APPLE CROPS FOLIAR DISEASES CLASSIFICATION BY COMPUTER VISION METHODS
Abstract
Background. Development of a convolutional neural network model for detecting foliar diseases of apple trees from a photo of leaves from a mobile phone.
Materials and methods. The material for the research was taken images with various types of apple’s foliar diseases, published in open access of the Kaggle platform. Research methods: theory of design and development of information systems, programming, methods of augmentation and extension of datasets for computer vision problems, methods of tuning hyperparameters for training neural network models.
Results. Apple (Malus) is a perennial tree of the genus Malus. Apples are the main fruit crop in Russia. The apple tree as a fruit crop is widespread in almost all temperate countries, in Russia it is grown everywhere – from the northern regions to the south [3]. Diseases of apple trees are one of the main reasons for the decline in the yield of orchards around the world. For the prevention and early warning of the spread of apple tree diseases, a tool is needed in the form of a neural network model that allows you to determine the presence of the disease from a smartphone photo of apple leaves. The methods of deep learning of convolutional neural networks, as well as the concept of “transfer learning”, were used in the work. A neural network was trained on the basis of the EfficientNet network, which allows to determine the presence of non-root diseases of apple trees by the image of leaves with an accuracy of 0.985 using the F1-score metric.
Conclusion. The data set of apple’s leaves images, including four classes, was prepared for efficient classification by a neural network. Two classes with signs of a certain apple tree disease, one class for having more than one disease, and one class for healthy apple trees. A model was built and trained for classification task of detecting apple tree disease from images of leaves from a smartphone.
Downloads
References
Tutygin V.S., Lelyukhin D.O. Sistema diagnostiki zabolevaniy list’ev rasteniy po fotoizobrazheniyam, poluchennym s pomoshch’yu BPLA [A system for diagnosing plant leaf diseases based on photographs obtained with the help of BPLA]. Materialy nauchnoy konferentsii «Nedelya nauki SPbPU». Sankt-Peterburg, 19–24 noyabrya 2018 [Materials of the scientific conference “Science Week of SPbPU”. St. Petersburg, 19-24 November 2018].
Apples, AGRARII. https://agrarii.com/jablonja/ (accessed 20.03.2021).
Apples, AgroWIKI. https://agrostrana.ru/wiki/305 (accessed 20.03.2021).
Amara J., Bouaziz B., Algergawy A. A Deep Learning-based Approach for Banana Leaf Diseases Classification. Conference Datenbanksysteme für Business, Technologie und Web. January 2017. http://btw2017.informatik.uni-stuttgart.de/slidesandpapers/E1-10/paper_web.pdf (дата обращения: 20.03.2021).
Reyes A.K., Caicedo J.C., Camargo J.E. Fine-tuning Deep Convolutional Networks for Plant Recognition. Conference and Labs of the Evaluation Forum - CLEF 2015. http://ceur-ws.org/Vol-1391/121-CR.pdf
Al-Hiary H., Bani-Ah Mad S., Reyalat M., Braik M., ALRahamneh Z. Fast and Accurate Detection and Classification of Plant Diseases. International Journal of Computer Applications (0975 – 8887), March 2011, vol. 17, no. 1, pp. 31-38. https://doi.org/10.5120/2183-2754
Ginsburg I. Exploring convolutional neural network architectures with fast.ai. https://proglib.io/p/issleduem-arhitektury-svertochnyh-neyronnyh-setey-s-pomoshchyu-fast-ai-2020-12-28 (accessed 20.03.2021).
Goncharov P., Nechaevskiy A., Ososkov G., Uzhinskiy A. Disease Detection on the Plant Leaves by Deep Learning. Papers from the XX International Conference on Neuroinformatics. October 8-12, 2018, Moscow, Russia. Advances in Neural Computation, Machine Learning, and Cognitive Research II. pp.151-159. https://doi.org/10.1007/978-3-030-01328-8_16
Rahman C. R., Arko P. S., Ali M. E., Khan M. A. I., Apon S. H., Nowrin F., Wasif A. Identification and Recognition of Rice Diseases and Pests Using Convolutional Neural Networks. Biosystems Engineering, June 2020, vol. 194, pp. 112-120. https://doi.org/10.1016/j.biosystemseng.2020.03.020
Khirade S.D., Patil A.B. Plant Disease Detection Using Image Processing. 2015 International Conference on Computing Communication Control and Automation. 2015, pp. 768-771. https://doi.org/10.1109/ICCUBEA.2015.153
Lee D., Back C. et al. Biological Characterization of Marssonina coronaria Associated with Apple Blotch Disease. Mycobiology, 2011, vol. 39, no. 3. https://doi.org/10.5941/MYCO.2011.39.3.200
Liu B., Zhang Y., He D., Li Y.: Identification of apple leaf diseases based on deep convolutional neural networks. Symmetry, 2017. vol. 10, no. 1, 11. https://doi.org/10.3390/sym10010011
Mahlein A. Plant Disease Detection by Imaging Sensors – Parallels and Specific Demands for Precision Agriculture and Plant Phenotyping. Computational Intelligence and Neuroscience, June 2016. https://doi.org/10.1155/2016/3289801
Mwebaze E., Gebru T., Frome A., Nsumba S., Tusubira J. iCassava 2019 Fine-Grained Visual Categorization Challenge. https://arxiv.org/abs/1908.02900 (accessed 20.03.2021).
Phadikar S., Sil J. Rice Disease Identification Using Pattern Recognition Techniques. 2008 11th International Conference on Computer and Information Technology. J24-27, Dec. 2008. https://doi.org/10.1109/ICCITECHN.2008.4803079
Plant Pathology 2020 - FGVC7, Kaggle. https://www.kaggle.com/c/plant-pathology-2020-fgvc7/overview (accessed 20.03.2021).
Revathi P., Hemalatha M. Classification of Cotton Leaf Spot Diseases Using Image Processing Edge Detection Techniques. International Conference on Emerging Trends in Science, Engineering and Technology (INCOSET). 13-14 Dec. 2012. https://doi.org/10.1109/INCOSET.2012.6513900
Sagar A., J Dheeba J. On Using Transfer Learning For Plant Disease Detection. https://www.biorxiv.org/content/10.1101/2020.05.22.110957v1.full (accessed 20.03.2021).
Sladojevic S., Arsenovic M., Anderla A., Culibrk D. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification. Computational Intelligence and Neuroscience, June 2016. P. 1-11. https://doi.org/10.1155/2016/3289801
Tan M., Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. hhttps://arxiv.org/pdf/1905.11946.pdf (accessed 20.03.2021).
Karmokar B. C, Ullah M. S., Siddiquee Md. K., Alam K. Md. R. Tea leaf diseases recognition using neural network ensemble. International Journal of Computer Applications, March 2015, vol. 114, no. 17, pp. 27-30. http://dx.doi.org/10.5120/20071-1993
Tete T. N., Kamlu S. Plant Disease Detection Using Different Algorithms. Proceedings of the Second International Conference on Research in Intelligent and Computing in Engineering, June 2017, vol. 10, pp. 103–106. https://doi.org/10.15439/2017R24
Thapa R., Snavely N., Belongie S., Khan A. The Plant Pathology 2020 challenge dataset to classify foliar disease of apples. https://arxiv.org/pdf/2004.11958.pdf (accessed 20.03.2021).
Osipov A.L., Bobrov L.K. The use of statistical models of recognition in the virtual screening of chemical compounds. Automatic Documentation and Mathematical Linguistics, 2012, vol. 46, no. 4, pp. 153-158. https://link.springer.com/article/10.3103/S0005105512040024
Copyright (c) 2021 Sergei N. Tereshchenko, Artem A. Perov, Alexander L. Osipov
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
