. ElMasry G, Sun D W. Principles of hyperspectral imaging technology[M]. Hyperspectral imaging for food quality analysis and control. Academic Press, 2010: 3-43. DOI: https://doi.org/10.1016/B978-0-12-374753-2.10001-2
  5. Fu L, Okamoto H, Shibata Y, et al. Distinguishing overripe berries of Japanese blue honeysuckle using hyperspectral imaging analysis[J]. Engineering in agriculture, environment and food, 2014, 7(1): 22-27. DOI: https://doi.org/10.1016/j.eaef.2013.12.004
  6. Hu L. Wuyuan green tea: green bushes are all over the mountains and fields, and every household has fragrant tea[J]. Jiangxi Agriculture, 2015(02): 24-25.
  7. Hu B., He X. Key technologies for primary processing of Wuyuan green tea[J]. Agricultural Devel-opment and Equipment, 2016(05): 138.
  8. Jimenez L O, Landgrebe D A. Hyperspectral data analysis and supervised feature reduction via pro-jection pursuit[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(6): 2653-2667. DOI: https://doi.org/10.1109/36.803413
  9. LIU Y. Status and development of hyperspectral imaging remote sensing payload technology[J]. Acta Remote Sensing, 2021, 25(01): 439-459. DOI: https://doi.org/10.11834/jrs.20210283
  10. Lu R. Detection of bruises on apples using near-infrared hyperspectral imaging[J]. Transactions of the ASAE, 2003, 46(2): 523. DOI: https://doi.org/10.13031/2013.12941
  11. Lu B, Dao P D, Liu J, et al. Recent advances of hyperspectral imaging technology and applications in agriculture[J]. Remote Sensing, 2020, 12(16): 2659. DOI: https://doi.org/10.3390/rs12162659
  12. Panda A, Pachori R B, Sinnappah-Kang N D. Classification of chronic myeloid leukemia neutrophils by hyperspectral imaging using Euclidean and Mahalanobis distances[J]. Biomedical Signal Pro-cessing and Control, 2021, 70: 103025. DOI: https://doi.org/10.1016/j.bspc.2021.103025
  13. Quan Q. Research and development of tea stem picker in China [J]. China Tea, 2018, 40 (07): 6-11.
  14. Ren Z. A new intermittent tea stem picker [J]. China Tea, 1989 (02): 21. DOI: https://doi.org/10.5979/cha.1989.21
  15. Ren J, Zabalza J, Marshall S, et al. Effective feature extraction and data reduction in remote sensing using hyperspectral imaging [applications corner][J]. IEEE Signal Processing Magazine, 2014, 31(4): 149-154. DOI: https://doi.org/10.1109/MSP.2014.2312071
  16. Sun J., Xiong S., Wang L. Single chip control of tea stem picking machine[J]. Mechanical and Electrical Engineering, 1997(03): 23-24.
  17. Shaheen F, Verma B, Asafuddoula M. Impact of automatic feature extraction in deep learning archi-tecture[C]. 2016 International conference on digital image computing: techniques and applications (DICTA). IEEE, 2016: 1-8. DOI: https://doi.org/10.1109/DICTA.2016.7797053
  18. Uğuz H. A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm[J]. Knowledge-Based Systems, 2011, 24(7): 1024-1032. DOI: https://doi.org/10.1016/j.knosys.2011.04.014
  19. Windham W R, Lawrence K C, Park B, et al. Analysis of reflectance spectra from hyperspectral images of poultry carcasses for fecal and ingesta detection[C]. Imaging Spectrometry Ⅷ. SPIE, 2002, 4816: 317-324. DOI: https://doi.org/10.1117/12.451653
  20. Xie P., Tao D., Ren S. Development status and trend of tea stem picker [J]. Research on Agricultural Mechanization, 2004 (01): 44-45.

Metrics

Citations and online attention from Dimensions, Altmetric and PlumX.

PlumX Metrics

License

Copyright (c) 2024 the Author(s)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.