Skip to main content

Comparison of Machine Learning and Deep Learning Methods for Grape Cluster Segmentation

Part of the Communications in Computer and Information Science book series (CCIS,volume 1470)


Automatic grape detection is one of the first steps towards automatic yield estimation. This step is often performed with a computer vision algorithm using the classic feature extraction and classification approach. Many grape bunch detection algorithms have been proposed in the last decade and most of them follow this standard approach. An alternative is semantic segmentation with deep learning models. The main objective of this work is to compare existing algorithms based on machine learning to encoder-decoder segmentation models (UNet and PSPNet). The comparison was performed on two challenging datasets of white grape varieties in natural lighting conditions. The UNet model reached better performances on both datasets with up-to 0.76 IoU score (compared to 0.59 IoU for the second best model). UNet was combined to a linear model to estimate the total number of grape bunches in 200 plants and reached 86% counting accuracy. The results show that deep learning models are more robust to white grape detection compared to classic segmentation techniques. This is an important property for early yield estimation before veraison.


  • Grape detection
  • Precision viticulture
  • Deep learning
  • Semantic segmentation

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD   54.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions


  1. 1.


  1. Abdelghafour, F., Rosu, R., Keresztes, B., Germain, C., Da Costa, J.P.: A bayesian framework for joint structure and colour based pixel-wise classification of grapevine proximal images. Comput. Electron. Agric. 158, 345–357 (2019).

    CrossRef  Google Scholar 

  2. Aquino, A., Millan, B., Diago, M.P., Tardaguila, J.: Automated early yield prediction in vineyards from on-the-go image acquisition. Comput. Electron. Agric. 144, 26–36 (2018).

    CrossRef  Google Scholar 

  3. Araya-Alman, M., et al.: A new localized sampling method to improve grape yield estimation of the current season using yield historical data. Precis. Agric. 20(2), 445–459 (2019).

    CrossRef  Google Scholar 

  4. Behroozi-Khazaei, N., Maleki, M.R.: A robust algorithm based on color features for grape cluster segmentation. Comput. Electron. Agric. 142, 41–49 (2017).

    CrossRef  Google Scholar 

  5. Berenstein, R., Shahar, O.B., Shapiro, A., Edan, Y.: Grape clusters and foliage detection algorithms for autonomous selective vineyard sprayer. Intell. Serv. Robot. 3(44), 233–243 (2010).

    CrossRef  Google Scholar 

  6. Bramley, R., Hamilton, R.: Understanding variability in winegrape production systems. Aust. J. Grape Wine Res. 10(1), 32–45 (2004).,

  7. Burges, C.J.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121–167 (1998).

    CrossRef  Google Scholar 

  8. Cecotti, H., Rivera, A., Farhadloo, M., Pedroza, M.A.: Grape detection with convolutional neural networks. Expert Syst. Appl. 159, 113588 (2020).

  9. Chamelat, R., Rosso, E., Choksuriwong, A., Rosenberger, C., Laurent, H., Bro, P.: Grape detection by image processing. In: IECON 2006–32nd Annual Conference on IEEE Industrial Electronics, pp. 3697–3702 (2006).

  10. Cireşan, D.C., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Deep neural networks segment neuronal membranes in electron microscopy images. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 2, pp. 2843–2851. NIPS 2012, Curran Associates Inc., Red Hook, NY, USA (2012)

    Google Scholar 

  11. Clingeleffer, P.R., Martin, S.R., Dunn, G.M., Krstic, M.P.: Crop development, crop estimation and crop control to secure quality and production of major wine grape varieties : a national approach : final report to Grape and Wine Research and Development Corporation/principal investigator, Peter Clingeleffer; [prepared and edited by Steve Martin and Gregory Dunn]. Adelaide, Grape and Wine Research and Development Corporation (2001)

    Google Scholar 

  12. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 886–893 (2005).

  13. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)

    Google Scholar 

  14. Dunn, G.M., Martin, S.R.: Yield prediction from digital image analysis: a technique with potential for vineyard assessments prior to harvest. Aust. J. Grape Wine Res. 10(33), 196–198 (2004).

    CrossRef  Google Scholar 

  15. Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997).,

  16. Goldberg, D.E.: Genetic algorithms. Pearson Education India (2006)

    Google Scholar 

  17. Grimm, J., Herzog, K., Rist, F., Kicherer, A., Töpfer, R., Steinhage, V.: An adaptable approach to automated visual detection of plant organs with applications in grapevine breeding. Biosyst. Eng. 183, 170–183 (2019).

    CrossRef  Google Scholar 

  18. Grossetete, M., Berthoumieu, Y., Da Costa, J.P., Germain, C., Lavialle, O., Grenier, G.: Early estimation of vineyard yield: site specific counting of berries by using a smartphone. In: International Conference on Agiculture Engineering (AgEng), pp. tabla137-C1915 (July 2012).

  19. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016).

  20. Heinrich, K., Roth, A., Breithaupt, L., Möller, B., Maresch, J.: Yield prognosis for the agrarian management of vineyards using deep learning for object counting. Wirtschaftsinformatik 2019 Proceedings, p. 15 (February 2019).

  21. Keresztes, B., Abdelghafour, F., Randriamanga, D., Da Costa, J.P., Germain, C.: Real-time fruit detection using deep neural networks. In: 14th International Conference on Precision Agriculture (2018).

  22. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015).

  23. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, pp. 1097–1105. NIPS 2012, Curran Associates Inc., Red Hook, NY, USA (2012)

    Google Scholar 

  24. LeCun, Y., Bengio, Y.: Convolutional Networks for Images, Speech, and Time Series, pp. 255–258. MIT Press, Cambridge, MA, USA (1998)

    Google Scholar 

  25. Liu, L., et al.: On the variance of the adaptive learning rate and beyond. CoRR abs/1908.03265 (2019).

  26. Liu, S., Zeng, X., Whitty, M.: A vision-based robust grape berry counting algorithm for fast calibration-free bunch weight estimation in the field. Comput. Electron. Agric. 173, 11 (2020).

    CrossRef  Google Scholar 

  27. Luo, L., Tang, Y., Zou, X., Wang, C., Zhang, P., Feng, W.: Robust grape cluster detection in a vineyard by combining the adaboost framework and multiple color components. Sensors (Basel, Switzerland) 16(1212), 21 (2016).,

  28. Millan, B., Velasco-Forero, S., Aquino, A., Tardaguila, J.: On-the-go grapevine yield estimation using image analysis and boolean model (December 2018).,

  29. Nuske, S., Wilshusen, K., Achar, S., Yoder, L., Singh, S.: Automated visual yield estimation in vineyards. J. Field Robot. 31(55), 837–860 (2014).

    CrossRef  Google Scholar 

  30. Reis, M.J.C.S., et al.: Automatic detection of bunches of grapes in natural environment from color images. J. Appl. Log. 10(44), 285–290 (2012).

  31. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).

    CrossRef  Google Scholar 

  32. Rudolph, R., Herzog, K., Töpfer, R., Steinhage, V.: Efficient identification, localization and quantification of grapevine inflorescences in unprepared field images using fully convolutional networks. arXiv:1807.03770 [cs] pp. 95–104 (July 2018)., arXiv: 1807.03770

  33. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2018)

    Google Scholar 

  34. Santos, T.T., de Souza, L.L., dos Santos, A.A., Avila, S.: Grape detection, segmentation, and tracking using deep neural networks and three-dimensional association. Comput. Electron. Agric. 170, 105247 (2020).

  35. Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017).

    CrossRef  Google Scholar 

  36. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015).

  37. Vazquez-Fernandez, E., Dacal-Nieto, A., Martin, F., Formella, A., Torres-Guijarro, S., Gonzalez-Jorge, H.: A computer vision system for visual grape grading in wine cellars. In: Fritz, M., Schiele, B., Piater, J.H. (eds.) ICVS 2009. LNCS, vol. 5815, pp. 335–344. Springer, Heidelberg (2009).

    CrossRef  Google Scholar 

  38. Victorino, G., Maia, G., Queiroz, J., Braga, R., Marques, J., Lopes, C.: Grapevine yield prediction using image analysis - improving the estimation of non-visible bunches. European Federation for Information Technology in Agriculture, Food and the Environment (EFITA), p. 6 (2019)

    Google Scholar 

  39. Wada, K., LabelMe, K.: Image Polygonal Annotation with Python (2016).

  40. Yakubovskiy, P.: Segmentation models (2019).

  41. Zabawa, L., Kicherer, A., Klingbeil, L., Töpfer, R., Kuhlmann, H., Roscher, R.: Counting of grapevine berries in images via semantic segmentation using convolutional neural networks. ISPRS J. Photogramm. Remote. Sens. 164, 73–83 (2020).

    CrossRef  Google Scholar 

  42. Zhang, M.R., Lucas, J., Hinton, G.E., Ba, J.: Lookahead optimizer: k steps forward, 1 step back. CoRR abs/1907.08610 (2019).

  43. Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. arXiv:1612.01105 [cs] (December 2016)., arXiv: 1612.01105

  44. Škrabánek, P.: Deepgrapes: precise detection of grapes in low-resolution images. IFAC-PapersOnLine 51(66), 185–189 (2018).

    CrossRef  Google Scholar 

  45. Škrabánek, P., Doležel, P.: Robust grape detector based on svms and hog features. Comput. Intell. Neurosci. 2017, 3478602 (2017).

Download references


This work has been performed in the project AI4DI: Artificial Intelligence for Digitizing Industry, under grant agreement No 826060. The project is co-funded by grants from Germany, Austria, Finland, France, Norway, Latvia, Belgium, Italy, Switzerland, and the Czech Republic and - Electronic Component Systems for European Leadership Joint Undertaking (ECSEL JU).

We want to thank Vranken-Pommery Monopole, our partner in the AI4DI project, for allowing image collection in their vineyards. We also thank the ROMEO Computing Center ( of Université de Reims Champagne-Ardenne, whose Nvidia DGX-1 server allowed us to accelerate the training steps and compare several model approaches.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Lucas Mohimont .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mohimont, L., Roesler, M., Rondeau, M., Gaveau, N., Alin, F., Steffenel, L.A. (2021). Comparison of Machine Learning and Deep Learning Methods for Grape Cluster Segmentation. In: Boumerdassi, S., Ghogho, M., Renault, É. (eds) Smart and Sustainable Agriculture. SSA 2021. Communications in Computer and Information Science, vol 1470. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-88258-7

  • Online ISBN: 978-3-030-88259-4

  • eBook Packages: Computer ScienceComputer Science (R0)