Evaluation and Analysis of Plant Classification System Based on Feature Level Fusion and Score Level Fusion

  • Pradip Salve
  • Pravin YannawarEmail author
  • Milind SardesaiEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1037)


This paper describes the automatic leaf recognition based on feature level fusion and score level fusion of vein orientation angles, GLCM, SIFT, SURF as a features. However, to obtain the sophisticated leaf recognition, the system must be undergo through numerous difficulties such as intra and inter-class variations in plants and defining the proper local and global image descriptors which can deal with the color, shape and textual, information for the classification. Selection of the meticulous features plays key role in designing the best classification system. In this paper we proposed multi-modal plant classification where several components are fused together for a more precise classification. The results shows that the proposed system for feature level fusion achieved 93.72% GAR with 6.27% of EER and for score level fusion system achieves 97.13% GAR and 2.86% EER. It is found that the performance of the classification has been increased by 3.79% of EER when score level fusion applied to the system.


Leaf veins Plant recognition Plant classification Leaf features 



The authors would like to acknowledge Department of Computer Science & IT, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad, Maharashtra, India providing support for the infrastructure during the research work and UGC-MANF fellowship for financial support.


  1. 1.
    Fern, B.M., et al.: Stratified classification of plant species based on venation state. Biomed. Res. 28(13), 5660–5663 (2017)Google Scholar
  2. 2.
    Salve, P., Sardesai, M., Manza, R., Yannawar, P.: Identification of the plants based on leaf shape descriptors. In: Satapathy, S.C., Raju, K.S., Mandal, J.K., Bhateja, V. (eds.) Proceedings of the Second International Conference on Computer and Communication Technologies. AISC, vol. 379, pp. 85–101. Springer, New Delhi (2016). Scholar
  3. 3.
    Bonnet, P., et al.: Plant identification: experts vs. machines in the era of deep learning. In: Joly, A., Vrochidis, S., Karatzas, K., Karppinen, A., Bonnet, P. (eds.) Multimedia Tools and Applications for Environmental & Biodiversity Informatics. MMSA, vol. 379, pp. 131–149. Springer, Cham (2018). Scholar
  4. 4.
    Amlekar, M., Manza, R.R., Yannawar, P., Gaikwad, A.T.: Plant classification based on leaf features. IBMRD’s J. Manag. Res. 5(1), 30–34 (2016)Google Scholar
  5. 5.
    Amlekar, M.M., Ashok T.G.: Plant classification based on leaf Shape features using Neural Network. Int. J. Adv. Res. Sci. Eng. 635–639 (2017)Google Scholar
  6. 6.
    Rahmadhani, M., Herdiyeni, Y.: Shape and vein extraction on plant leaf images using Fourier and B-spline modeling. In: AFITA International Conference, the Quality Information for Competitive Agricultural Based Production System and Commerce, pp. 306–310 (2010)Google Scholar
  7. 7.
    Sun, Z., Lu, S., Guo, X., Tian, Y.: Leaf vein and contour extraction from point cloud data. In: 2011 International Conference on Virtual Reality and Visualization (ICVRV), pp. 11–16. IEEE (2011)Google Scholar
  8. 8.
    Clarke, J., et al.: Venation pattern analysis of leaf images. In: Bebis, G., et al. (eds.) ISVC 2006. LNCS, vol. 4292, pp. 427–436. Springer, Heidelberg (2006). Scholar
  9. 9.
    Siravenha, A.C., Carvalho, S.R.: Plant classification from leaf textures. In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, QLD, pp. 1–8 (2016).
  10. 10.
    Goeau, H., Bonnet, P., Joly, A.: Plant identification based on noisy web data: the amazing performance of deep learning. In: CLEF 2017-Conference and Labs of the Evaluation Forum (LifeCLEF 2017) (2017)Google Scholar
  11. 11.
    Wu, S.G., Bao, F.S., Xu, E.Y., Wang, Y., Chang, Y., Xiang, Q.: A leaf recognition algorithm for plant classification using probabilistic neural network. In: IEEE 7th International Symposium on Signal Processing and Information Technology, Cairo, Egypt (2007)Google Scholar
  12. 12.
    Prasad, S., Kumar, P.S., Ghosh, D.: An efficient low vision plant leaf shape identification system for smart phones. Multimed. Tools Appl. 76(5), 6915–6939 (2017)CrossRefGoogle Scholar
  13. 13.
    Chaki, J., Parekh, R., Bhattacharya, S.: Plant leaf classification using multiple descriptors: a hierarchical approach. J. King Saud Univ.-Comput. Inf. Sci. (2018), ISSN 1319-1578.
  14. 14.
    Hamrouni, L., Bensaci, R., Kherfi, M.L., Khaldi, B., Aiadi, O.: Automatic recognition of plant leaves using parallel combination of classifiers. In: Amine, A., Mouhoub, M., Ait Mohamed, O., Djebbar, B. (eds.) CIIA 2018. IAICT, vol. 522, pp. 597–606. Springer, Cham (2018). Scholar
  15. 15.
    Lee, S.H., Chee, S.C., Simon, J.M., Remagnino, P.: How deep learning extracts and learns leaf features for plant classification. Pattern Recogn. 71, 1–13 (2017)CrossRefGoogle Scholar
  16. 16.
    Zhang, S., Wang, H., Huang, W.: Two-stage plant species recognition by local mean clustering and Weighted sparse representation classification. Cluster Comput. 20(2), 1517–1525 (2017)CrossRefGoogle Scholar
  17. 17.
    Murat, M., Chang, S.-W., Abu, A., Yap, H.J., Yong, K.-T.: Automated classification of tropical shrub species: a hybrid of leaf shape and machine learning approach. PeerJ 5, e3792 (2017)CrossRefGoogle Scholar
  18. 18.
    Pawara, P., Okafor, E., Surinta, O., Schomaker, L., Wiering, M.: Comparing local descriptors and bags of visual words to deep convolutional neural networks for plant recognition. In: ICPRAM, pp. 479–486 (2017)Google Scholar
  19. 19.
    Ghazi, M.M., Yanikoglu, B., Aptoula, E.: Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 235, 228–235 (2017)CrossRefGoogle Scholar
  20. 20.
    Barre, P., Stőver, B.C., Müller, K.F., Steinhage, V.: LeafNet: a computer vision system for automatic plant species identification. Ecol. Inf. 40, 50–56 (2017)CrossRefGoogle Scholar
  21. 21.
    Goeau, H., Bonnet, P., Joly, A.: Plant identification based on noisy web data: the amazing performance of deep learning. In: CLEF 2017-Conference and Labs of the Evaluation Forum (LifeCLEF 2017), pp. 1–13 (2017)Google Scholar
  22. 22.
    Lasseck, M.: Image-based plant species identification with deep convolutional neural networks. In: Working Notes of CLEF 2017 (2017)Google Scholar
  23. 23.
    Santosh, K.C., Antani, S., Thoma, G.: Stitched multipanel biomedical figure separation. In: 2015 IEEE 28th International Symposium on Computer-Based Medical Systems (CBMS), pp. 54–59. IEEE (2015)Google Scholar
  24. 24.
    Santosh, K.C., Wendling, L., Antani, S., Thoma, G.R.: Overlaid arrow detection for labeling regions of interest in biomedical images. IEEE Intell. Syst. 31(3), 66–75 (2016)CrossRefGoogle Scholar
  25. 25.
    Candemir, S., Borovikov, E., Santosh, K.C., Antani, S., Thoma, G.: RSILC: rotation-and scale-invariant, line-based color-aware descriptor. Image Vis. Comput. 42, 1–12 (2015)CrossRefGoogle Scholar
  26. 26.
    Fouad, M.M.M., Zawbaa, H.M., El-Bendary, N., Hassanien, A.E.: Automatic Nile Tilapia fish classification approach using machine learning techniques. In: 2013 13th International Conference on Hybrid Intelligent Systems (HIS), pp. 173–178. IEEE (2013)Google Scholar
  27. 27.
    Mistry, D., Banerjee, A.: Comparison of feature detection and matching approaches: SIFT and SURF. GRD J.- Global Res. Dev. J. Eng. 2(4), 7–13 (2017), ISSN 2455-5703Google Scholar
  28. 28.
    Herbert, B., Andreas, E., Tinne, T., Luc, V.G.: Speeded up robust feature (SURF). J. Comput. Vis. Image Underst. 110(3), 346–359 (2008)CrossRefGoogle Scholar
  29. 29.
    Utsav, S., Darshana, M., Asim, B.: Image registration of multi-view satellite images using best feature points detection and matching methods from SURF. SIFT PCA-SIFT 1(1), 8–18 (2014)Google Scholar
  30. 30.
    Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: SURF: speeded up robust features. Comput. Vis. Image Underst. (CVIU) 110(3), 346–359 (2008)CrossRefGoogle Scholar
  31. 31.
    Vijayakumar, V., Neelanarayanan, V., Veeramuthu, A., Meenakshi, S., PriyaDarsini, V.: Big data, cloud and computing challengesbrain image classification using learning machine approach and brain structure analysis. Proc. Comput. Sci. 50, 388–394 (2015)CrossRefGoogle Scholar
  32. 32.
    Shijin, K.P.S., Dharun, V.S.: Extraction of texture features using GLCM and shape features using connected regions. Int. J. Eng. Technol. (IJET) 8(6), 2926–2930 (2016)CrossRefGoogle Scholar
  33. 33.
    Salve, P., Yannawar, P., Sardesai, M.: Multimodal plant recognition through hybrid feature fusion technique using imaging and non-imaging hyper-spectral data. J. King Saud Univ. - Comput. Inf. Sci. (2018), ISSN 1319-1578.
  34. 34.
    Salve, P., Sardesai, M., Yannawar, P.: Classification of plants using GIST and LBP score level fusion. In: Thampi, S.M., Marques, O., Krishnan, S., Li, K.-C., Ciuonzo, D., Kolekar, M.H. (eds.) SIRS 2018. CCIS, vol. 968, pp. 15–29. Springer, Singapore (2019). Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Vision and Intelligence Lab, Department of Computer Science and ITDr. Babasaheb Ambedkar Marathwada UniversityAurangabadIndia
  2. 2.Floristic Research Lab, Department of BotanySavitribai Phule Pune UniversityPuneIndia

Personalised recommendations