Abstract
Plant diseases are one of the main causes of crop loss in agriculture. Machine Learning, in particular statistical and neural nets (NNs) approaches, have been used to help farmers identify plant diseases. However, since new diseases continue to appear in agriculture due to climate change and other factors, we need more data-efficient approaches to identify and classify new diseases as early as possible. Even though statistical machine learning approaches and neural nets have demonstrated state-of-the-art results on many classification tasks, they usually require a large amount of training data. This may not be available for emergent plant diseases. So, data-efficient approaches are essential for an early and precise diagnosis of new plant diseases and necessary to prevent the disease’s spread. This study explores a data-efficient Inductive Logic Programming (ILP) approach for plant disease classification. We compare some ILP algorithms (including our new implementation, PyGol) with several statistical and neural-net based machine learning algorithms on the task of tomato plant disease classification with varying sizes of training data set (6, 10, 50 and 100 training images per disease class). The results suggest that ILP outperforms other learning algorithms and this is more evident when fewer training data are available.
Keywords
- Few-shot Learning
- Data Efficient Machine Learning
- ILP
- Inverse Entailment
- Plant Disease Classification
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Available from: https://github.com/danyvarghese/PyGol.
References
Machine Learning. McGraw Hill (1997)
Algorithmia’: 2020 state of enterprise machine learning. https://algorithmia.com/state-of-ml
Argüeso, D., et al.: Few-shot learning approach for plant disease classification using images taken in the field. Comput. Electron. Agric. 175, 105542 (2020)
Armi, L., Fekri-Ershad, S.: Texture image analysis and texture classification methods - a review (2019). https://doi.org/10.48550/ARXIV.1904.06554. https://arxiv.org/abs/1904.06554
Babapour Mofrad, F., Valizadeh, G.: A comprehensive survey on two and three-dimensional Fourier shape descriptors: biomedical applications. Arch. Comput. Methods Eng. 29(7), 4643–4681 (2022)
Brian Hudelson, U.: Early blight. https://hort.extension.wisc.edu/articles/early-blight/
Chen, L., Cui, X., Li, W.: Meta-learning for few-shot plant disease detection. Foods 10, 2441 (2021). https://doi.org/10.3390/foods10102441
Chen, Z., et al.: Plant disease recognition model based on improved yolov5. Agronomy 12(2), 365 (2022)
Cropper, A.: Metgol - an ILP system based on meta-iterpretive learning (2016). https://github.com/metagol/metagol
Dai, W.Z., Muggleton, S., Wen, J., Tamaddoni-Nezhad, A., Zhou, Z.H.: Logical vision: one-shot meta-interpretive learning from real images. In: ILP (2017)
Davis, R., Miyao, G., Subbarao, K., Stapleton, J., Aegerter, B.: Tomato yellow leaf curl. https://www2.ipm.ucanr.edu/agriculture/tomato/Tomato-Yellow-Leaf-Curl/
Fink, M.: Object classification from a single example utilizing class relevance metrics. In: Advances in Neural Information Processing Systems, vol. 17 (2004)
Garcia, V., Bruna, J.: Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043 (2017)
Garden, M.B.: Septoria leaf spot of tomato. https://www.missouribotanicalgarden.org/gardens-gardening/your-garden/help-for-the-home-gardener/advice-tips-resources/pests-and-problems/diseases/fungal-spots/septoria-leaf-spot-of-tomato.aspx
Gevens, A., Seidl, A., Brian Hudelson, U.: Late blight. https://hort.extension.wisc.edu/articles/late-blight/
GmbH, P.: Plantix : a mobile crop advisory app for farmers, extension workers and gardeners (2015). https://plantix.net/en/
Harakannanavar, S.S., Rudagi, J.M., Puranikmath, V.I., Siddiqua, A., Pramodhini, R.: Plant leaf disease detection using computer vision and machine learning algorithms. Glob. Trans. Proc. 3(1), 305–310 (2022)
Hinek, J.P.: How long does it take to build an ml model?. https://m.mage.ai/how-long-does-it-take-to-build-an-ml-model-d68b8afa50a5
Hong, T.C.K., Economou, A.: What shape grammars do that cad should: the 14 cases of shape embedding. Artif. Intell. Eng. Des. Anal. Manuf. 36, e4 (2022). https://doi.org/10.1017/S0890060421000263
Hu, M.K.: Visual pattern recognition by moment invariants. IRE Trans. Inf. Theory 8(2), 179–187 (1962)
Huang, H.P., Puvvada, K.C., Sun, M., Wang, C.: Unsupervised and semi-supervised few-shot acoustic event classification. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 331–335. IEEE (2021)
Huang, Z., Leng, J.: Analysis of Hu’s moment invariants on image scaling and rotation, vol. 7, pp. V7–476 (2010)
Hughes, D.P., Salathe, M.: An open access repository of images on plant health to enable the development of mobile disease diagnostics (2015)
Iseli, M.: Mosaic virus - is my plant infected? identification & treatment. https://plantophiles.com/plant-care/mosaic-virus-symptoms-and-treatments/
Joshi, K., Awale, R., Ahmad, S., Patil, S., Pisal, V.: Plant leaf disease detection using computer vision techniques and machine learnings. In: ITM Web of Conferences (2022)
KSaradhambal, G., D.R.L.S.R.R.: Plant disease detection and its solution using image classification. Int. J. Pure Appl. Math. 119 (2018). https://doi.org/10.1051/itmconf/20224403002
Lake, B., Salakhutdinov, R., Tenenbaum, J.: One-shot learning by inverting a compositional causal process. In: Advances in Neural Information Processing Systems (2013), 27th Annual Conference on Neural Information Processing Systems, NIPS 2013, 05–10-December-2013 (2013)
Li, Y., Chao, X.: Semi-supervised few-shot learning approach for plant diseases recognition. Plant Methods 17, 1–10 (2021)
Li Fe-Fei, Fergus, Perona: A bayesian approach to unsupervised one-shot learning of object categories. In: Proceedings Ninth IEEE International Conference on Computer Vision, vol. 2, pp. 1134–1141 (2003)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)
Lu, J., Ehsani, R., Shi, Y., De Castro, A., Wang, S.: Detection of multi-tomato leaf diseases (late blight, target and bacterial spots) in different stages by using a spectral-based sensor. Sci. Rep. 8, 2793 (2018)
Lu, J., Zhou, M., Gao, Y., Jiang, H.: Using hyperspectral imaging to discriminate yellow leaf curl disease in tomato leaves. Precis. Agric. 19, 1–16 (2018)
McAvoy, G.: Take the right aim to tame target spot of tomato. https://www.growingproduce.com/vegetables/take-the-right-aim-to-tame-target-spot-of-tomato/
Michelle Marks, U.: Bacterial spot of tomato. https://hort.extension.wisc.edu/articles/bacterial-spot-of-tomato/
Mohanty, S.: Plantvillage-dataset. https://github.com/spMohanty/PlantVillage-Dataset
Muggleton, S., Dai, W.Z., Sammut, C., Tamaddoni-Nezhad, A.: Meta-interpretive learning from noisy images. Mach. Learn. 107, 1097–1118 (2018)
Muggleton, S., de Raedt, L.: Inductive logic programming: theory and methods. J. Logic Program. 19–20, 629–679 (1994). Special Issue: Ten Years of Logic Programming
Muggleton, S., Lin, D., Tamaddoni-Nezhad, A.: Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Mach. Learn. 100, 49–73 (2015)
Müller, T., Pérez-Torró, G., Basile, A., Franco-Salvador, M.: Active few-shot learning with fasl. arXiv preprint arXiv:2204.09347 (2022)
Narwade Manoorkar, J., Kumar, D.B.: Local and Global Color Histogram Feature for Color Content-Based Image Retrieval System, pp. 293–300 (2016)
Ökten, İ, Yüzgeç, U.: Rice plant disease detection using image processing and probabilistic neural network. In: Seyman, M.N. (ed.) Electrical and Computer Engineering, pp. 82–94. Springer International Publishing, Cham (2022). https://doi.org/10.1007/978-3-031-01984-5_7
Qi, A., Gryaditskaya, Y., Xiang, T., Song, Y.Z.: One sketch for all: one-shot personalized sketch segmentation. IEEE Trans. Image Process. 31, 2673–2682 (2022)
Radovanović, D., Ukanovic, S.: Image-based plant disease detection: a comparison of deep learning and classical machine learning algorithms. In: 2020 24th International Conference on Information Technology (IT), pp. 1–4 (2020)
Reganold, J.P., Papendick, R.I., Parr, J.F.: Sustainable agriculture. Sci. Am. 262(6), 112–121 (1990)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)
RHS: Tomato leaf mould. https://www.rhs.org.uk/disease/tomato-leaf-mould
Sharma, P., Berwal, Y., Ghai, W.: Performance analysis of deep learning CNN models for disease detection in plants using image segmentation. Inf. Process. Agric. 7, 566–574 (2019)
Spengler, T.: What are two-spotted spider mites - two-spotted mite damage and control insects. https://www.gardeningknowhow.com/plant-problems/pests/insects/two-spotted-spider-mite-control.htm
Srinivasan, A.: A learning engine for proposing hypotheses (aleph) (2001). https://www.cs.ox.ac.uk/activities/programinduction/Aleph/aleph.html
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. CoRR (2019)
Tamaddoni-Nezhad, A.: Metagol_nt. https://github.com/atnezhad/Metagol_NT
Tekol, Y., contributors: PySwip v0.2.10 (2020). https://github.com/yuce/pyswip
Türkoğlu, M., Yanikoglu, B., Hanbay, D.: Plantdiseasenet: convolutional neural network ensemble for plant disease and pest detection. Signal Image Video Process. 16(2), 301–309 (2022)
Varghese, D.: Metagol_nt. https://github.com/danyvarghese/Metagol_NT
Varghese, D., Bauer, R., Baxter-Beard, D., Muggleton, S., Tamaddoni-Nezhad, A.: Human-like rule learning from images using one-shot hypothesis derivation. In: Katzouris, N., Artikis, A. (eds.) Inductive Logic Programming, pp. 234–250. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97454-1_17
Varghese, D., Tamaddoni-Nezhad, A.: One-shot rule learning for challenging character recognition. In: Proceedings of the 14th International Rule Challenge, Oslo, Norway, vol. 2644, pp. 10–27 (2020)
Varghese, D., Tamaddoni-Nezhad, A.: Pyilp (2022). https://github.com/danyvarghese/PyILP/
Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. 53(3), 1–34 (2020)
Ying, Z.: Weakly-supervised diagnosis with attention models (2022)
Yu, Z., Chen, L., Cheng, Z., Luo, J.: Transmatch: a transfer-learning scheme for semi-supervised few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12856–12864 (2020)
Zhu, P., Zhu, Z., Wang, Y., Zhang, J., Zhao, S.: Multi-granularity episodic contrastive learning for few-shot learning. Pattern Recognit. 131, 108820 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Varghese, D., Patel, U., Krause, P., Tamaddoni-Nezhad, A. (2023). Few-Shot Learning for Plant Disease Classification Using ILP. In: Garg, D., Narayana, V.A., Suganthan, P.N., Anguera, J., Koppula, V.K., Gupta, S.K. (eds) Advanced Computing. IACC 2022. Communications in Computer and Information Science, vol 1781. Springer, Cham. https://doi.org/10.1007/978-3-031-35641-4_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-35641-4_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35640-7
Online ISBN: 978-3-031-35641-4
eBook Packages: Computer ScienceComputer Science (R0)