Improved
                    CycleGAN
                    Based Quality Level Identification of Tea

Xiaohui Lu; Jin Wang; Cheng Zhang; Guodong Lu

doi:10.1111/jfpe.70482

journal article Apr 01, 2026

Improved CycleGAN Based Quality Level Identification of Tea

Xiaohui Lu

Jin Wang

Cheng Zhang

Guodong Lu

Journal of Food Process Engineering Vol. 49 No. 4 · Wiley

View at Publisher Save 10.1111/jfpe.70482

Abstract

ABSTRACT
Chinese tea culture has a long history, and tea tasting is a relaxation and a kind of art philosophy. Thus, they have a set of quality evaluation system since ancient times. There are many varieties and brands of Chinese tea. It is relatively difficult to identify tea quality without a professional analyzer. To this end, we propose a quality identification method by computer vision based on deep learning methods. The method can help to analyze the complex characteristics of tea. The results show that the proposed system is capable of distinguishing the Longjing green tea grades accurately. Our findings will assist people to achieve intelligent inspecting and grading of tea by vision.

Topics

No keywords indexed for this article. Browse by subject →

References

26

[1]

10.1631/jzus.b1600423

[2]

Dou H. C.Chen X.Hu andS.Peng.2019.“Asymmetric Cyclegan for Unpaired NIR‐To‐RGB Face Image Translation.”ICASSP IEEE International Conference on Acoustics Speech and Signal Processing ‐ Proceedings 2019‐May. 1757–1761.https://doi.org/10.1109/ICASSP.2019.8682600. 10.1109/icassp.2019.8682600

[3]

10.1016/j.biosystemseng.2013.08.002

[4]

Generative adversarial networks

Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al.

Communications of the ACM 10.1145/3422622

[5]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[6]

10.1016/j.fbp.2016.12.004

[7]

Isola P. J. Y.Zhu T.Zhou andA. A.Efros.2017.“Image‐To‐Image Translation With Conditional Adversarial Networks.”Proceedings ‐ 30th IEEE Conference on Computer Vision and Pattern Recognition CVPR 2017. 5967‐5976.https://doi.org/10.1109/CVPR.2017.632. 10.1109/cvpr.2017.632

[8]

ImageNet classification with deep convolutional neural networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

Communications of the ACM 10.1145/3065386

[9]

10.1016/j.snb.2019.127056

[10]

10.1007/978-981-10-5430-3_19

[11]

Simonyan K. andA.Zisserman.2014.“Very Deep Convolutional Networks for Large‐Scale Image Recognition.”ArXiv 1409.1556.

[12]

10.1016/j.jfoodeng.2011.04.013

[13]

Going deeper with convolutions

Christian Szegedy, Wei Liu, Yangqing Jia et al.

2015 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2015.7298594

[14]

Tan M. B.Chen R.Pang et al.2019.“MnasNet: Platform‐Aware Neural Architecture Search for Mobile.”2815‐2823.https://doi.org/10.1109/CVPR.2019.00293. 10.1109/cvpr.2019.00293

[15]

10.1016/j.neucom.2015.05.024

[16]

Voreiter C. J. C.Burnel P.Lassalle M.Spigai R.Hugues andN.Courty.2020.“A Cycle Gan Approach for Heterogeneous Domain Adaptation in Land Use Classification.”International Geoscience and Remote Sensing Symposium (IGARSS) 1961‐1964.https://doi.org/10.1109/IGARSS39084.2020.9324264. 10.1109/igarss39084.2020.9324264

[17]

Wang C. andY. B.Yu.2020.“CycleGAN‐VC‐GP: Improved CycleGAN‐Based Non‐Parallel Voice Conversion.”International Conference on Communication Technology Proceedings ICCT. 1281–1284.https://doi.org/10.1109/ICCT50939.2020.9295938. 10.1109/icct50939.2020.9295938

[18]

10.1016/j.jfoodeng.2018.07.020

[19]

10.1111/jfpe.13378

[20]

10.1109/tcsvt.2019.2920407

[21]

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin et al.

2018 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2018.00716

[22]

10.1007/s11263‐020‐01301‐6

[23]

10.3390/e18030077

[24]

10.1007/s11042‐018‐5765‐3

[25]

10.1364/ao.48.003557

[26]

Zhu J. Y. T.Park P.Isola andA. A.Efros.2017.“Unpaired Image‐To‐Image Translation Using Cycle‐Consistent Adversarial Networks.”Proceedings of the IEEE International Conference on Computer Vision. 2242–2251.https://doi.org/10.1109/ICCV.2017.244. 10.1109/iccv.2017.244

Metrics

0

Citations

26

References

Details

Published: Apr 01, 2026
Vol/Issue: 49(4)
License: View

Authors

X

Xiaohui Lu

School of Intelligent Manufacturing and Energy Engineering, Zhejiang University of Science and Technology Hangzhou China

J

Jin Wang

State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou China

C

Cheng Zhang

China North Artificial Intelligence and Innovation Research Institute Beijing China

G

Guodong Lu

State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou China

Funding

Key Research and Development Program of Zhejiang Province Award: 2024C01127

Cite This Article

Xiaohui Lu, Jin Wang, Cheng Zhang, et al. (2026). Improved CycleGAN Based Quality Level Identification of Tea. Journal of Food Process Engineering, 49(4). https://doi.org/10.1111/jfpe.70482

Improved CycleGAN Based Quality Level Identification of Tea

You May Also Like