Farmland Weed Species Identification Based on Computer Vision

  • Shengping Liu
  • Junchan Wang
  • Liu Tao
  • Zhemin Li
  • Chengming Sun
  • Xiaochun ZhongEmail author
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 545)


In order to alleviate the difficulties in collecting indexes for the analysis of farmland weed communities, we implemented a computer vision technology-based method for the identification of farmland weeds at the species level. By using the super-green and maximum interclass difference methods to obtain a green vegetation binary image, we were able to separate weeds from cultivated crops through multiple etching and the removal of small areas. A BP (back propagation) neural network was used for weed recognition, and the morphological characteristics of the weeds and each region were selected following etching to construct the input matrix of the recognition model for training and testing the BP network. After experimenting with the computational vision method for the identification of five weed species, we discovered that the recognition accuracy rate reached 96%. The results showed that the computer vision method could quickly and accurately extract a weed community analysis index, thereby providing a reference for the intelligent analysis of weed communities.


Weed communities Index extraction Image processing Class Computer vision 



This research was supported by Technology Innovation Project Fund of Chinese Academy of Agricultural Sciences (2017).


  1. 1.
    Shuren, C., Huadong, Z., Ruimei, W., et al.: Identification for weedy rice at seeding stage based on hyper-spectral imaging technique. Trans. Chin. Soc. Agric. Mach. 44(05), 253–257 (2013)Google Scholar
  2. 2.
    Ali, A., Streibig, J.C., Andreasen, C.: Yield loss prediction models based on early estimation of weed pressure. Crop. Prot. 53, 125–131 (2013)CrossRefGoogle Scholar
  3. 3.
    Shi, L., Shen, M., Jiang, M.: Effect of long-term different fertilization management on weed community in rice-wheat rotation field. Sci. Agric. Sin. 46(02), 310–316 (2013)Google Scholar
  4. 4.
    Lake, E.C., Hough-Goldstein, J., Shropshire, K.J., et al.: Establishment and dispersal of the biological control weevil Rhinoncomimus latipes on mile-a-minute weed, Persicaria perfoliata. Biol. Control 58(3), 294–301 (2011)CrossRefGoogle Scholar
  5. 5.
    Radicetti, E., Mancinelli, R., Campiglia, E.: Impact of managing cover crop residues on the floristic composition and species diversity of the weed community of pepper crop (Capsicum annuum L.). Crop Protection. 44, 109–119 (2013)CrossRefGoogle Scholar
  6. 6.
    Cheng, C., Wan, K., Tao, Y., et al.: The effects of fertilization on weed communities and wheat growth in winter wheat (Triticum aestivum L.) field under different cropping rotations. Ecol. Environ. Sci. 22(03), 370–378 (2013)Google Scholar
  7. 7.
    Dong, C., Liu, Q., Gao, J., et al.: Effects of different fertilization models on the characteristics of weed communities during the rice growing seasons. Acta Prataculturae Sin. 22(03), 218–226 (2013)Google Scholar
  8. 8.
    Yang, R., Yongzhong, S.: Effects of cultivation regimes on weed community structures in newly reclaimed sandy farmlands. Chin. J. Eco-Agric. 18(06), 1218–1222 (2010)CrossRefGoogle Scholar
  9. 9.
    Dongjian, H., Yongliang, Q., Pan, L., et al.: Weed recognition based on SVM-DS multi-feature fusion. Trans. Chin. Soc. Agric. Mach. 44(02), 182–187 (2013)Google Scholar
  10. 10.
    Zhang, W., Bingjun, L., Shi, W.: Determination of vegetation coverage by photograph and automatic calculation. Bull. Soil Water Conserv. 29(02), 39–42 (2009)Google Scholar
  11. 11.
    Hu, L., Luo, X., Zeng, S., et al.: Plant recognition and localization for intra-row mechanical weeding device based on machine vision. Trans. Chin. Soc. Agric. Eng. 29(10), 12–18 (2013)Google Scholar
  12. 12.
    Bauer, T., Strauss, P.: A rule-based image analysis approach for calculating residues and vegetation cover under field conditions. CATENA 113, 363–369 (2014)CrossRefGoogle Scholar
  13. 13.
    Swain, K.C., Nørremark, M., Jørgensen, R.N., et al.: Weed identification using an automated active shape matching (AASM) technique. Biosyst. Eng. 110(4), 450–457 (2011)CrossRefGoogle Scholar
  14. 14.
    Tellaeche, A., Pajares, G., Burgos-Artizzu, X.P., et al.: A computer vision approach for weeds identification through Support Vector Machines. Appl. Soft Comput. 11(1), 908–915 (2011)CrossRefGoogle Scholar
  15. 15.
    Zhang, J., Yang, H.: Application of self-organizing neural networks to classification of plant communitiee in Panquangou nature reserve, North China. Acta Ecol. Sin. 27(03), 1005–1010 (2007)Google Scholar
  16. 16.
    Deyao, F., Qing, Y., Baojun, Y., et al.: Progress in research on intelligentization of field weed recognition and weed control technology. Sci. Agric. Sin. 43(09), 1823–1833 (2010)Google Scholar
  17. 17.
    Zhou, J., Wang, M., Shao, Q.: Adaptive segmentation of field image for green plants. Trans. Chin. Soc. Agric. Eng. 29(18), 163–170 (2013)Google Scholar
  18. 18.
    Zhang, D., Zhou, C., Zhou, Q., et al.: Hole-filling algorithm based on contour. J. Jilin Univ. (Sci. Ed.) 49(1), 82–86 (2011)MathSciNetGoogle Scholar
  19. 19.
    Zou, X., Ding, W., Liu, D., et al.: Classification of rice planthopper based on invariant moments and BP neural network. Trans. Chin. Soc. Agric. Eng. 29(18), 171–178 (2013)Google Scholar
  20. 20.
    Liu, X.: Study on data normalization in BP neural network. Mech. Eng. Autom. 03, 122–123 (2010)Google Scholar
  21. 21.
    Pulido, C., Solaque, L., Velasco, N.: Weed recognition by SVM texture feature classification in outdoor vegetable crop images. Ing. E Investig. 37(1), 68–74 (2017)CrossRefGoogle Scholar
  22. 22.
    Pantazi, X.-E., Moshou, D., Bravo, C.: Active learning system for weed species recognition based on hyperspectral sensing. Biosyst. Eng. 146(SI), 193–202 (2016)CrossRefGoogle Scholar
  23. 23.
    Rahman, M., Blackwell, B.: Smartphone-based hierarchical crowdsourcing for weed identification. Comput. Electron. Agric. 113, 14–23 (2015)CrossRefGoogle Scholar
  24. 24.
    Saha, D., Hanson, A. and Shin, S.Y.: Development of enhanced weed detection system with adaptive thresholding and support vector machine. In: Conference on Research in Adaptive and Convergent Systems (RACS). ACM, pp. 85–88 (2016)Google Scholar
  25. 25.
    Jianjiao, Y., Ji, Q., Fengwu, Z.: Study on identification of the field weed based on genetic neural network. J. Chin. Agric. Mech. 37(9), 223–226, 230 (2016)Google Scholar
  26. 26.
    Fenfang, L., Dongyan, Z., Wang Xiu, W., Taixia, C.X.: Identification of corn and weeds on the leaf scale using polarization spectroscopy. Infrared Laser Eng. 45(12), 361–370 (2016)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2019

Authors and Affiliations

  • Shengping Liu
    • 1
  • Junchan Wang
    • 2
  • Liu Tao
    • 3
  • Zhemin Li
    • 1
  • Chengming Sun
    • 3
  • Xiaochun Zhong
    • 1
    Email author
  1. 1.Institute of Agriculture Information, Chinese Academy of Agriculture Sciences/Key Laboratory of Agro-Information Services TechnologyMinistry of AgricultureBeijingChina
  2. 2.Lixiahe Regional Institute of Agricultural Sciences of Jiangsu ProvinceYangzhouChina
  3. 3.Jiangsu Key Laboratory of Crop Genetics and Physiology/Co-Innovation Center for Modern Production Technology of Grain CropsYangzhou UniversityYangzhouChina

Personalised recommendations