Skip to main content
SpringerLink
Log in

Related Study Based on Otsu Watershed Algorithm and New Squeeze-and-Excitation Networks for Segmentation and Level Classification of Tea Buds

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In this study, image segmentation technology is utilized for segmentation of tea leaves and tender buds and deep learning technology is introduced for tea bud classification. Watershed algorithm has good robustness in the field of image segmentation under complex backgrounds, and the key of the algorithm is to determine the image segmentation threshold, which directly affects the accuracy of segmentation. “Maximum Between-Class Variance Method” (Otsu) as a great algorithm that can obtain the global optimal threshold is applied creatively to traditional watershed algorithm in this paper, which we call “Otsu Watershed Algorithm”. Then the structure of the “Squeeze-and-Excitation” (SE) block is adjusted appropriately to improve the feature presentation ability of the network by embedding into several common deep learning models. Extensive experiments demonstrate that this new SE block has superior accuracy and integration capability on challenging dataset and our tea bud dataset.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Nakachi K, Matsuyama S, Miyake S et al (2000) Preventive effects of drinking green tea on cancer and cardiovascular disease: epidemiological evidence for multiple targeting prevention. BioFactors 13:49–54

    Article  Google Scholar 

  2. Setiawan VW, Zhang ZF, Yu GP et al (2001) Protective effect of green tea on the risks of chronic gastritis and stomach cancer. Int J Cancer 92:600–604

    Article  Google Scholar 

  3. Shibata K, Moriyama M, Fukushima T et al (2000) Green tea consumption and chronic atrophic gastritis: a cross-sectional study in a green tea production village. Epidemiol 10:310–316

    Article  Google Scholar 

  4. Jian L, Xie LP, Lee AH et al (2004) Protective effect of green tea against prostate cancer: a case-control study in southeast China. Int J Cancer 108:130–135

    Article  Google Scholar 

  5. Fujiki H, Suganuma M, Okabe S et al (2001) Cancer inhibition by green tea. Research 299:480–481

    Google Scholar 

  6. Feng HS (2015) The demand for mechanized tea picking is urgent. Farmers Daily

  7. Huang XD (2006) The development of picking machinery in China and the research direction of high-grade tea picking. In: The 6th China Agricultural Machinery Forum and the 4th Asian Agricultural Machinery Summit, the National Agricultural Machinery Circulation Outstanding Contribution Unit commendation meeting, the 4th National Council of Agricultural Machinery Circulation Association

  8. Hang Y, Hong R, Guang M (2014) Research on the development status of tea picking machinery at domestic and foreign. Chin J Agric Mech 5:20–24

    Google Scholar 

  9. Zheng NF, Zhen K (2011) Mechanized tea picking: broking the bottleneck in the development of tea industry. Chin Rural Technol 64–65

  10. Kuma N, Belhumeur PN, Biswas A (2012) Leafsnap: a computer vision system for automatic plant species identification. Eur Conf Comput Vis 7573:502–508

    Google Scholar 

  11. Cerutti G, Tougne L, Mille J (2011) Guiding active contours for tree leaf segmentation and identification. In: CLEF 2011 labs and workshop, pp 19–22

  12. Wang XF, Huang DS, Du JX (2008) Classification of plant leaf images with complicated background. Appl Math Comput 205:916–926

    MathSciNet  MATH  Google Scholar 

  13. Wang J, Zeng X, Liu J (2011) Three-dimensional modeling of tea-shoots using images and models. Sensors 11:3803–3815

    Article  Google Scholar 

  14. Yang FZ, Yang LL, Tian YN (2009) Tea buds recognition method based on color and shape characteristics. Trans Chin Soc Agric Mach S1:119–121

    Google Scholar 

  15. Oide M, Ninomiya S (2000) Discrimination of soybean leaflet shape by neural networks with image input. Comput Electron Agric 29:64–70

    Article  Google Scholar 

  16. Tang Z, Su Y, Er MJ (2015) A local binary pattern based texture descriptors for classification of tea leaves. Neurocomputing 168:1011–1023

    Article  Google Scholar 

  17. Barre P, Stoever BC (2017) LeafNet: A computer vision system for automatic plant species identification. Ecol Inform 40:50–54

    Article  Google Scholar 

  18. Jun Yu, Yao J, Zhang J et al (2020) SPRNet: single-pixel reconstruction for one-stage instance segmentation. IEEE TCYB. https://doi.org/10.1109/TCYB

    Article  Google Scholar 

  19. de Oliveira ISM, Linares OAC, de Oliveira AHM et al (2019) Image segmentation based on multiplex networks and super pixels. Comput Sci Inf Technol 34:33–42

    Google Scholar 

  20. Khairuzzaman AKM, Chaudhury S (2019) Masi entropy based multilevel thresholding for image segmentation. Multimed Tools Appl 78:33573–33591

    Article  Google Scholar 

  21. Podrezov RV, Raifeld MA (2020) Nonparametric method of estimating number of classes in image segmentation. Optoelectron Instrum Data Process 56:280–287

    Article  Google Scholar 

  22. Yang SB, Long YH, Yao JC (2019) Research on target Arae segmentation algorithm based on image. Electron Eng Product World 2:67–68

    Google Scholar 

  23. Cha YF, Liu JL, Bi DY (2006) Watershed image segmentation algorithm based on multi-resolution. Comput Eng 19:202–203

    Google Scholar 

  24. Zhang R, Feng XC, Yang LX (2019) A global sparse gradient based coupled system for image denoising. Comput Math Appl 78:3692–3711

    Article  MathSciNet  Google Scholar 

  25. Tian CW, Xu Y, Zuo WM (2019) Image denoising using deep CNN with batch renormalization. Neural Netw 121:461–473

    Article  Google Scholar 

  26. Wang GH, Liu Y, Xiong W (2018) An improved non-local means filter for color image denoising. Optik 173:157–173

    Article  Google Scholar 

  27. Hamarneh G, Li X (2009) Watershed segmentation using prior shape and appearance knowledge. Image Vis Comput 27:59–64

    Article  Google Scholar 

  28. Huang HJ (2018) Image recognition of tea leaves based on improved watershed algorithm. Guizhou Agric Sci 46:136–138

    Google Scholar 

  29. Fang Y, Zhao J (2019) Image classification toward breast cancer using deeply-learned quality features. J Vis Commun Image Represent 64:102609

    Article  Google Scholar 

  30. Ciocca G, Napoletano P (2018) CNN-based features for retrieval and classification of food images. Comput Vis Image Underst 176–177:70–75

    Article  Google Scholar 

  31. Steinbrener J (2019) Hyperspectral fruit and vegetable classification using convolutional neural networks. Comput Electron Agric 162:364–370

    Article  Google Scholar 

  32. Zou XW, Wang ZD, Li Q (2019) Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification. Neurocomputing 367:39–45

    Article  Google Scholar 

  33. Zeng Z, Liang NY, Yang XL (2018) Multi-target deep neural networks: theoretical analysis and implementation. Neurocomputing 273:634–642

    Article  Google Scholar 

  34. Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. In: NIPS, vol 1, p 2

  35. Lee H, Grosse R, Ranganath R et al (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: ICML, p 8

  36. Mnih V, Heess N, Graves A et al (2014) Recurrent models of visual attention. In: NIPS, p 2

  37. Stollenga MF, Masci J, Gomez F et al (2014) Deep networks with internal selective attention through feedback connections. In: NIPS, p 2

  38. Hong CQ, Yu J, Zhang J et al (2019) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Industr Inf 15:3952–3961

    Article  Google Scholar 

  39. Szegedy C, Liu W, Jia Y, et al (2015) Going deeper with convolutions. In: CVPR, pp 1–4

  40. Szegedy C, Vanhoucke V, Loffe S et al (2016) Rethinking the inception architecture for computer vision. In: CVPR, pp 2–6

  41. Szegedy C, Loffe S,Vanhoucke V et al (2016) Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: ICLR Workshop, pp 2–6

  42. Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks. In: CVPR. 2–6

  43. He KM, Zhang XG, Ren SQ et al (2016) Deep residual learning for image recognition. In: CVPR, pp 2–6

  44. He KM, Zhang XG, Ren SQ et al (2016) Identity mappings in deep residual networks. In: ECCV, pp 2–6

Download references

Acknowledgements

This work is supported by the Project of Scientific and Technological Innovation Planning of Hunan Province (2020NK2008), the earmarked fund for China Agriculture Research System (CARS-19), Hunan Province Modern Agriculture Technology System for Tea Industry.

Author information

Authors and Affiliations

  1. School of Computer Science, Central South University, Changsha, 410083, China

    Fang Qi, Zuoqi Xie & Zhe Tang

  2. Changsha Xiangfeng Tea Machinery Manufacturing Co., Ltd., Changsha, 410100, China

    Huarong Chen

Authors
  1. Fang Qi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zuoqi Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhe Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huarong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhe Tang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qi, F., Xie, Z., Tang, Z. et al. Related Study Based on Otsu Watershed Algorithm and New Squeeze-and-Excitation Networks for Segmentation and Level Classification of Tea Buds. Neural Process Lett 53, 2261–2275 (2021). https://doi.org/10.1007/s11063-021-10501-1

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-021-10501-1

Keywords

Search

Navigation