Abstract
Automatically identifying plants from images is a trending research domain due to its importance in production and science popularization. It attempts to classify the name of a plant with a known species from a given image. The majority of existing studies on automatic plant identification focus on identifying plants with the images of leaves and a few with other plant organs like flowers, fruits, branches, etc. Classification using a single organ is not sufficiently reliable because of its interclass similarity and intraclass dissimilarity among various species. Therefore, multiple organs of a plant can be used to automatically identify plant species with the help of classification techniques by multiple input-based Convolutional Neural Network (CNN). Among several plant species, citrus represents a vast spectrum of similar plants. The current investigation was carried out to evaluate the power of using multiple organs or components on multiple input CNN to classify similar-looking citrus species. Experiments were conducted to compare classification accuracies of a single component with multiple components based CNN in classifying 10 citrus species commonly found in the northern region of India. From the analysis of results, it was observed that leaves input having top-1 accuracy of 81.1% are better in discriminating species. When input from leaves, fruits, and entire plants are combined the classification accuracy is highest with 98.2% top-5 and 91.4% top-1 accuracies followed by a combination of leaves and fruits having 96.1% top-5 and 90.7% top-1 accuracies. In this study, it has been found out that flowers are insignificant in determining citrus plant species and cause classification accuracy to dip to top-1 89.6% when combined with all other organs.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Gaston, K.J., O’Neill, M.A.: Automated species identification: why not? Philos. Trans. R. Soc. B Biol. Sci. 359(1444), 655–667 (2004). https://doi.org/10.1098/rstb.2003.1442
Kumar, N., Belhumeur, P.N., Biswas, A., Jacobs, D.W., Kress, W., Lopez, I.C., Soares, J.V.: Leafsnap: a computer vision system for automatic plant species identification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 502–516. Springer, Heidelberg (2012)
Joly A, Goëau H, Glotin H, Spampinato C, Bonnet P, Vellinga W, Lombardo J, Planqué R, Palazzo S, Müller H.: LifeCLEF 2017 lab overview: multimedia species identification challenges. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction, vol. 10456, pp. 255–274 (2017). https://doi.org/10.1007/978-3-319-65813-1_24
Pl@ntNet. https://identify.plantnet.org/, Accessed 15 Dec 2020
iNaturalist. https://www.inaturalist.org/, Accessed 15 Dec 2020
Wäldchen, J., et al.: Automated plant species identification—trends and future directions. PLoS Comput. Biol. 14(4), 1–19 (2018). https://doi.org/10.1371/journal.pcbi.1005993
Jye, K.S., et al.: Automated plant identification using artificial neural network and support vector machine. Front. Life Sci. 10(1), 98–107 (2017). https://doi.org/10.1080/21553769.2017.1412361
Ghazi, M.M., Yanikoglu, B., Aptoula, E.: Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 235, 228–235 (2017). https://doi.org/10.1016/j.neucom.2017.01.018
Rzanny, M., et al.: Flowers, leaves or both? how to obtain suitable images for automated plant identification. Plant Methods 15(1), 1–11 (2019). https://doi.org/10.1186/s13007-019-0462-4
Lee, S.H., et al.: Multi-organ plant classification based on convolutional and recurrent neural networks. IEEE Trans. Image Process. 27(9), 4287–4301 (2018). https://doi.org/10.1109/TIP.2018.2836321
Hazarika, T.K.: Citrus genetic diversity of north-east India, their distribution, ecogeography and ecobiology. Genet. Res. Crop Evol. 59, 1267–1280 (2012). https://doi.org/10.1007/s10722-012-9846-2
Cerutti, G., et al.: Understansding leaves in natural images - a model-based approach for tree species identification. Comput. Vis. Image Underst. 117(10), 1482–1501 (2013). https://doi.org/10.1016/j.cviu.2013.07.003
Anami, B.S., et al.: A combined color, texture and edge features based approach for identification and classification of indian medicinal plants. Int. J. Comput. Appl. 6(12), 45–51 (2010). https://doi.org/10.5120/1122-1471
Caglayan, A., et al.: A plant recognition approach using shape and color features in leaf images. In: Petrosino, A. (ed.) Image Analysis and Processing – ICIAP 2013. ICIAP 2013. Lecture Notes in Computer Science, vol. 8157. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41184-7_17.
Munisami, T., et al.: Plant leaf recognition using shape features and colour histogram with K-nearest neighbour classifiers. Procedia Comput. Sci. 58, 740–747 (2015). https://doi.org/10.1016/j.procs.2015.08.095
Wang, X.F., et al.: Recognition of leaf images based on shape features using a hypersphere classifier. In: Huang, D.S., Zhang, X.P., Huang, G.B. (eds.) Advances in Intelligent Computing. ICIC 2005. Lecture Notes in Computer Science, vol 3644. Springer, Heidelberg (2005). https://doi.org/10.1007/11538059_10.
Larese, M.G., et al.: Automatic classification of legumes using leaf vein image features. Pattern Recogn. 47(1), 158–168 (2014). https://doi.org/10.1016/j.patcog.2013.06.012
Larese, M.G., et al.: Legume identification by leaf vein images classification. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2012. Lecture Notes in Computer Science, vol 7441. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33275-3_55
Tan, J.W., et al.: Deep learning for plant species classification using leaf vein morphometric. IEEE/ACM Trans. Comput. Biol. Bioinf. 17(1), 82–90 (2020). https://doi.org/10.1109/TCBB.2018.2848653
Grinblat, G.L., et al.: Deep learning for plant identification using vein morphological patterns. Comput. Electron. Agric. 127(C), 418–424 (2016). https://doi.org/10.1016/j.compag.2016.07.003
Lee, S.H., et al.: How deep learning extracts and learns leaf features for plant classification. Pattern Recogn. 71, 1–13 (2017). https://doi.org/10.1016/j.patcog.2017.05.015
Krizhevsky, A., et al.: ImageNet classification with deep convolutional neural networks. Neural Inf. Process. Syst. 25, 1097–1105 (2012). https://doi.org/10.1145/3065386
Goëau, H., et al.: Deep learning for plant identification: how the web can compete with human experts. Biodiv. Inf. Sci. Stand. 2, e25637 (2018). https://doi.org/10.3897/biss.2.25637
Sun, Y. et al.: Deep learning for plant identification in natural environment. Comput. Intell. Neurosci. 2017, Article id. 7361042 (2017). https://doi.org/10.1155/2017/7361042
Krause, J., et al.: WTPlant (What’s that plant?): a deep learning system for identifying plants in natural images. In: ACM 2018 Proceedings on International Conference on Multimedia Retrieval, pp. 517–520 (2018). https://doi.org/10.1145/3206025.3206089
Mureşan, H., Oltean, M.: Fruit recognition from images using deep learning. Acta Universitatis Sapientiae Informatica 10(1), 26–42 (2018). https://doi.org/10.2478/ausi-2018-0002
Gurnani, A., Mavani, V., et al.: Flower categorization using deep convolutional neural networks. arXiv preprint arXiv:1708.03763 (2017)
Hiary, H., et al.: Flower classification using deep convolutional neural networks. IET Comput. Vision 12(6), 855–862 (2018). https://doi.org/10.1049/iet-cvi.2017.0155
Gogul, I., Kumar, V.S.: Flower species recognition system using convolution neural networks and transfer learning. In: 2017 4th International Conference on Signal Processing, Communication and Networking, ICSCN 2017, 1–6 November 2017 (2017). https://doi.org/10.1109/ICSCN.2017.8085675.
Seeland, M., Rzanny, M., et al.: Correction: plant species classification using flower images—a comparative study of local feature representations. PLoS ONE 12(3), e0175101 (2017). https://doi.org/10.1371/journal.pone.0175101
Goëau, H., et al.: The ImageCLEF 2013 plant identification task. In: Proceedings of the 2nd ACM international workshop on Multimedia analysis for ecological data, 23–28 October 2013 (2013). https://doi.org/10.1145/2509896.2509902
Do, T.B., et al.: Plant identification using score-based fusion of multi-organ images. In: Proceedings on 9th International Conference on Knowledge and System Engineering, pp. 191–196 (2017). https://doi.org/10.1109/KSE.2017.8119457
He, A., Tian, X.: Multi-organ plant identification with multi-column deep convolutional neural networks. In: Proceedings on 2016 IEEE International Conference on System, Man, Cybernetics (SMC), pp. 2020–2025 (2017). https://doi.org/10.1109/SMC.2016.7844537
Lee, S.H. et al.: HGO-CNN: hybrid generic-organ convolutional neural network for multi-organ plant classification. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 4462–4466 (2017). https://doi.org/10.1109/ICIP.2017.8297126
Seeland, M., et al.: Image-based classification of plant genus and family for trained and untrained plant species. BMC Bioinf. 20(1), 1–13 (2019). https://doi.org/10.1186/s12859-018-2474-x
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Sharma, P., Abrol, P. (2022). Analysis of Multiple Component Based CNN for Similar Citrus Species Classification. In: Gunjan, V.K., Zurada, J.M. (eds) Modern Approaches in Machine Learning & Cognitive Science: A Walkthrough. Studies in Computational Intelligence, vol 1027. Springer, Cham. https://doi.org/10.1007/978-3-030-96634-8_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-96634-8_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96633-1
Online ISBN: 978-3-030-96634-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)