Simplified Version of White Wine Grape Berries Detector Based on SVM and HOG Features

  • Pavel SkrabanekEmail author
  • Filip Majerík
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 464)


The detection of grapes in real scene images is a serious task solved by researches dealing with precision viticulture. Our research has shown that in the case of white wine varieties, grape berry detectors based on a support vector machine classifier in combination with a HOG descriptor are very efficient. In this paper, simplified versions of our original solutions are introduced. Our research showed that skipping contrast normalization by image preprocessing accelerates the detection process; however, the performance of the detectors is not negatively influenced by this modification.


Computer vision Precision viticulture Grape detection Support vector machine HOG features 



The work has been supported by the Funds of University of Pardubice, Czech Republic. We would like to offer our special thanks to company Víno Sýkora s.r.o. which enabled us to perform experiments in its vineyards.


  1. 1.
    Arnó Satorra, J., Martínez Casasnovas, J.A., Ribes Dasi, M., Rosell Polo, J.R.: Review. Precision viticulture. Research topics, challenges and opportunities in site-specific vineyard management. Span. J. Agric. Res. 7(4), 779–790 (2009)Google Scholar
  2. 2.
    Berenstein, R., Shahar, O., Shapiro, A., Edan, Y.: Grape clusters and foliage detection algorithms for autonomous selective vineyard sprayer. Intell. Serv. Robot. 3(4), 233–243 (2010)CrossRefGoogle Scholar
  3. 3.
    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)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005, vol. 1, pp. 886–893 (2005)Google Scholar
  5. 5.
    Diago, M.P., Correa, C., Milln, B., Barreiro, P., Valero, C., Tardaguila, J.: Grapevine yield and leaf area estimation using supervised classification methodology on RGB images taken under field conditions. Sensors 12(12), 16988–17006 (2012)CrossRefGoogle Scholar
  6. 6.
    Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach. Pearson, 2nd edn. (2012)Google Scholar
  7. 7.
    ITU-R Recommendation BT.601: Studio encoding parameters of digital television for standard 4:3 and wide screen 16:9 aspect ratios (2011)Google Scholar
  8. 8.
    Krig, S.: Computer Vision Metrics: Survey, Taxonomy, and Analysis, 1st edn. Apress, Berkely, CA, USA (2014)Google Scholar
  9. 9.
    Lampert, C.H.: Kernel methods in computer vision. Found. Trends Comput. Graph. Vis. 4(3), 193–285 (2008)CrossRefzbMATHGoogle Scholar
  10. 10.
    Liu, S., Whitty, M.: Automatic grape bunch detection in vineyards with an SVM classifier. J. Appl. Logic (2015)Google Scholar
  11. 11.
    Nuske, S., Achar, S., Bates, T., Narasimhan, S., Singh, S.: Yield estimation in vineyards by visual grape detection. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2352–2358. IEEE (2011)Google Scholar
  12. 12.
    Reis, M., Morais, R., Peres, E., Pereira, C., Contente, O., Soares, S., Valente, A., Baptista, J., Ferreira, P., Cruz, J.B.: Automatic detection of bunches of grapes in natural environment from color images. J. Appl. Logic 10(4), 285–290 (2012)CrossRefGoogle Scholar
  13. 13.
    Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45(4), 427–437 (2009)CrossRefGoogle Scholar
  14. 14.
    Škrabánek, P., Runarsson, T.P.: Detection of grapes in natural environment using support vector machine classifier. In: Proceedings of the 21st International Conference on Soft Computing MENDEL 2015, Brno University of Technology, Brno, Czech Republic, 23–25 Jun 2015, pp. 143–150 (2015)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Faculty of Electrical Engineering and InformaticsUniversity of PardubicePardubiceCzech Republic

Personalised recommendations