Abstract
The main problem addressed in this work is the creation of a Region Based Convolutional Neural Networks (R-CNN) plant diseases detector. The platform for plant disease detection pdd.jinr.ru exists several years, but, we still searching for new functionality. Our current architecture for disease classification by images is based on the Siamese neural network with a triplet loss function. One of the main reasons for the development of this R-CNN detector is difficulties in classification when users send photos where diseased leaves are present in much less space than healthy ones. In such cases, it is necessary to accurately indicate the infected leaves for their further treatment. Infected leaves could be framed and have inscriptions corresponding to the name of the disease with an R-CNN.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
A. Uzhinskiy, G. Ososkov, P. Goncharov, and A. Nechaevskiy, “Multifunctional platform and mobile application for plant disease detection,” in CEUR Workshop Proceedings of the 27th Symposium on Nuclear Electronics and Computing NEC 2019 (2019), pp. 110–114.
R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580–587. https://doi.org/10.1109/CVPR.2014.81
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the Conference on Computer Vision and Pattern Recognition, 2016, p. 13. https://doi.org/10.1109/CVPR.2016.91
J. R. Uijlings, K. E. van de Sande, T. Gevers, and A. W. Smeulders, “Selective search for object recognition,” Int. J. Comput. Vision 104, 154–171 (2013).
R. Rasmus, G. Matthieu, and L. van Gool, “Non-maximum suppression for object detection by passing messages between windows,” Lect. Notes Comput. Sci. 9003, 290 (2015). https://doi.org/10.1007/978-3-319-16865-4_19
D. Cheng, Y. Gong, S. Zhou, J. Wang, and N. Zheng, “Person re-identification by multi-channel parts-based CNN with improved triplet loss function,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR (2016), pp. 1335–1344.
A. Uzhinskiy, G. Ososkov, P. Goncharov, A. Nechaevskiy, and A. Smetanin, “Oneshot learning with triplet loss for vegetation classification tasks,” Comput. Opt. 45, 608–614 (2021). https://doi.org/10.18287/2412-6179-CO-856
F. Schroff, D. Kalenichenko, and J. Philbin, “A unified embedding for face recognition and clustering,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition CVPR (2015), pp. 815–823.
Funding
Authors gratefully acknowledge financial support from the Ministry of Science and Higher Education of the Russian Federation in accordance with agreement no. 075-15-2020-905 dated November 16, 2020, on providing a grant in the form of subsidies from the Federal budget of Russian Federation. The grant was provided for state support for the creation and development of a World-class Scientific Center “Agrotechnologies for the Future”.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Rights and permissions
About this article
Cite this article
Gerasimchuk, M., Uzhinskiy, A. R-CCN Plant Diseases Detector Using Triples Loss and Siamese Neural Networks. Phys. Part. Nuclei Lett. 19, 570–573 (2022). https://doi.org/10.1134/S1547477122050193
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1547477122050193